Continuous line for automatic diamond color grading evaluation

Abstract

The automatic diamond color grader can carry out color grading on diamonds on a continuous line, and manual color evaluation is not needed. And a sample diamond is conveyed by the input conveying belt and is placed on the mounting seat on the rotating plate by the mechanical arm. Nm mounting seats are arranged on the rotating plate, and Nr colorimetric stones with known color grades and Ns sample diamonds are mounted on the mounting seats. The camera shoots pictures of all diamonds on the rotating plate, then the stepping motor rotates the rotating plate by 360 / Nm degrees, and another picture is shot. The operation is repeated for Nm times, so that the sample diamond and all the colorimetric stones are respectively imaged at all Nm possible rotating positions. Averaging the pixels of all positions of each diamond to obtain x and y average values of each diamond; and the color grade of the sample diamond is the closest colorimetric stone with light x and y average values.

Description

W O 2 02 6 / 07 67 39 A l _ _l llll _l _l lll_ m i’ (12) INTERNATIONAL APPLICATION PUBLISHED UNDER THE PATENT COOPERATION TREATY (PCT) (19) Worid Intellectual Property Organization International Bureau (43) International Publication Date 16 April 2026 (16.04.2026) (10) International Publication Number WO 2026 / 076739 Al WIPOI PCT (51) International Patent Classification: B07C 5 / 342 (2006.01) B07C 5 / 36 (2006.01) B07C 5 / 02 (2006.01) GOIN 21 / 25 (2006.01) (21) International Application Number: PCT / CN2024 / 125519 (22) International Filing Date: 17 October 2024 (17.10.2024) (25) Filing Language: English (26) Publication Language: English (30) Priority Data: 18 / 911,583 10 October 2024 (10.10.2024) US (71) Applicant: HONG KONG APPLIED SCIENCE AND TECHNOLOGY RESEARCH INSTITUTE COMPA­ NY LIMITED [CN / CN]; 5 / F, Photonics Centre, 2 Science Park East Avenue, Hong Kong Science Paik, Shatin, N.T., Hong Kong (CN). (72) Inventors: WANG, Yiielin; Flat B, 12 / f, Tong Ning Bldg, Shatin Centre, 2-16 Wang PokStreet, Shatin, N.T., Hong Kong (CN). WANG, Ziqi; 1C, Til, Centra Horizon, 18 Chong San Road, Pak Shek Kok, Tai Po, N.T., Hong Kong (CN). ZHANG, Chun; Flat A, 5 / F, Tower 1, Dragon Cen­ tre, 21 Wunsha Street, Tai Hang, Hong Kong (CN). (74) Agent: CHINA TRUER IP; Room 1104, Building 2, Excellence Meilin Central Plaza (North Area), No. 128 Zhongkang Road, Meidu Community, Meilin Street, Futian District, Shenzhen, Guangdong 518049 (CN). (81) Designated States (unless otherwise indicated, for every kind of national protection available) '. AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY BZ, CA, CH, CL, CN, CO, CR, CU, CY CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, (54) Title: CONTINUOUS LINE FOR AUTOMATIC DIAMOND COLOR GRADING EVALUATION FIG. 3 (57) Abstract: An automated diamond color-grading machine color grades a continuous line of diamonds without human color eval­ uation. A sample diamond is carried by an input conveyor and placed on a mounton a rotating plate by a robotic arm. The rotating plate has Nm mounts with Nr master stones of known color grades and Ns sample diamonds. A cameta takes a photo of the rotating plate with all diamonds and then a step motor rotates the plate by 360 / Nm degrees and another photo captured. This is repeated Nm times so that the sample diamond and all master stones are each imaged in all Nm possible rotational positions. Pixels are averaged over all positions for each diamond to get an average x, y value for each diamond. The color grade of the satr^le diamond is the master stone with the closest less-color x,y average. [Continued on next page] WO 2026 / 076739 Al HN, HR, HU, ID, IL, IN, IQ, IR, IS, IT, JM, JO, JP, KE, KG, KH, KN, KP,KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, MG, MK, MN, MU, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, WS, ZA, ZM, ZW. (84)Designated States (unless otherwise indicated, for every kind of regional protection available) '. ARIPO (BW, CV, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SC, SD, SL, ST, SZ, TZ, UG, ZM, ZW), Eurasian (AM, AZ, BY, KG, KZ, RU, TJ, TM), European (AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV, MC, ME, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR), OAPI (BF, BJ, OF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE,SN, TO, TG). Published: — with international search report (Art. 21(3)) WO 2026 / 076739 PCT / CN2024 / 125519 1 Continuous Line for Automatic Diamond Color Grading Evaluation FIELD OF THE INVENTION

[0001] This invention relates to automated inspection machines, and more particularly to automatic color grading of diamonds. BACKGROUND OF THE INVENTION

[0002] Diamonds have long been one of the most sought-after of all the precious stones. Wide availability despite their relative scarcity boosts consumer demand. Pricing and value can vary widely dueto variations of each individual diamond.

[0003] The quality of a diamond is based on the 4 C’s: Color, Clarity, Cut, and Carat weight Clear diamonds are worth more than faint yellow diamonds, which are worth more than light colored diamonds that have more than a faint color. Typically a person with specialized training and years of experience will compare a diamond under evaluation to a series of diamond master stones of different known color grades.

[0004] Figure 1 shows color grades of diamonds. A colorless diamond with a D grade is the most valuable while a light colored diamond with a Z grade or past the Z grade (>Z) are the least valuable, based on color alone. Grades D, E, and F are colorless, grades G, H, I, J are near colorless, while grades K, L, M have greater degrees of faint color. Grades N through R have increasing levels of light color, while lightly colored diamonds are graded S to Z.

[0005] Since its introduction in the early 1950s, the Gemological Institute of America(GIA)’s D-to-Z scale has been used to color grade the overwhelming majority of colorless to light yellow gem-quality polished diamonds on which laboratory reports have been issued. D-to-Z color grading is based on the observations of a trained observer, who compares a diamond being evaluated to color master stones of known position on the grading scale. GIA master stones are located at the highest point in their respective grade range. A diamond equal to the G master is graded a G. If it has slightly less color, it would receive a grade of F.

[0006] Typically, a trained person will hne up the known master stones in a line on a dull white background table under a light source with a color temperature of 5500-6500K. The diamond under evaluation and the master stones are all examined at a 45 degree angle while the stones are aligned directly under the light source. The sample diamond under evaluation is usually examined in several different directions.

[0007] Color can be evaluatedqualitatively by a person. However, color can also be defined by a color space, such as the International Commission on Dlumination (CIE) RGB XYZ„ xy, or Lightness, Aperture, Brightness (LAB) color spaces. Colors can be represented by two or three digital values in the color space. For instance, the chromaticity in the CIE XYZ color space is specified by the two derived parameters x and y, two of the three normalized values being functions of all three tristimulus values X, Y, and Z. The CIE xy WO 2026 / 076739 PCT / CN2024 / 125519 2 chromaticity diagram displays the maximally saturated bright colors. Machines can detect color and report the digital values in the selected color space.

[0008] Figure 2 shows a series of diamond master stones evaluated in a CIE 1931 color space chromaticity diagram. The CIE 1931 color space represents a color by x, y values between 0 and 1, when nonnalized. The same 10 master stones are evaluated by a color-detection machine during a trail that is repeated 3times.

[0009] In first trial 12, master stone D has the lowest x,y value and master stone M has the highest x,y value. Master stones E though K have successively higher x,y values, but then stone L has a lower x,y value than the x,y value for stone K, even though master stone K should have a lower x,y value than master stone L. This regression of the x,y value for master stone L of trial 12 is clearly in error.

[00010] In second trail 14, master stones D and E have about the same x,y values, even though master stone D should have a lower x,y value. Master stones F and G are too close to each other and should have x,y values that differ from each other by a greater amount.

[00011] In third trial 16, master stones D and E have almost the same x,y values, but they should differ. Master stones L and M also have nearly the same x,y values, but should differ.

[00012] Although the same 10 master stones were evaluated in trials 12, 14, 16, there is an offset for each trail. Trail 12 has moststones x,y value shifted down and to the left relative to the x,y values for trial 14. The x,y values for third trial 16is shifted up (higher y values) and to the right (higher x values) relative to trials 12, 14.

[00013] The amount of x and y shifts are small, roughly 0.001 in x and 0.002 in y, or about 0.3%. However, the distance between color grades of the master stones is even smaller, being about 0.0004 in x and 0.0003 in y. A much more precise system is needed to evaluate sample diamonds to within 0.5 of a color grade. While offsets in x,y may be tolerated for different trials, the master stones should have steadily increasing x,y values for successive master stones. No regressions should occur.

[00014] More recently, automated diamond color grading machines are becoming available. Some may use a manually rotated platform that can be slow and difficult to use. These machine may be expensive or have poor accuracy.

[00015] It is desired to automatically color grade diamonds towithin + / - 0.5 color grade. An automated process and machine to evaluate the color grade of sample diamonds is desirable. A machine that feeds a continuous line of sample diamonds for comparison to known master stones is desirable for automated diamond color grading. BRIEF DESCRIPTION OF THE DRAWINGS

[00016] Figure 1 shows color grades of diamonds.

[00017] Figure 2 shows a prior-art series of diamond master stones evaluated in a CIE 1931 color space chromaticity diagram. WO 2026 / 076739 PCT / CN2024 / 125519 3

[00018] Figure 3 is a diagram of a diamond color grading machine.

[00019] Figures 4A-4C show the rotating plate in more detail.

[00020] Figure 5 shows a target area on an image of a diamond.

[00021] Figure 6A-6D show a conveyor system loading and unloading a sample diamond on the rotating plate.

[00022] Figures 7A-7E show a side view of the conveyor system loading and unloading a sample diamond onto the rotating plate.

[00023] Figure 8 is a graph of chromaticity with x,y color valuesfor master stones using the diamond color grading machine.

[00024] Figures 9A-9D show a flowchart of operation of the diamond color-grading machine.

[00025] Figure 10 is a diamond color grading machine having input and output conveyors on the same side.

[00026] Figure 11 is a side view of a diamond color grading machine having input and output conveyors on the same side but on different levels.

[00027] Figures 12A-12B show a side view of an alternative diamond color grading machine with an annular output sorter.

[00028] Figure 13 shows a top view of the alternative diamond color grading machine with an annular output sorter of Fig. 12A-12B.

[00029] Figure 14 shows an alternative for the mount on the rotating plate.

[00030] Figure 15 is an alternative diamond color grading machine with the camera directly over the rotating plate of diamonds. DETAILED DESCRIPTION

[00031] The present invention relates to an improvement in diamond color grading. The foDowing description is presented toenable one of ordinary skill in the art to make and use the invention as provided in the context of a particular application and its requirements. Various modifications to the preferred embodiment will be apparent to those with skill in the art, and the general principles defined herein may be applied to other embodiments. Therefore, the present invention is not intended to be limited to the particular embodiments shown and described, but is to be accorded the widest scope consistent with the principles and novel features herein disclosed.

[00032] Figure 3 is a diagram of a diamond color grading machine. A batch of sample diamonds can be input to the diamond color grading machine, which has a conveyer or robotic arm system (not shown) to continuously feed the sample diamonds and place a sample diamond on rotating plate 30 for comparison to a set of master stones 10 that are also placed on rotating plate 30. Step motor 24 rotates rotating plate 30 to allow a new sample diamond to beplaced on rotating plate 30 and to remove sample diamonds that have finished evaluation. WO 2026 / 076739 PCT / CN2024 / 125519 4

[00033] Light source 42 under rotating plate 30 provides a uniform white light that illuminates master stones 10 and the sample diamond on rotating plate 30. Shell 46 can be a sphere with its interior having a flat white surface to diffuse light from light source 42 within chamber 20 and provide a dull white background. The top sinface of rotating plate 30 can likewise have a dull white color surface.

[00034] Camera 40 is mounted on bracket 44 to shell 46. An opening in shell 46 allows the lens of camera 40 to capture an image of light reflected off the sample diamond and master stones 10 on rotating plate 30. Controller or computer 50 can cause camera 40 to capture images after computer 50 causes step motor 24 to rotate rotating plate 30 a desired amount. The images captured by camera 40 can be analyzed by computer 50 or sent to a different computer or server formore intense processing.

[00035] Figures 4A-4C show the rotating plate in more detail. In Fig, 4A, rotating plate 30 is empty with no diamonds loaded upon it. There are several mounts 32 that are arranged around rotating plate 30. Each mount 32 can be a dip or depression in rotating plate 30 that a diamond can be placed into by a conveyor or robotic arm. Mount 32 can also be a raised mount or clip that is attached to the surface of rotating plate 30 that can hold a diamond in place as rotating plate 30 rotates.

[00036] In Fig. 4B, master stones 10 have been placed in mounts 32. However, one mount 32 remains vacant. In this example, 11 master stones 10 have been placed on rotating plate 30.

[00037] In Fig. 4C, sample diamond 18 has been placed in the one vacant mount 32. All mounts 32 are occupied by either sample diamond 18 or master stones 10. Each of master stones 10 has a different color grade.

[00038] For a set of 11 master stones 10 and one sample diamond, a total of 12 mounts 32are placed on rotating plate 30, each separated by a radial angle of 30 degrees (360 / 12). Computer 50 instructs step motor 24 to rotate rotating plate 30 by 30 degrees, then instructs camera 40 to capture a photo of rotating plate 30 and the sample diamond and master stones 10 on it. Then computer 50 instructs step motor 24 to rotate by another 30 degrees, and another photo captured. This is repeated for a total of 12 photos and 12 rotations for a total of 360 degrees.

[00039] Figure 5 shows a target area on an image of a diamond. Camera 40 captures a photo of all master stones 10 and sample diamond 18 on rotating plate 30 for each rotation of step motor 24. Computer 50 detects portions of the photo containing a diamond and separates the photo into 12 images, with one diamond per image. Then computer 50 can further process each single-diamond image to select target area 48 on master stone 10 or on sample diamond 18.

[00040] Target area 48 can be within one of the facets or faces of thediamond, or can include more than one face and include one or more edges of the diamond. Computer 50 can select target area 48 as an area with a consistent color and without abrupt color changes, or can simply define a boundary of the diamond and select target area 48 as an area within the defined boundary. WO 2026 / 076739 PCT / CN2024 / 125519 5

[00041] Figure 6A-6D show a conveyor system loading and unloading a sample diamond on the rotating plate. In Fig. 6A, rotating plate 30 has been pre-loaded with 11 master stones 10 and has one vacant mount 32. Computer 50 has instructed step motor 24 (not shown) to rotate rotating plate 30 so that vacant mount 32 is aligned with input conveyor 60. Sample diamond 18 is moved along by input conveyor 60 until the end of input conveyor 60 is reached, when sample diamond 18 drops into mount 32. Mount 32 can have a narrowing shape to guide sample diamond 18 into position as sample diamond 18 falls from input conveyor 60.

[00042] In Fig. 6B, rotatingplate 30 has been rotated three times, for a total of 90 degrees, so that sample diamond 18 is at the top of Fig. 6B. Camera 40 has captured three photos, one for each step rotation of rotating plate 30.

[00043] In Fig. 6C, rotating plate 30 has been rotated six times, for a total of 180 degrees, so that sample diamond 18 is at the right of Fig. 6C. Camera 40 has captured six photos, one for each step rotation of rotating plate 30.

[00044] Computer 50 then continues stepping rotating plate 30 until sample diamond 18 returns to the initial position under input conveyor 60. A total of 12 photos have been captured for the 12 step rotations of rotating plate 30. Finally, computer 50 causes step motor 24 to rotate rotating plate 30 by 180 degrees so that sample diamond 18 is placed under output conveyor 62.

[00045] In Fig. 6D, sample diamond 18 has been removed from mount 32 and placed on output conveyor 62. A robotic arm (not shown) can pick up sample diamond 18 from rotating plate 30 andplace sample diamond 18 on output conveyor 62.

[00046] Output sorter 64 has several bins 66, each for a different color grade of sample diamond 18. When computer 50 detennines the color grade of sample diamond 18, then computer 50 commands output sorter 64 to move bins 66 so that target bin 68 for the determined color grade is below the end of output conveyor 62. Then sample diamond 18 falls into target bin 68.

[00047] Figures 7A-7E show a side view of the conveyor system loading and unloading a sample diamond onto the rotating plate. In Fig. 7 A, rotating plate 30 has been pre-loaded with master stones 10 and has one vacant mount 32. Computer 50 has instructed step motor 24 (not shown) to rotate rotating plate 30 so that vacant mount 32 is aligned with input conveyor 60. Sample diamond 18 is moved along by input conveyor 60 until the end of input conveyor 60 is reached, when sample diamond 18 drops into mount 32. Mount 32 can have a narrowing shape to guide sample diamond 18 intoposition as sample diamond 18 falls from input conveyor 60.

[00048] In Fig. 7B, input conveyor 60 has dropped sample diamond 18 into mount 32. rotating plate 30 is now fully loaded with master stones 10 and sample diamond 18. Camera 40 takes one photo per radial step of step motor 24, for a total of Nt rotations and Nt photos. Nt = Ns + Nr, wherein Ns is the number of sample diamond 18 on rotating plate 30 and Nr is the number of master stones 10 on rotating plate 30. WO 2026 / 076739 PCT / CN2024 / 125519 6

[00049] In Fig. 7C, after the Nt radial steps of step motor 24, computer 50 determines the color grade of sample diamond 18. Computer 50 instructs output sorter 64 to shift bins 66 so that target bin 68 for the color grade determined by computer 50 is aligned under the end of output conveyor 62.

[00050] Computer 50 also activated step motor 24 to rotate rotating plate 30 by 180 degrees so that sample diamond 18 is aligned with output conveyor 62. Then computer 50 commands robotic arm 72to pick up sample diamond 18 out of mount 32 on rotating plate 30. In Fig, 7D, robotic arm 72 has been commanded by computer 50 to move sample diamond 18 over to output conveyor 62 and place sample diamond 18 onto output conveyor 62.

[00051] In Fig. 7E, sample diamond 18 reaches the end of output conveyor 62 and sample diamond 18 falls into target bin 68 that was moved into position under the end of output conveyor 62 by output sorter 64. Target bin 68 may contain other sample diamonds 18 that have the same color grade, such as G.

[00052] Figure 8 is a graph of chromaticity with x,y color values for master stones using the diamond color grading machine. During each evaluation run or trial, rotating plate 30 is rotated Nt times and camera 40 captures Nt photos.

[00053] Although there is an offset of run 22 and run 26 compared to run 24, the 10 master stones D-M are in the correct sequence within each trial. Although master stones D and E are closer together than for other master stonesF-M, master stone D still has lower x,y values than master stone E. Sample stone 25 is correctly located between master stones E and F in all three runs 22, 24, 26, allowing for sample stone 25 to be correctly evaluated as color grade E. Re-generating the x,y values for the master stones for each evaluation run for a sample stone corrects for the offsets between runs 22, 24, 26 that can occur as temperature and other operating conditions vary.

[00054] Evaluating the color of each master stone while evaluating the color of the sample stone acts as an internal reference to correct for operating condition color offsets. Thus it is not necessary to perform calibration before each evaluation run. The relative sequence of each master stone within the D to M range remains consistentiy accurate. After evaluation runs on different days, the distance and slope between two adjacent grades in the entire baseline by master stones from D to M is reproducible. For sample diamond color evaluation, theresults of the sample diamond consistently shows an accuracy within 0.5 of a color grade after each evaluation run.

[00055] Figures 9A-9D show a flowchart of operation of the diamond color-grading machine. In Fig. 9A, a total of Nr master stones 10 are placed onto mounts 32 or holders 73 on rotating plate 30, step 202. These master stones 10 remain on rotating plate 30 as many sample diamonds 18 are placed onto and removed from rotating plate 30 during continuous-line testing. WO 2026 / 076739 PCT / CN2024 / 125519 7

[00056] The Diamond Under Test (DUT), sample diamond 18, is placed onto rotating plate 30, step 204. Input conveyor 60 may move sample diamond 18 to be near rotating plate 30 and then robotic arm 72 picks up sample diamond 18 and places it in mount 32 or holder 73 on rotating plate 30.

[00057] In step 206, parameter P is set to the total number of mount 32 on rotating plate 30, Nm, which may be more than Nt when some of mount 32 are vacant with no gemstone. Nt, is the sum of thenumber of sample diamond 18 (Ns) and the number of master stones 10 (Nr).

[00058] Camera 40 captures a photo of rotating plate 30 with all its diamonds, step 208, for an initial rotational position. This photo is stored for later access and processing by the computer, step 210. Step motor 24 is then activated to rotate rotating plate 30 by an angle of 360 / Nm degrees, step 212. This rotation causes diamonds to be located at the same positions as in the prior photo (step 208), but a different diamond is in each of these positions, as all diamonds are shifted by one position in the direction of the rotation. Parameter P is decremented, step 214 to track the number of partial rotations.

[00059] The photo of all Nt diamonds on rotating plate 30 from step 208 is divided into Nt smaller images, step 216. Each of these smaller images generated in step 216 contains only one diamond, while the larger photo from step 208 has Nt diamonds in it. Image processing software running on the computersuch as object detection routines can detect the outlines of each diamond against the dull while background of rotating plate 30 and shell 46, and the detected outlines used to cut the photo into the smaller images.

[00060] When step parameter P has not yet reached zero, step 218, then camera 40 capmres another photo of all Nt diamonds, but rotated into new positions, while step 216 isolates each diamond into a separate smaller image. This loop is repeated Nm times so that each diamond is photographed in each of the Nm positions relative to camera 40. Any slight variation in lighting for positions within chamber 20 are applied to all Nt diamonds by this loop that rotates sample diamond 18 through all Nm positions.

[00061] In Fig. 9B, after all Nm photos have been taken, and each divided into Nt smaller images, there are Nm*Nt smaller images. For each of these Nm*Nt images, step 220, target area 48 is selected within that smaller image, step 222. This target area 48 can be selected asan area within the diamond, or even selected as an area within one face of the diamond, or an area within the diamond’s outline that has good uniformity of color. Areas with the diamond’s outline with saturated and dark or sharp and abrupt changes in color may be removed from target area 48 as these may be reflections or image distortions.

[00062] The Red Green Blue (RGB) pixel values for all pixels within target area 48 are obtained from the smaller image, step 224. The computer then converts these RGB values into XYZ values in the CIE XYZ tristimulus color space, step 226. The computer then further calculates these XYZ values into xy values in the CIE chromaticity space, step 230. WO 2026 / 076739 PCT / CN2024 / 125519 8

[00063] The computer then generates the average x value and the average y value over all the xy pixel values for all pixels in target area 48 in the current smaller image, step 232. The average x value and the average y value are stored for this smaller image, step 234.

[00064] This image processing loop, steps 222-234, is repeated for all of the smaller images, step 236, for a total of Nm*Nt loops. Once all Nm*Nt smaller images have been processed, step 236, then Nm*Nt average values of x,y are stored.

[00065] In Fig. 9C, the computer tracks which of the smaller images are for which of the master stones 10 and sample diamond 18, by tracking rotations of step motor 24 and placement of sample diamond 18. For each diamond, step 250, such as for sample diamond 18 or for each of master stones 10, there are Nt smaller images for each diamond and Nt average values of x and y. These Nt average x,y values for that diamond are read, step 252, and the Nt average x values are averaged to obtain the average x color of this diamond, and the Nt average y values are averaged to obtain the average y color of this diamond, step 254.

[00066] When Fig. 9C finishes, there is an average x,y color for sample diamond 18, and there is an average x,y color for the grade Ddiamond of master stones 10, and an average x,y color for the grade E diamond of master stones 10, etc.

[00067] In Fig. 9D, these Nr average x,y colors for the Nr grades of diamond of the Nr master stones 10 are arranged in grade order and stored as a reference database, step 248. The average x,y color of sample diamond 18 is compared to the average x,y values in this database, step 240, to find the closest less-color (left) master stones. For example, the color grade number value of either sample stone 18 or master stones 10 can be calculated as the projection position of a line, which is fitted by average x,y colors of master stones 10. The master stone with the largest number value that is smaller than sample diamond 18 is selected as the closest less-color reference, step 242.

[00068] The left reference effectively “rounds up” to the better color grade, so that the closest master stone has less color than the sample gemstone. The computer sends the color grade determined in step242 to output sorter 64, which moves the bins so that target bin 68 for this grade is aligned with output conveyor 62. Robotic arm 72 picks up sample diamond 18 from rotating plate 30 and places sample diamond 18 onto output conveyor 62 and into target bin 68, step 244. The computer may need to activate step motor 24 to bring sample diamond 18 into alignment with output conveyor 62 and then again to bring the empty holder 73 into alignment with input conveyor 60 to allow placement of the next DUT, steps 246, 204.

[00069] Figure 10 is a diamond color grading machine having input and output conveyors on the same side. In this alternative, input conveyor 60 and output conveyor 62 are both on the right side of rotating plate 30. Input conveyor 60 and output conveyor 62 can be located next to each other above rotating plate 30, or input conveyor 60 can be located above or below output conveyor 62. Output conveyor 62 can end over target bin 68 on output sorter 64 while input conveyor 60 canextend over output sorter 64 to access a bin (not shown) of WO 2026 / 076739 PCT / CN2024 / 125519 9 input sample diamonds 18 that are located beyond output sorter 64. A single robotic arm 72 could move sample diamond 18 among rotating plate 30 and input conveyor 60 and output conveyor 62.

[00070] Figure 11 is a side view of a diamond color grading machine having input and output conveyors on the same side but on different levels. In this alternative, input conveyor 60 and output conveyor 62 are both on the right side of rotating plate 30. Input conveyor 60 and output conveyor 62 are located next to each other above rotating plate 30, while input conveyor 60 is located above output conveyor 62. Output conveyor 62 can end over target bin 68 on output sorter 64 while input conveyor 60 can extend over output sorter 64 to access a bin (not shown) of input sample diamonds 18 that are located beyond output sorter 64. A single robotic arm 72 could move sample diamond 18 among rotating plate 30 andinput conveyor 60 and output conveyor 62.

[00071] Figures 12A-12B show a side view of an alternative diamond color grading machine with an annular output sorter. In Fig. 12A, input conveyor 60 moves sample diamond 18’ and drops sample diamond 18 into a vacant mount 32 on rotating plate 30.

[00072] In Fig. 12B, after evaluation is completed, robotic arm 72 picks up sample diamond 18 from rotating plate 30 and drops sample diamond 18 into target bin 68. Robotic arm 72 can softly place sample diamond 18 into target bin 68 rather than allowing sample diamond 18 to fall into target bin 68.

[00073] Figure 13 shows a top view of the alternative diamond color grading machine with an annular output sorter of Fig. 12A-12B. Output sorter 64’ forms an annular ring around rotating plate 30, with bins 66 arranged outside of the perimeter of rotating plate 30. Computer 50 instructs output sorter 64’ to rotate relative to input conveyor 60 and output conveyor 62, which are fixed, to rotate target bin68 to be under the end of output conveyor 62.

[00074] Figure 14 shows an alternative for the mount on the rotating plate. Robotic arm 72 picks up sample diamond 18’ from input conveyor 60 and places sample diamond 18 into holder 73. Holder 73 is a V-shaped fixture that is mounted to the top surface of rotating plate 30. Holder 73 holds sample diamond 18 or master stones 10 at a standard designed angle to the top surface of rotating plate 30. When camera 40 is mounted directly overhead, as shown in Fig. 15, holder 73 makes the viewing angle exactly 45 degrees to meet the GIA standard for viewing by camera 40. The viewing angle is between camera 40 and the axis of the stones through the culet and normal to the table facet (top surface) of sample diamond 18 or master stones 10. Also, when robotic arm 72 drops sample diamond 18 into holder 73, the slope of the grove in holder 73 helps guide sample diamond 18 into position within holder 73.

[00075] Figure 15 is an alternative diamond colorgrading machine with the camera direcdy over the rotating plate of diamonds. When holders 73 (Fig. 14) are used with a V-shaped bottom, master stones 10 and sample diamond 18 are held at an angle to rotating plate 30. To achieve a viewing angle between camera 40 and an axis of the gemstones through the culet and normal to the table facet (top surface) of sample diamond 18 or master stones 10 in holders 73, camera 40 and bracket 44 are moved to an opening at the top of shell 46. Light source WO 2026 / 076739 PCT / CN2024 / 125519 10 42 may also be placed below rotating plate 30 to provide appropriate lighting within chamber 20. There may be additional light sources within shell 46 to provide optimal lighting. ALTERNATE EMBODIMENTS

[00076] Several other embodiments are contemplated by the inventors. For example many combinations and variations of the apparatus and methods are possible. In Fig. 9, color conversion, target area 48 detection, and pixel averaging could be performed after all Nmphotos are captured, or could be performed after each photo is captured. All RGB pixels in the target area could be averaged together to get an average RGB value for the target area, and then the average RGB converted to an average XYZ and then to an average x,y value in steps 226, 230, 232 of Fig. 9B. Averaging all pixels could also be performed after conversion to XYZ and before conversion to x,y. Rather than convert RGB to XYZ and then to xy, a single conversion could be performed from RGB to xy. Rather than a 2-dimensional x,y graph, a 3-dimensional R, G, B graph could be used for color grading without conversion to x,y values, although this may provide less accuracy and more computational work.

[00077] Rotating plate 30 could be circular, or might have some other shape that still provides clearance for rotation within shell 46. Shell 46 can be a sphere, or could have other shapes. A sphere is considered better for integrating light and providing flat background lighting, but othershapes for shell 46 might still provide adequately uniform lighting even if less ideal.

[00078] There may be additional light sources other than light source 42 within shell 46 to provide optimal lighting. The position and number of light sources could be modified, and the intensity and color profile of the light source may be adjusted, such as under program control. The program could adjust the while balance or color temperature of light source 42 within a range, such as 5500-6500K. Testing may be performed to find optimal settings of light source intensity and color temperature that produce the best uniformity of the background light within chamber 20 for color grading accuracy.

[00079] A cutout or hole in the side of shell 46 may be provided to allow input conveyor 60 to enter chamber 20. Alternately, input conveyor 60 may end outside of shell 46 and then a robotic arm could pick up sample diamond 18 from input conveyor 60 outside of shell 46 and move sample diamond 18 through thehole and into chamber 20 and place sample diamond 18 on mount 32 on rotating plate 30. This may allow for a smaller hole in shell 46 and less non-uniformity of the background light within chamber 20. The alternatives of Figs. 10, 11 may have better lighting since they have input conveyor 60 and output conveyor 62 on the same side. Then a single robotic arm 72 could use a single hole in shell 46 rather than require a second hole for output conveyor 62. This hole in shell 46 could have a door or curtain that closes after robotic arm 72 loads sample diamond 18 unto rotating plate 30. Such a door could provide a more uniform lighting within chamber 20 compared to leaving the hole in shell 46. The door could be painted the same dull while as the interior of shell 46. WO 2026 / 076739 PCT / CN2024 / 125519 11

[00080] While output sorter 64 with bins 66 and target bin 68 have been described, bins could be sacks or bags or other collection devise with flexible sides. Output sorter 64 could move bins66 to select target bin 68 in various ways other than linear or rotational. Many variations and physical configurations of output sorter 64, input conveyor 60, output conveyor 62, and robotic arm 72 are possible.

[00081] Robotic arm 72 could have a clamp to grab sample diamond 18, or could have a small tube with an applied vacuum to hold sample diamond 18 during movement. Robotic arm 72 could pivot in various ways to better align sample diamond 18 onto mount 32. When robotic arm 72 has a wide range of motion and length of travel, alignment with sample diamond 18 on rotating plate 30 does not have to be as exact. Robotic arm 72 may be able to pick up diamonds from several of the holders on rotating plate 30, allowing some rotation for alignment to be avoided. Input conveyor 60 can be used, and the robotic arm used to drop the sample diamond into the target bin directly, eliminating output conveyor 62.

[00082] Mount 32 could have various shapes and feamres to better hold and align samplediamond 18, and could hold sample diamond 18 at angles to the plane of rotating plate 30. The location of camera 40 could be adjusted from the 45-degree location shown in Fig. 3 when mount 32 has a built-in angle, allowing viewing from camera 40 to be 45 degrees to the axis of sample diamond 18 and master stones 10 on rotating plate 30. Other viewing angles could be substituted for 45 degrees.

[00083] The interior of shell 46, the surface of rotating plate 30, and mount 32 or holders 73 could be painted with a same dull-white color, or could be made from a dull while plastic or other material. There could be some non-uniformities, such as screw heads, gaps, or seams, but ideally these are kept to a minimum so as to improve light uniformity within chamber 20.

[00084] A variety of kinds of mount 32 or holders 73 may be used. Ideally, sample diamond 18 and master stones 10 all use the same mount 32 or holder 73, but sample diamond 18 could be fitted with a holders 73 that differs frommount 32 for master stones 10, but mount 32 and holders 73 should not introduce non-uniformities in the images captured by camera 40, or these non-uniformities should be able to be removed when target area 48 is selected from the larger photos. Target area 48 may be a composite of several areas within a diamond that are all included in image processing and averaging for that diamond. Target area 48 can be non-contiguous rather than one distinct area bounded by a polygon. Mount 32 or holders 73 may be fixtures or may be integral with rotating plate 30.

[00085] The master stones can all have the same carat weight, which is ideally the same carat weight as the sample diamond. Cut and clarity can also be the same or similar for all master stones in the set of master stones. The better matched master stones 10 to sample diamond 18, the better the color grading can be. However, the automated color grading system might also work adequately when matching is not ideal, although there may besome loss of accuracy. The master stones 10 may be placed on rotating plate 30 in order of their known color grade, or may be placed in a random order. However, the program can be instructed when grade diamond is WO 2026 / 076739 PCT / CN2024 / 125519 12 placed on which location on rotating plate 30 so that the program can track these diamond grades. Alternatively, the program could determine the grades from the x,y values and order of the x,y values for the master stones.

[00086] An alternate for unloading sample diamond 18 onto output conveyor 62 is an eject mechanism in mount 32 that can eject sample diamond 18 from mount 32 and onto output conveyor 62. Another alternative is that rotating plate 30 may be fitted with a trap door under mount 32 that opens to allow sample diamond 18 to fall through the trap door in rotating plate 30 and onto output conveyor 62 or target bin 68 placed below rotating plate 30.

[00087] The locations of mount 32 or holders 73 on the top surface of rotatingplate 30 can be separated by equal angles, and can have and equal distance to the center of rotating plate 30. Thus when rotating plate 30 is rotated by 360 / Nm degrees, where Nm is the number of mounts 32 or holders 73, camera 40 sees a different one of master stones 10 or sample diamond 18 in the same location as a prior diamond. An alternative may use non­ equal angles, or may have some diamonds that are farther from the center of rotating plate 30 than others, and the program may map these variations. Mount 32 can be in a non-circle or in an arc-shape that is an arc along a circle. There can be vacant mounts having no gemstone when Nm> Nt. For example, there can be 6 mounts and only 3 gemstones on rotating plate 30. To obtain the best results, it is desired to have the same lighting conditions of each gemstone at each position. For example, if there are 6 mounts and the last 3 mounts are vacant, stone 1 can be shot at Photos No. 1 2, 3. But Stone 2 can be shot at Photos No. 2, 3, 6,and Stone 3 at Photos No. 1, 5, 6. In this example, rotating plate 30 can be rotated Nm=6 times although there are only 3 gemstones (Nt=3). The gemstones can be put in any vacancy on rotating plate 30.

[00088] While a single sample diamond 18 has been shown on rotating plate 30, there could be more than one sample diamond 18, such as Ns. Also, the number of master stones 10, Nr, can vary, as can the total number of diamonds, Nt = Ns + Nr. There may also be empty mount 32 or holders 73 on rotating plate 30 that are not occupied by a diamond. The program can filter out these locations of unoccupied mounts and not include them. The program can track each one of master stones 10 and its current location on rotating plate 30 as step motor 24 is activated, and these locations of the same master stone 10 averaged together once all Nt locations of rotating plate 30 have been captured.

[00089] While the CIE XYZ color space has been described, other color spaces could be used. For example,camera 40 may capture pixels using RGB, and then RGB may be converted to XYZ by a processor or computer. XYZ is preferred over RGB because Y is the luminance or intensity and does not have color information, so color is expressed by just two variables X, Y in and XYZ color space, rather than three variables R, G, B. The use of 2 variables allows for easier graphing and comparing of color values. Removing the Z luminance component helps to mask out variations in the brightness of the lighting within chamber 20 and provide more accurate color grading. Conversion among several color spaces, such as XYZ and xyZ, may be performed by WO 2026 / 076739 PCT / CN2024 / 125519 13 the computer. Other color spaces may be used, such as CIE Lab, Hue Saturation, Lightness (HSL), or Hue Saturation, Value (HSV). Various filters and image processing may be performed as well.

[00090] When camera 40 outputs RGB, steps 224, 226 of Fig. 9B are used. When camera 40 can output XYZ, then steps 224,226 can be skippedor modified.

[00091] While camera 40 has been shown, various image sensors could be used, and various lens systems could funnel light to the image sensor. There could be more than one camera 40 mounted to shell 46, allowing multiple simultaneous photos to be captured for different viewing angles to rotating plate 30. The angle of camera 40 to rotating plate 30 could be adjustable, and various mounts or bracket 44 could be substituted.

[00092] While having camera 40 capture a photo every 360 / Nm degrees of rotation of rotating plate 30 has been described, additional images could be captured at smaller rotational increments. For example, an image could be captured every 360 / (2*Nm) degrees, and the number of images averaged together doubled. This might improve accuracy. Alternately, camera 40 could be a video camera that captures a continuous series of frames, and computer 50 could select frames at the desired rotational intervals.

[00093] There could be additional mounts 32 that are notoccupied by a diamond, and these vacant mounts could be ignored by the image processing of computer 50. When Ns is 2 or more, computer 50 can color-grade 2 or more sample diamonds during one 360-degree rotation, improving throughput.

[00094] While diamonds have been described, other precious stones could be substituted. While a round or circular rotating plate 30 has been described, rotating plate 30 could be elliptical, octagonal, square, or have other shapes that still allow sufficient clearance for rotation within chamber 20. Computer 50 can be a Personal Computer (PC), a controller or a processor with a memory such as a semiconductor main memory, and may have mass storage such as a flash drive or hard disk drive and may have I / O such as an interface to a network such as the Internet. Computer 50 may offload some processing tasks to external servers, such as specialized image processing tasks. Neural networks may be used for some processing tasks. The steps of Fig 9 may beimplemented by a computer executing machine-readable instructions that controls step motor 24 and the robotic arm and conveyors and camera.

[00095] Various values may be calculated rather than stored. For example, once all Nm*Nt smaller images have been processed, step 236, Fig. 9B, then Nm*Nt average values of x,y are stored. Alternatively, the original Nm*Nt x,y values can be stored instead of the average values of x,y. Then the Nt average x,y values can be calculated when needed in Fig. 9C.

[00096] Input conveyor 60, robotic arm 72, rotating plate 30, and output conveyor 62 can allow for a continuous line of diamonds to be tested as sample diamond 18. When bins 66 on output sorter 64 become full, the machine may be paused to allow swapping the full bin for an empty bin, or for removal of the sorted diamonds firom output sorter 66. Untested diamonds may be poured into an input bin that feeds diamonds to input conveyor 60. Of course, the continuous line of diamonds may be paused forvarious reasons such as WO 2026 / 076739 PCT / CN2024 / 125519 14 loading, unloading, error handling, maintenance, or at the end of the day when work stops. Many color grading machines may be operated by a human operator, eliminating the need for skilled, highly-trained human experts to view each diamond.

[00097] Terms such as up, down, above, under, horizontal, vertical, inside, outside, are relative and depend on the viewpoint and are not meant to limit the invention to a particular perspective. Devices may be rotated so that vertical is horizontal and horizontal is vertical, so these terms are viewer dependent.

[00098] The background of the invention section may contain background information about the problem or environment of the invention rather than describe prior art by others. Thus inclusion of material in the background section is not an admission of prior art by the Applicant.

[00099] Any methods or processes described herein are machine-implemented or computer-implemented and areintended to be performed by machine, computer, or other device and are not intended to be performed solely by humans without such machine assistance. Tangible results generated may include reports or other machine­ generated displays on display devices such as computer monitors, projection devices, audio-generating devices, and related media devices, and may include hardcopy printouts that are also machine-generated. Computer control of other machines is another tangible result. [000100] Any advantages and benefits described may not apply to all embodiments of the invention. When the word "means" is recited in a claim element, Applicant intends for the claim element to fall under 35 USC Sect. 112, paragraph 6. Often a label of one or more words precedes the word "means". The word or words preceding the word "means" is a label intended to ease referencing of claim elements and is not intended to convey a structural limitation. Such means-plus-function claims are intended to cover notonly the structures described herein for performing the function and their structural equivalents, but also equivalent structures. For example, although a nail and a screw have different structures, they are equivalent structures since they both perform the function of fastening. Claims that do not use the word “means” are not intended to fall under 35 USC Sect. 112, paragraph 6. Signals are typically electronic signals, but may be optical signals such as can be carried over a fiber optic line. [000101] The foregoing description of the embodiments of the invention has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise form disclosed. Many modifications and variations are possible in light of the above teaching. It is intended that the scope of the invention be limited not by this detailed description, but rather by the claims appended hereto. WO 2026 / 076739 PCT / CN2024 / 125519 15 Claims: 1. Anautomated gemstone color-grading machine comprising: a rotating plate having mounts on a surface, the mounts each for supporting a gemstone; wherein gemstones on the mounts include a sample gemstone and a series of master gemstones, wherein the series of master gemstones has master gemstones of varying known color grades; wherein the sample gemstone has an unknown color grade that is between at least two of the known color grades of the master gemstones; a step motor for rotating the rotating plate by one or more increments that are less than a full rotation; an image sensor for capturing images of the gemstones on the mounts on the rotating plate; a light source for illuminating the gemstones on the rotating plate; a computer for instructing the step motor to rotate the rotating plate by an increment so that the sample gemstone is rotated to a position in the image sensor’s field of view that was previously occupied by one of the master gemstones; the computer causing the image sensorto capture an image after each increment of rotation as the sample gemstone is successively rotated into all positions previously occupied by the master gemstones on the rotating plate; wherein each master gemstone successively occupies positions of the sample gemstone and other master gemstones as the rotating plate is incremented; the computer executing machine-readable instructions that cause the computer, for the sample gemstone and for each of the master gemstones, to select pixels for that gemstone from images captured by the image sensor after each increment of rotation, the computer averaging color indexes of these pixels for each gemstone over all incremented positions of the gemstone to generate a gemstone average color value for each gemstone, the computer selecting one of the master gemstones as a closest gemstone that has a smallest difference in the gemstone average color value for the sample gemstone and the master gemstone, the computer outputting an indication of theknown color grade of the closest gemstone as a color grade of the sample gemstone, whereby the color grade of the sample gemstone is determined by averaging color indexes from pixels of gemstones captured by the image sensor over different rotational increments. 2. The automated gemstone color-grading machine of claim 1 wherein the gemstones are diamonds; wherein the closest gemstone has a smallest negative difference between the gemstone average color values of the sample gemstone and of the closest gemstone; and wherein the sample gemstone has more color than the closest gemstone. 3. The automated gemstone color-grading machine of claim 2 further comprising: WO 2026 / 076739 PCT / CN2024 / 125519 16 a shell that encloses the rotating plate and that permits the image sensor to view the gemstones on the rotating plate; an interior of the shell and the rotating plate having a dull white color to provide a flat background in images captured by the image sensor. 4. The automated gemstonecolor-grading machine of claim 3 wherein the shell is a sphere having cutouts, including a cutout for the image sensor and a cutout to allow the sample gemstone to be placed on an empty mount on the rotating plate and to be removed from the mount on the rotating plate after the color grade of the sample gemstone is determined by the computer. 5. The automated gemstone color-grading machine of claim 4 further comprising: a robotic arm for picking up the sample gemstone from an input of sample gemstones and placing the sample gemstone into an empty mount on the rotating plate, the robotic arm reaching through a cutout in the shell. 6. The automated gemstone color-grading machine of claim 5 wherein the robotic arm also reaches through the shell to pick up the sample gemstone from the mount on the rotating plate after the color grade of the sample gemstone is determined by the computer, the robotic arm placing the sample gemstone into an output bin containing sample gemstones of a samecolor grade determined by the computer. 7. The automated gemstone color-grading machine of claim 6 further comprising: an output sorter having a plurality of output bins, each output bin for a different color grade of the sample gemstone, the output sorter for receiving the color grade determined by the computer and for moving a target bin having the color grade to an output position near the robotic ann to receive the sample gemstone from the robotic arm. 8. The automated gemstone color-grading machine of claim 6 further comprising: an input conveyor for moving sample gemstones from an input bin of sample gemstones with unknown color grades to an input position near the robotic arm to permit the robotic ann to pick up the sample gemstone and place the sample gemstone on the mount on the rotating plate. 9. The automated gemstone color-grading machine of claim 3 wherein the image sensor is a camera that is mounted to the shell at a 45-degree angle to a surface of the rotating plate;wherein the light source has a fixed color temperature between 5500K and 6500K. 10. The automated gemstone color-grading machine of claim 1 wherein the mounts are fixtures that hold the gemstones at an angle to a sxirface of the rotating plate; wherein the image sensor is mounted to the shell so that an axis of the gemstone has a 45 degree angle to the image sensor. 11. The automated gemstone color-grading machine of claim 3 wherein the series of master gemstones comprise at least 10 gemstones of at least 10 different known color grades; WO 2026 / 076739 PCT / CN2024 / 125519 17 wherein the step motor rotates the rotating plate by at least 11 increments and the image sensor captxires images for all of the at least 11 increments. 12. The automated gemstone color-grading machine of claim 3 wherein pixels from images captured by the image sensor are converted to x and y color values in an xy color space, wherein the computer has an image processor that identifies boundaries of gemstones in theimages, and selects pixels from target areas within the boundaries for averaging; wherein for the sample gemstone and for each master gemstone, pixels are averaged from target areas for that gemstone from images captured for all of the increments of the rotating plate. 13. The automated gemstone color-grading machine of claim 12 wherein the computer selects the closest gemstone by generating differences of averaged x and y color values, each difference being between an averaged x and y value of the sample gemstone and an averaged x and y value of one of the master gemstones, wherein the closest gemstone is a closest less-color gemstone having less color than the sample gemstone. 14. The automated gemstone color-grading machine of claim 3 wherein the mounts on the rotating plate are each located at a same radial distance from a center of the rotating plate; wherein the mounts are separated by equal distances to closest neighboring mounts on the rotating plate; wherein the mounts arelocated along a circle on the rotating plate; wherein the camera captures images of all gemstones at all incremented positions of the rotating plate under a same lighting condition. 15. A system for evaluating diamond color comprising: a rotating plate having mounts ananged along a circle on a surface, the mounts each for holding a diamond; wherein Nr mounts are pre-loaded with master stones, the master stones being diamonds with a known color grade, wherein Nr master stones have Nr different color grades, wherein Nr is a whole number of at least 3; wherein Nm is a total number of mounts on the rotating plate, wherein Nm is a whole number of at least 4; wherein Ns mounts are loaded and unloaded with Ns sample diamonds having an unknown color grade, wherein Ns is a whole number of at least 1, wherein Nt is Ns + Nr; a camera that captures images of diamonds on the mounts on the rotating plate; a light source that illuminates the diamonds on the rotating plate; a chamber that partiallysurrounds the rotating plate and provides a background of diffuse light for the camera; an input loader that loads sample diamonds from an input diamond bin outside the chamber onto the Ns mounts on the rotating plate; an output loader that removes sample diamonds from the Ns mounts on the rotating plate after evaluation; an output sorter that places sample diamonds from the output loader into sorted bins that are sorted by an evaluated color grade of the sample diamonds; WO 2026 / 076739 PCT / CN2024 / 125519 18 a step motor that rotates the rotating plate; a color evaluation routine, executing on a computer that controls the step motor, the input loader, the output loader, the output sorter, and the camera, the color evaluation routine comprising: instructing the input loader to load a sample diamond onto the rotating plate; (a) instructing the camera to take a photo of the rotating plate, the photo including all diamonds on the rotating plate; (b) instructing the step motor to rotate therotating plate by an increment; repeating steps (a) and (b) until the rotating plate has been incremented Nm times; dividing each of Nm - 1 photos into Nt images, each image having one diamond; for each image, selecting a target area on the image that is within a boundary of the diamond in the image; reading pixel values for pixels within the target area and converting each of these pixel values into an x color value and a y color value; calculating an average x color value and an average y color value of pixels within the target area for each image; for the sample diamond and for each of the master stones, calculating a stone average x color value as an average of the average x color value for all images having a particular stone, and calculating a stone average y color value as an average of the average y color value for all images having the particular stone; generating a color grade number value with an x,y color space for the sample diamond and each of the master stones, the colorgrade number value being calculated as a projection position of a line fitted by the stone average x color value and the stone average y color value of the master stones; finding a selected master stone having a largest value of the color grade number value, wherein the selected master stone has a color that is clearer than a color of the sample diamond; outputting an indication of a known color grade of the selected master stone as the evaluated color grade of the sample diamond; instructing the output loader to remove the sample diamond from the rotating plate and instructing the output sorter to place the sample diamond into a sorted bin for the evaluated color grade of the sample diamond, whereby sample diamonds are loaded and unloaded onto the rotating plate and color evaluated by comparison to master stones in the x,y color space. 16. The system of claim 15 wherein the camera captures images having Red Green Blue (RGB) pixels; wherein the RGB pixels are converted to x and y colorvalues. 17. The system of claim 15 further comprising: a robotic arm that reaches through a cutout in the chamber to load or unload the sample diamond onto the rotating plate. WO 2026 / 076739 PCT / CN2024 / 125519 19 18. The system of claim 17 wherein the output sorter comprises a rotating ring around the chamber having output bins that are rotated into position. 19. The system of claim 15 wherein the x color values and y color values of the master stones are re­ generated for each evaluation of the sample diamond. 20. A method for evaluating color of a sample diamond comprising: placing master stones on mounts on a rotating plate, wherein the master stones are diamonds having a known color grade, wherein there are at least 7 master stones having at least 7 different known color grades; placing a sample diamond into a mount on the rotating plate; (a) instructing a camera to take a photo of the rotating plate, the photo including all diamonds on the rotating plate; (b) instructing a stepmotor to rotate the rotating plate by an increment; repeating steps (a) and (b) until the rotating plate has been incremented at least 7 times; dividing each of the photos into smaller images, each smaller image having one diamond; for each smaller image, selecting a target area on the smaller image that is within a boundary of the diamond in the smaller image; reading pixel values for pixels within the target area and converting each of these pixel values into an x color value and a y color value; calculating an average x color value and an average y color value for pixels within the target area for each smaller image; for the sample diamond and for each of the master stones, calculating a stone average x color value as an average of the average x color value for all smaller images having a particular stone, and calculating a stone average y color value as an average of the average y color value for all smaller images having the particular stone; generating a color grade number value对于样品钻石和每个母石,采用x,y颜色空间,颜色等级数值被计算为通过母石的平均x颜色值和平均y颜色值拟合的直线的投影位置;找到颜色等级数值最大的选定母石,其中选定母石的颜色比样品钻石的颜色更清澈;输出选定母石的已知颜色等级作为样品钻石的评估颜色等级;指示输出装载机从旋转板上取下样品钻石,并指示输出分拣器将样品钻石放入针对样品钻石评估颜色等级的分拣箱中,由此将样品钻石装载到旋转板上并卸载,并通过在x,y颜色空间中与母石进行比较来进行颜色评估。WO 2026 / 076739 PCT / CN2024 / 125519 l crv ocO I H d t 0 一LL 1 / 28 0.33 2 WO 2026 / 076739 PCT / CN2024 / 125519 X 2 / 28 FI G . 2 PR IO R AR T WO 2026 / 076739 PCT / CN2024 / 125519 CO 0 3 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 < 0 4 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 CO ST 0 5 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 O 0 6 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 7 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 co CD nri htiEj EJ — EJ CO <0 CD ◎ 8 / 28 FI G . 6 A 7^ 64 WO 2026 / 076739 PCT / CN2024 / 125519 9 / 28 FI G . 6 B ^6 4 WO 2026 / 076739 PCT / CN2024 / 125519 co (3) CO — ’—-------- CD <0 <0 10 / 28 FI G . 6 C WO 2026 / 076739 PCT / CN2024 / 125519 11 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 12 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 13 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 O 0 14 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 Q 0 15 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 16 / 28 0. 34 2 WO 2026 / 076739 PCT / CN2024 / 125519 X 17 / 28 FI G . 8 WO 2026 / 076739 PCT / CN2024 / 125519 18 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 19 / 28 FI G . 9 C WO 2026 / 076739 PCT / CN2024 / 125519 20 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 Q O) 21 / 28 WO 2026 / 076739PCT / CN2024 / 125519 22 / 28 FI G . 1 0 WO 2026 / 076739 PCT / CN2024 / 125519 23 / 28 FI G . 1 1 FI G . 1 2A WO 2026 / 076739 PCT / CN2024 / 125519 24 / 28 FI G . 1 2B WO 2026 / 076739 PCT / CN2024 / 125519 25 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 26 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 27 / 28 WO 2026 / 076739 PCT / CN2024 / 125519 28 / 28 INTERNATIONAL SEARCH REPORT International application No. PCT / CN2024 / 125519 A. CLASSIFICATION OF SUBJECT MATTER B07C5 / 342(2006.01)i; B07C5 / 02(2006.01)i; B07C5 / 36(2006.01)i; G01N21 / 25(2006.01)i According to International Patent Classification (IPC) or to both national classification and IPC B. FIELDS SEARCHED Minimum documentation searched (classification system followed by classification symbols) IPC: B07C; GOIN Documentation searched other than minimum documentation to the extent that such documents are included in the fields searched Electronic data base consulted during the international search (name of data base and, where practicable, search terms used) CNTXT, ENTXT, DWPI, CNKI:HONG KONG APPLED SCIENCE AND TECHNOLOGY RESEARCH INSTITUTE COMPANY LIMITED, WANG YUELIN, WANG ZIQI, ZHANG CHUN, diamond?, gemstone?, rotat+, color+, master, grade?, image, camera?, pixels, average, value?, load+, sort+ C. DOCUMENTS CONSIDERED TO BE RELEVANT Category* Citation of document, with indication, where appropriate, of the relevant passages Relevant to claim No. A CN 115769066 A (GEMOLOGICAL INSTITUTE OF AMERICA, INC.(GIA)) 07 March 2023 (2023-03-07) description, paragraphs 42-161, and figures 1-5 1-20 A CN 102596433 A (ETERNITY MANUFACTURING LIMITED) 18 July 2012 (2012-07-18) the whole document 1-20 A CN 106679811 A (SHIPU (SHANGHAI) OPTICS TECHNOLOGY CO., LTD.) 17 May 2017 (2017-05-17) the whole document 1-20 A CN 106840404 A (SHANDONG MEASUREMENT SCENCE RESEARCH INSTITUTE) 13 June 2017 (2017-06-13) the whole document 1-20 A CN 108027328 A (DE BEERS UK LTD.) 11 May 2018 (2018-05-11) the whole document 1-20 A CN 112381833 A (GOLDWAY TECHNOLOGY LIMITED) 19 February 2021(2021-02-19) the whole document 1-20 \<^\Further documents are listed in the continuation of Box C. See patent family annex. * Special categories of cited documents: “T’ later document published after the international filing date or priority “A” document defining the general state of the art which is not considered date and not in conflict with the appUcation but cited to understand the to be of particular relevance pnnciple or theory underlying the invention “D” document cited by the applicant in the international application “X” document of particular relevance; the claimed invention cannot be “E” earner application or patent but published on or after the international ^considered to involve an inventive step filing dote “L” document which may throw doubts on priority claim(s) or which is “Y” document of particular relevance; the claimed invention cannot be cited to establish the publication date of another citation or other considered to involve an inventive step when the documentis special reason (as specified) combined with one or more other such documents, such combination “O” document referring to an oral disclosure, use, exhibition or other being obvious to a person skilled in the art means document member of the same patent family “P” document published prior to the international filing date but later than the priority date claimed Date of the actual completion of the international search 24 June 2025 Date of mailing of the international search report 30 June 2025 Name and mailing address of the ISA / CN CHINA NATIONAL INTELLECTUAL PROPERTY ADMINISTRATION 6, Xitucheng Rd., Jimen Bridge, Haidian District, Bering 100088, China Authorized officer CHEN,Yang Telephone No. (+86) 010-53962368 Form PCT / ISA / 210 (second sheet) (July 2022) INTERNATIONAL SEARCH REPORT International application No. PCT / CN2024 / 125519 C. DOCUMENTS CONSIDERED TO BE RELEVANT Category* Citation of document, with indication, where appropriate, of the relevant passages Relevant to claim No. AUS 2010111354 Al (OPAL PRODUCERS AUSTRALIA LIMITED) 06 May 2010 (2010-05-06) the whole document 1-20 A US 2021131974 Al (SARINE TECHNOLOGIES LTD.) 06 May 2021 (2021-05-06) the whole document 1-20 Form PCT / ISA / 210 (second sheet) (July 2022) INTERNATIONAL SEARCH REPORT International application No. members PCT / CN2024 / 125519 Patent document cited in search report Publication date (day / month / year) Patent family memberfs) Publication date (day / month / year) CN 115769066 A 07 March 2023 US 2024385119 Al 21 November 2024 US 2023366830 Al 16 November 2023 US 12085511 B2 10 September 2024 WO 2021194774 Al 30 September 2021 US 2021302322 Al 30 September 2021 US 11499920 B2 15 November 2022 US 2023082604 Al 16 March 2023 US 11754506 B2 12 September 2023 EP 4107515 Al 28 December 2022 JP 2023511785 A 22 March 2023 JP 7321391 B2 04 August 2023 CN 102596433 A 18 July 2012 US 2012179290 Al 12 July 2012 US 9008832 B2 14 April 2015 wo 2011037481 Al 31 March 2011 EP 2480347 Al 01 August 2012 CN 106679811A 17 May 2017 None CN 106840404 A 13 June 2017 None CN 108027328 A 11 May 2018 JP 2018519511 A 19 July 2018 JP 6670327 B2 18 March 2020 US 2018156735 Al 07 June 2018 US 10393669 B2 27 August 2019 wo 2016203210 Al 22 December 2016 EP 3311144 Al 25 April 2018 EP 3311144 Bl 17 May 2023 CN 112381833 A 19 February 2021 US 2021033465 Al 04 February 2021 US 11326952 B2 10 May 2022 wo 2021018174 Al 04 February 2021 EP 3771902 Al 03 February 2021 US 2010111354 Al 06 May 2010 WO 2008119125 Al 09 October 2008 US 8436986 B2 07 May 2013 JP 2010523180 A 15 July 2010 JP 5474759 B2 16 April 2014 EP 2140251 Al 06 January 2010 EP 2140251 Bl 19 March 2014 US 2021131974 Al 06 May 2021 EP 3821234 Al 19 May 2021 EP 3821234 Bl 12 February 2025 US 11112368 B2 07 September 2021 WO 2020016884 Al 23 January 2022146433 As of May 12, 2022 US 11892412 B2 Filed as of February 06, 2024 2020016874 As of January 23, 2020 Form PCT / ISA / 210 (patent family annex) (July 2022) (19). (12)Window Attachment Attachment (10)Attachment Attachment CN 119562865 A.(43) Publication date: March 4, 2025 (21) Application number: 202480002329.3 (22) Application date: October 17, 2024 (30) Priority data: 18 / 911,583 October 10, 2024 US (85) Date of entry into the national phase of the PCT international application: October 25, 2024 (51) Int.CI. B07C 5 / 542 (January 2006) B07C 5 / 02 (January 2006) B07C 5 / 36 (January 2006) B07C 5 / 35 (January 2006) (86) Application data for the PCT international application: PCT / CN 2024 / 125519 October 17, 2024 (71) Applicant: Hong Kong Applied Science and Technology Research Institute Limited Address: 5 / F, Optoelectronics Centre, 2 Science Avenue East, Hong Kong Science Park, Sha Tin, New Territories, Hong Kong (72) Inventors: Wang Yuelin, Wang Ziqi, Zhang Chun (74) Patent Agency: Shenzhen Xinchuangyou Intellectual Property Agency Co., Ltd. 44223 Patent Attorney: Xie Linhong Claims: 4 pages Specification: 10 pages Drawings: 16 pages (54) Invention Title: Continuous Line for Automatic Diamond Color Grading Evaluation (57) Abstract: An automatic diamond color grading machine can grade the color of diamonds on a continuous line without manual color evaluation. Sample diamonds are conveyed by an input conveyor belt and placed on mounting seats on a rotating plate by a robotic arm. There are Nm mounting seats on the rotating plate, each mounting seat holding Nr color stones of known color grades and Ns sample diamonds. A camera takes a picture of all the diamonds on the rotating plate, and then a stepper motor rotates the rotating plate 360 / Nm degrees and takes another picture. This operation is repeated Nm times, so that the sample diamonds and all color stones are imaged at all Nm possible rotation positions. The average of pixels at all positions of each diamond is taken to obtain the x, y average of each diamond. The color grade of the sample diamond is the color comparison stone with the closest lighter x, y average. < ⑦ g CN 119562865 A Claims 1 / 4 page 1. An automatic gemstone color grading machine, comprising: a rotating plate having mounting seats on its surface, each mounting seat for supporting a gemstone; wherein the gemstones on the mounting seats include a sample gemstone and a series of color comparison gemstones, wherein the series of color comparison gemstones are color comparison gemstones with different known color grades; wherein the sample gemstone has an unknown color grade, the unknown color grade being between at least two color comparison gemstones with known color grades; a stepper motor for rotating the rotating plate in one or more increments less than one full revolution; an image sensor for capturing an image of the gemstone mounted on the rotating plate; a light source for illuminating the gemstone on the rotating plate; a computer for instructing the stepper motor to rotate the rotating plate by an increment, causing the sample gemstone to rotate.The computer moves the sample gem to a position previously occupied by one of the color-matching gems in the field of view of the image sensor; as the sample gem rotates sequentially to all positions previously occupied by the color-matching gems on the rotating plate, the computer causes the image sensor to capture an image after each rotation increment; wherein, with each increment of the rotating plate, each color-matching gem sequentially occupies the position of the sample gem and the other color-matching gems; the computer executes machine-readable instructions to select pixels for the sample gem and each color-matching gem from the images captured by the image sensor after each rotation increment; the computer averages the color index of these pixels of each gem at all increment positions of the gem to generate an average color value for each gem; the computer selects the closest color-matching gem from the color-matching gems whose average color value differs least from the average color values ​​of the sample gem and the color-matching gems; the computer outputs an indication of the known color grade of the closest gem as the color grade of the sample gem; thus, the color grade of the sample gem is determined by the average color index of the gem pixels captured by the image sensor at different rotation increments. 2. The automatic gemstone color grading machine of claim 1, wherein the gemstone is a diamond; wherein the negative difference between the average gemstone color value of the sample gemstone and the average gemstone color value of the closest gemstone is minimal; wherein the color of the sample gemstone is deeper than that of the closest gemstone. 3. The automatic gemstone color grading machine of claim 2, further comprising: a housing surrounding the rotating plate and allowing the image sensor to view the gemstone on the rotating plate; the interior of the housing and the rotating plate are made of a matte white material, providing a flat background for the image captured by the image sensor. 4. The automatic gemstone color grading machine of claim 3, wherein the housing is an open sphere, including an opening for the image sensor and an opening for placing the sample gemstone on an empty mounting seat on the rotating plate and removing it from the mounting seat on the rotating plate after the computer determines the color grade of the sample gemstone. 5. The automatic gemstone color grading machine of claim 4, further comprising: a robotic arm for picking up the sample gemstone from a sample gemstone input end and placing the sample gemstone into an empty mounting seat on the rotating plate, the robotic arm passing through an opening in the housing. 6. The automatic gemstone color grading machine according to claim 5, wherein after the computer determines the color grade of the sample gemstone, the robotic arm further passes through the housing and picks up the sample gemstone from the mounting base on the rotating plate.The robotic arm places the sample gemstone into an output chamber containing sample gemstones of the same color grade determined by the computer. 7. The automatic gemstone color grading machine of claim 6 further comprises: an output sorting machine having multiple output chambers, each output chamber for sample gemstones of different color grades, the output sorting machine being used to receive the color grade determined by the computer and move a target chamber with that color grade to an output position near the robotic arm so as to receive the sample gemstone from the robotic arm. 8. The automatic gemstone color grading machine of claim 6 further comprises: an input conveyor belt for moving sample gemstones from an input chamber for sample gemstones of unknown color grade to an input position near the robotic arm so that the robotic arm picks up the sample gemstone and places the sample gemstone on the mounting base on the rotating plate. 9. The automatic gemstone color grading machine of claim 3, wherein the image sensor is a camera, mounted on the housing at a 45-degree angle to the surface of the rotating plate; wherein the light source has a fixed color temperature between 5500K and 6500K. 10. The automatic gemstone color grading machine of claim 1, wherein the mounting base is a fixing device for holding the gemstone at an angle on the surface of the rotating plate; wherein the image sensor is mounted on the housing such that the axis of the gemstone is at a 45-degree angle to the image sensor. 11. The automatic gemstone color grading machine of claim 3, wherein the series of color-matching gemstones comprises at least 10 gemstones having at least 10 different known color grades; wherein the stepper motor rotates the rotating plate by at least 11 increments, and the image sensor captures images of all at least 11 increments. 12. The automatic gemstone color grading machine of claim 3, wherein pixels in the images captured by the image sensor are converted into color coordinate values ​​x and y in an xy color space, wherein the computer has an image processor that identifies the boundaries of the gemstones in the images and selects pixels from a target region within the boundaries for averaging; wherein for the sample gemstone and each color-matching gemstone, the pixels of that gemstone are averaged from the target regions in all increments of images captured by the rotating plate. 13. The automatic gemstone color grading machine of claim 12, wherein the computer selects the closest gemstone by the difference between the generated average values ​​x and y of color coordinates, each difference being the difference between the average values ​​x and y of the sample gemstone and the average values ​​x and y of one of the comparison gemstones, wherein the closest gemstone is the gemstone whose color is closest to and lighter than the sample gemstone. 14. The automatic gemstone color grading machine of claim 3, wherein each mounting seat on the rotating plate is radially distanced from the center of the rotating plate; wherein the mounting seats are equally spaced, and each mounting seat is equidistant from its nearest adjacent mounting seat on the rotating plate.The distances are equal; wherein the mounting bases are distributed circumferentially along the rotating plate; wherein the camera captures images of all gemstones at all incremental positions of the rotating plate under the same lighting conditions. 15. A system for evaluating the color of diamonds, comprising: a rotating plate having mounting seats arranged in a circle on its surface, each mounting seat for holding a diamond; wherein Nr mounting seats are pre-loaded with color comparison stones, said color comparison stones being diamonds of known color grades, wherein the Nr color comparison stones have Nr different color grades, wherein Nr is an integer of at least 3; wherein Nm is the total number of mounting seats on the rotating plate, wherein Nm is an integer of at least 4; wherein Ns mounting seats are loaded and unloaded with Ns sample diamonds of unknown color grades, wherein Ns is an integer of at least 1, wherein Nt is Ns+Nr; a camera for capturing images of the diamonds on the mounting seats on the rotating plate; a light source for illuminating the diamonds on the rotating plate; and a chamber that partially surrounds the rotating plate and provides a diffuse light background for the camera. An input loader for loading sample diamonds from an input diamond bin outside the chamber onto the Ns mounting seats on the rotating plate; an output loader for unloading sample diamonds from the Ns mounting seats on the rotating plate after evaluation; an output sorter for placing sample diamonds from the output loader into sorting bins that sort according to the color grade of the evaluated sample diamonds; a stepper motor for rotating the rotating plate; and a color evaluation routine executed on a computer that controls the stepper motor, the input loader, the output loader, the output sorter, and the camera, the color evaluation routine comprising: instructing the input loader to load sample diamonds onto the rotating plate; (a) instructing the camera to take a photograph of the rotating plate, the photograph including all diamonds on the rotating plate; (b) instructing the stepper motor to rotate the rotating plate in an increment; and repeating steps (a) and (b) until the rotating plate is rotated Nm times. Each of the Nm-1 photographs is divided into Nt images, each containing one diamond. For each image, a target region is selected within the boundary of the diamond in the image. The pixel values ​​of the pixels within the target region are read and each pixel value is converted into color coordinate values ​​x and y. The average color coordinates x and y of the pixels within the target region of each image are calculated. For the sample diamond and each of the color comparison stones, the average color coordinate x of the gemstone is calculated as the average of the average color coordinate x of all images containing the specific gemstone, and the average color coordinate y of the gemstone is calculated as the average of the average color coordinate y of all images containing the specific gemstone. For the sample diamond and each of the color comparison stones, x,The system calculates a color grade value in the y-color space, where the color grade value is calculated as the projection position of the fitted line between the gemstone color average x and the gemstone color average y of the color comparison stone; identifies a selected color comparison stone with the maximum color grade value, wherein the color of the selected color comparison stone is lighter than the color of the sample diamond; outputs an indication of the known color grade of the selected color comparison stone as the evaluated color grade of the sample diamond; instructs the output loader to unload the sample diamond from the rotating plate and instructs the output sorter to place the sample diamond into the sorting bin where the sample diamond's color grade has been evaluated, thereby loading and unloading the sample diamond onto the rotating plate and evaluating its color by comparison with the coordinates of the color comparison stone in the x,y color space. 16. The system of claim 15, wherein the camera captures an image having red, green, and blue (RGB) pixels; wherein the RGB pixels are converted into x and y color values. 17. The system of claim 15, further comprising: a robotic arm, which loads or unloads the sample diamond onto the rotating plate through an opening in the chamber. 18. The system of claim 17, wherein the output sorter comprises a rotating ring surrounding the chamber having an output compartment rotated into place. 19. The system of claim 15, wherein the x-color and y-color values ​​of the color stones are regenerated each time a sample diamond is evaluated. 20. A method for evaluating the color of a sample diamond, comprising: placing color stones on a mounting on a rotating plate, wherein the color stones are diamonds having known color grades, wherein at least 7 color stones have at least 7 different known color grades; placing a sample diamond on the mounting on the rotating plate; (a) instructing a camera to take a photograph of the rotating plate, the photograph including all the diamonds on the rotating plate; (b) instructing a stepper motor to rotate the rotating plate in an increment; repeating steps (a) and (b) until the rotating plate is rotated at least 7 times; dividing each photograph into smaller images, each smaller image containing one diamond; for each smaller image, selecting a target region on the smaller image, the target region being located within the boundary of the diamond in the smaller image; reading pixel values ​​of pixels within the target region and converting each pixel value into a color value x and a color value y; calculating the average color value x and the average color value y of the pixels within the target region of each smaller image; For the sample diamond and each color comparison stone, calculate the gemstone color average x as the average of the color average x of all smaller images containing the specific gemstone, and calculate the gemstone color average y as the average of the color average y of all smaller images containing the specific gemstone; generate color level values ​​in the x, y color space for the sample diamond and each color comparison stone, the color level...The value is calculated as the projection position of the fitted line of the gemstone color average value x and gemstone color average value y of the color comparison stone; the selected color comparison stone with the maximum color grade value is found, wherein the color of the selected color comparison stone is lighter than the color of the sample diamond; the known color grade of the selected color comparison stone is output as an indication of the evaluated color grade of the sample diamond; the output loader is instructed to remove the sample diamond from the rotating plate, and the output sorting machine is instructed to place the sample diamond into the sorting bin with the evaluated color grade, thereby the sample diamond is loaded onto the rotating plate and unloaded from the rotating plate, and the color is evaluated by comparing it with the color value of the color comparison stone in the x, y color space. 5 CN 119562865 A Specification 1 / 10 pages Continuous line for automatic diamond color grading evaluation [Technical Field]

[0001] The present invention relates to automatic inspection machines, and particularly to automatic color grading of diamonds. [Background Art]

[0002] For a long time, diamonds have been one of the most sought-after gemstones. Although diamonds are relatively scarce, their wide availability still stimulates consumer demand. Because every diamond is different, its price and value will vary greatly.

[0003] The quality of a diamond is based on the 4Cs: color, clarity, cut, and carat weight. Diamonds with high clarity are more valuable than pale yellow diamonds, and pale yellow diamonds are more valuable than lighter-colored diamonds. Typically, a professionally trained person with many years of experience will compare the diamond to be evaluated with a series of diamond master stones of different known color grades.

[0004] Figure 1 shows the color grades of diamonds. In terms of color alone, D-grade colorless diamonds are the most valuable, while Z-grade or lighter-colored diamonds (Z) are the least valuable. Grades D, E, and F are colorless, grades G, H, I, and J are close to colorless, while grades K, L, and M are lighter in color. Grades N to R are increasingly lighter in color, while lighter-colored diamonds are divided into grades S to Z.

[0005] Since its introduction in the early 1950s, the Gemological Institute of America (GIA) D to Z grading system has been used to color grade the vast majority of colorless to pale yellow gem-quality polished diamonds and to issue laboratory reports. The D to Z color grading is based on the observations of a trained observer who compares the diamond to be evaluated to a color comparison stone at a known position on the grading scale. GIA color comparison stones are located at the highest point in their respective grade ranges. Diamonds identical to G color comparison stones are graded G. If the color is slightly inferior, they are graded F.

[0006] Typically, trained personnel will arrange known color comparison stones in a row on a matte white background table under a light source with a color temperature of 5500-6500K. Both the diamond to be evaluated and the color comparison stones are examined at a 45-degree angle, with the gemstones directly facing the light source. The sample diamond is usually examined from several different directions.

[0007] Color can be qualitatively evaluated by humans. However, color can also be defined by a color space, such as the International Commission on Illumination (CIE) RGB XYZ.xy or Luminance, Aperture, Lightness (LAB) color space. Color can be represented by two or three numerical values ​​in a color space. For example, chromaticity in the CIE XYZ color space is specified by two derived parameters x and y, two of which are functions of all three tristimulus values ​​x, y, and z. The CIE xy chromaticity diagram shows the brightest color with the highest saturation. Machines can detect colors and report numerical values ​​in the selected color space.

[0008] Figure 2 shows a series of diamond color stones evaluated in the CIE 1931 color space chromaticity diagram. When normalized, the CIE 1931 color space uses x, y values ​​between 0 and 1 to represent colors. The same 10 color stones were evaluated using a colorimeter in three repeated tests.

[0009] In the first experiment 12, colorimetric stone D had the lowest x and y values, and colorimetric stone M had the highest x and y values. The x and y values ​​of colorimetric stones E through K increased sequentially, but then the x and y values ​​of colorimetric stone L were lower than those of colorimetric stone K, even though the x and y values ​​of colorimetric stone K should be lower than those of colorimetric stone L. This regression in the x and y values ​​of colorimetric stone L in experiment 12 is clearly incorrect.

[0010] In the second experiment 14, the x and y values ​​of colorimetric stones D and E were approximately the same, even though the x and y values ​​of colorimetric stone D should be lower. Colorimetric stones F and G were too close to each other, and their x and y values ​​should differ more.

[0011] In the third experiment 16, the x and y values ​​of colorimetric stones D and E were almost the same, but they should be different. The x and y values ​​of colorimetric stones L and M were also almost the same, but they should be different.

[0012] Although the same 10 color stones were evaluated in tests 12, 14, and 16, there was a deviation in each test. The x and y values ​​of most of the color stones in test 12 were shifted downwards and to the left relative to the x and y values ​​in test 14. The x and y values ​​in test 16 were shifted upwards (higher y values) and to the right (higher x values) relative to tests 12 and 14.

[0013] The shifts in x and y were small, approximately 0.001 for x and 0.002 for y, or about 0.3%. However, the distance between the color grades of the color stones was even smaller, approximately 0.0004 for x and 0.0003 for y. A more precise system is needed to evaluate sample diamonds so that their color grades are within 0.5. While different tests can tolerate shifts in x and y, for consecutive color stones, the x and y values ​​should steadily increase. There should be no regression.

[0014] Recently, automatic diamond color grading machines have begun to appear. Some machines use a manually rotated platform, which is slow and difficult to operate.Use. These machines may be expensive or have poor accuracy.

[0015] It is desirable to automatically color grade diamonds so that the color grade is within the range of + / - 0.5. An automated process and machine are needed to evaluate the color grade of sample diamonds. For automated diamond color grading, it is best to have a machine capable of continuously feeding sample diamonds for comparison with known color stones. [Figure Descriptions]

[0016] Figure 1 shows the color grade of diamonds.

[0017] Figure 2 shows a prior art series of diamond color stones evaluated in the CIE 1931 color space chromaticity diagram.

[0018] Figure 3 is a schematic diagram of a diamond color grading machine.

[0019] Figures 4A-4C show the rotating plate in more detail.

[0020] Figure 5 shows the target area on the diamond image.

[0021] Figures 6A-6D show the conveying system for loading and unloading sample diamonds on the rotating plate.

[0022] Figures 7A-7E show side views of the conveying system loading and unloading sample diamonds on the rotating plate.

[0023] Figure 8 is a graph showing the analysis of chromaticity and x, y color values ​​of contrasting stones using a diamond color grading machine.

[0024] Figures 9A-9D are flowcharts of the operation of the diamond color grading machine.

[0025] Figure 10 shows a diamond color grading machine with the input and output conveyors on the same side.

[0026] Figure 11 is a side view of a diamond color grading machine with the input and output conveyors on the same side but at different heights.

[0027] Figures 12A-12B are side views of another diamond color grading machine with a ring-shaped output sorting machine.

[0028] Figure 13 is a top view of another diamond color grading machine with a ring-shaped output sorting machine as shown in Figures 12A-12B.

[0029] Figure 14 shows another mounting method on the rotating plate.

[0030] Figure 15 shows another diamond color grading machine with a camera located directly above the diamond rotating plate.

Detailed Description

[0032] Figure 3 is a schematic diagram of a diamond color grading machine. A batch of sample diamonds can be fed into the diamond color grading machine, which has a conveyor or robotic arm system (not shown) for continuously feeding the sample diamonds and placing them on a rotating plate 30 for comparison with a set of color stones 10 also placed on the rotating plate 30. A stepper motor 24 rotates.A rotating plate 30 is used to place new sample diamonds on the rotating plate 30 and to remove sample diamonds that have been evaluated.

[0033] A light source 42 below the rotating plate 30 emits uniform white light to illuminate the colorimetric stones 10 and the sample diamonds on the rotating plate 30. The housing 46 may be a sphere with a flat white surface inside to scatter light from the light source 42 into the chamber 20 and provide a matte white background. The top surface of the rotating plate 30 may also be a matte white surface.

[0034] A camera 40 is mounted on a bracket 44 on the housing 46. An opening in the housing 46 allows the lens of the camera 40 to capture images of the sample diamonds and the colorimetric stones 10 reflected light on the rotating plate 30. A controller or computer 50 may allow the camera 40 to capture images after the computer 50 causes the stepper motor 24 to rotate the rotating plate 30 by a desired amount. The images captured by the camera 40 may be analyzed by the computer 50 or sent to another computer or server for further processing.

[0035] Figures 4A-4C show the rotating plate in more detail. In Figure 4A, the rotating plate 30 is empty and not loaded with diamonds. Multiple mounting seats 32 are arranged around the rotating plate 30. Each mounting seat 32 can be a recess in the rotating plate 30 into which diamonds can be placed via a conveyor or robotic arm. The mounting seat 32 can also be a raised mounting seat or clamp, held in place on the surface of the rotating plate 30, which can hold the diamonds in place as the rotating plate 30 rotates.

[0036] In Figure 4B, color stones 10 are placed in mounting seats 32. However, one mounting seat 32 remains empty. In this example, 11 color stones 10 are placed on the rotating plate 30.

[0037] In Figure 4C, a sample diamond 18 is placed in an empty mounting seat 32. All mounting seats 32 are occupied by either sample diamonds 18 or color stones 10. Each color stone 10 has a different color grade.

[0038] For a set of 11 color comparison stones 10 and one sample diamond, a total of 12 mounting bases 32 are placed on the rotating plate 30, each mounting base being spaced apart by a radial angle of 30 degrees (360 / 12). The computer 50 instructs the stepper motor 24 to rotate the rotating plate 30 by 30 degrees, and then instructs the camera 40 to take a picture of the rotating plate 30 and the sample diamond and color comparison stones 10 on it. Then the computer 50 instructs the stepper motor 24 to rotate another 30 degrees and take another picture. This operation is repeated, taking a total of 12 pictures, rotating 12 times, for a total of 360 degrees.

[0039] Figure 5 shows the target area on the diamond image. For each rotation of the stepper motor 24, the camera 40 takes a picture of all the color comparison stones 10 and sample diamond 18 on the rotating plate 30. The computer 50 detects the portion of the picture containing the diamond and divides the picture into 12 images, each image containing one diamond. Then, computer 50 can further process each single diamond image to select target area 48 on color comparison stone 10 or sample diamond 18.

[0040] The target area 48 may be within one facet or one face of the diamond, or may include multiple facets, or may include one or more edges of the diamond. The computer 50 may select the target area 48 as an area with a consistent color and no sudden color changes, or may simply define the boundary of the diamond and select the target area 48 as the area within the defined boundary.

[0041] Figures 6A-6D show a conveyor system for loading and unloading sample diamonds on a rotating plate. In Figure 6A, the rotating plate 30 is pre-loaded with 11 color comparison stones 10 and has an empty mounting base 32. The computer 50 has instructed the stepper motor 24 (not shown) to rotate the rotating plate 30 so that the empty mounting base 32 is aligned with the input conveyor belt 60. The sample diamond 18 is moved by the input conveyor belt 60 until it reaches the end of the input conveyor belt 60, at which point the sample diamond 18 falls into the mounting base 32. As the sample diamond 18 falls from the input conveyor belt 60, the mounting base 32 may be folded down to guide the sample diamond 18 into place.

[0042] In Figure 6B, the rotating plate 30 has rotated three times, a total of 90 degrees, so that the sample diamond 18 is at the top of Figure 6B. The camera 40 took three photos, one photo for each rotation of the rotating plate 30.

[0043] In Figure 6C, the rotating plate 30 has rotated six times, a total of 180 degrees, so that the sample diamond 18 is at the right side of Figure 6C. The camera 40 took six photos, one photo for each rotation of the rotating plate 30. 8 CN 119562865 A Specification 4 / 10 pages

[0044] Then, the computer 50 continues to step the rotating plate 30 until the sample diamond 18 returns to its initial position below the input conveyor belt 60. A total of 12 photos were taken during the 12 rotations of the rotating plate 30. Finally, the computer 50 causes the stepper motor 24 to rotate the rotating plate 30 180 degrees, so that the sample diamond 18 is placed below the output conveyor belt 62.

[0045] In Figure 6D, the sample diamond 18 has been removed from the mounting base 32 and placed on the output conveyor belt 62. A robotic arm (not shown) can pick up the sample diamond 18 from the rotating plate 30 and place it on the output conveyor belt 62.

[0046] The output sorter 64 has multiple bins 66, each holding sample diamonds 18 of different color grades. When the computer 50 determines the color grade of the sample diamond 18, the computer 50 commands the output sorter 64 to move the bins 66 so that the target bin 68 for the determined color grade is located below the end of the output conveyor belt 62. The sample diamond 18 then falls into the target bin 68.

[0047] Figures 7A to 7E show side views of the conveyor system loading and unloading sample diamonds from the rotating plate. In Figure 7A, the rotating plate 30 is pre-loaded with color stones 10 and has an empty mounting base 32. The computer 50 has instructed the stepper motor 24.(Not shown) Rotate the rotating plate 30 so that the empty mounting base 32 is aligned with the input conveyor belt 60. The sample diamond 18 moves along the input conveyor belt 60 until it reaches the end of the input conveyor belt 60, at which point the sample diamond 18 falls into the mounting base 32. As the sample diamond 18 falls from the input conveyor belt 60, the mounting base 32 can be retracted to guide the sample diamond 18 into place.

[0048] In FIG. 7B, the input conveyor belt 60 has fed the sample diamond 18 into the mounting base 32. The rotating plate 30 is now fully loaded with color stones 10 and sample diamond 18. The stepper motor 24 moves radially one step each time, and the camera 40 takes one picture. A total of Nt rotations are performed, and Nt pictures are taken. Nt = Ns + Nr, where Ns is the number of sample diamonds 18 on the rotating plate 30, and Nr is the number of color stones 10 on the rotating plate 30.

[0049] In Figure 7C, after the stepper motor 24 rotates radially by Nt steps, the computer 50 determines the color grade of the sample diamond 18. The computer 50 instructs the output sorter 64 to move the hopper 66 so that the target hopper 68 for the color grade determined by the computer 50 is aligned with the end of the output conveyor belt 62.

[0050] The computer 50 also activates the stepper motor 24 to rotate the rotating plate 30 by 180 degrees so that the sample diamond 18 is aligned with the output conveyor belt 62. Then, the computer 50 commands the robotic arm 72 to pick up the sample diamond 18 from the mounting base 32 on the rotating plate 30. In Figure 7D, the computer 50 commands the robotic arm 72 to move the sample diamond 18 onto the output conveyor belt 62 and place the sample diamond 18 onto the output conveyor belt 62.

[0051] In Figure 7E, the sample diamond 18 reaches the end of the output conveyor belt 62 and falls into the target hopper 68, which is moved by the output sorter 64 to a position below the end of the output conveyor belt 62. Target chamber 68 may contain other sample diamonds 18 with the same color grade (e.g., G grade).

[0052] Figure 8 is a graph of chromaticity and x, y color value analysis of diamonds using a diamond color grading machine. During each evaluation run or test, the rotating plate 30 rotates Nt times, and the camera 40 takes Nt photographs.

[0053] Although there are offsets in runs 22 and 26 compared to run 24, the order of the 10 color stones DM is correct in each test. Although color stones D and E are closer than the other color stones FM, the x, y values ​​of color stone D are still lower than those of color stone E. Sample stone 25 is correctly positioned between main stones E and F in all three runs 22, 24, and 26, so sample stone 25 can be correctly evaluated as color grade E. The x, y values ​​of the color stones are regenerated for each evaluation run of the sample stone to correct for any offsets that may occur between runs 22, 24, and 26, which may occur with changes in temperature and other operating conditions.

[0054] Evaluating the color of each colorimetric stone while evaluating the color of the sample stone can serve as an internal reference for correcting the operating conditions.The color shift is minimized. Therefore, calibration is not required before each evaluation run. The relative order of each color stone in the D to M range remains accurate. After evaluation runs on different dates, the distance and slope between adjacent grades of color stones in the D to M range are repeatable across the entire baseline. For sample diamond color evaluation, the color grade of sample 9 (CN 119562865 A, instruction manual page 5 / 10) remains within 0.5 after each evaluation run. [OOM] Figure 9A-Figure 9B shows the operation flowchart of the diamond color grading machine. In Figure 9A, in step 202, a total of Nr color stones 10 are placed on the mounting base 32 or bracket 73 on the rotating plate 30. During continuous line testing, many sample diamonds 18 are placed on and removed from the rotating plate 30, leaving the color stones 10 on the rotating plate 30.

[0056] In step 204, the diamond to be tested (DUT), i.e., sample diamond 18, is placed on the rotating plate 30. The input conveyor belt 60 can move the sample diamond 18 to the vicinity of the rotating plate 30, and then the robotic arm 72 picks up the sample diamond 18 and places it into the mounting base 32 or bracket 73 on the rotating plate 30.

[0057] In step 206, parameter P is set to the total number Nm of the mounting bases 32 on the rotating plate 30. When some mounting bases 32 are empty and there are no gemstones, this total number may be greater than Nt, where Nt is the sum of the number of sample diamonds 18 (Ns) and the number of color comparison stones 10 (Nr).

[0058] In step 208, the camera 40 takes a photograph of the initial rotation position of the rotating plate 30 and all its diamonds. In step 210, the photograph is stored for later access and processing by the computer. Then in step 212, the stepper motor 24 is started to rotate the rotating plate 30 by 360 / Nm degrees. This rotation will place the diamonds in the same position as in the previous photograph (step 208), but since all diamonds are offset by one position in the direction of rotation, the diamonds in each position are different. In step 214, parameter P is decremented to track the number of partial rotations.

[0059] In step 216, the photograph of all Nt diamonds on the rotating plate 30 in step 208 is divided into Nt smaller images. In these small images generated in step 216, each image contains only one diamond, while the large photograph in step 208 contains Nt diamonds. Image processing software running on a computer (such as an object detection program) can detect the outline of each diamond against the matte white background of the rotating plate 30 and the housing 46, and use the detected outline to cut the photograph into smaller images.

[0060] In step 218, while parameter P has not yet reached zero, camera 40 takes another photograph of all Nt diamonds, but rotates to a new position, while step 216 separates each diamond into a separate smaller image. This cycle is repeated Nm times, so each diamondThe diamonds are photographed at Nm positions relative to camera 40. The sample diamond 18 is rotated through all Nm positions in this cycle, and any slight changes in illumination at each position within chamber 20 are applied to all Nt diamonds.

[0061] In Figure 9B, after all Nm photographs are taken and each photograph is divided into Nt smaller images, there are Nm*Nt smaller images. For each of these Nm*Nt images (step 220), a target region 48 is selected in the smaller image (step 222). The target region 48 can be selected as a region within the diamond, or even a region within a facet of the diamond, or a region with uniform color within the diamond's outline. Regions in the diamond's outline that are saturated, pure black, or have abrupt, sudden color changes can be removed from the target region 48 because these regions may be reflective or cause image distortion.

[0062] In step 224, the red, green, and blue (RGB) pixel values ​​of all pixels within the target region 48 are obtained from the smaller images. Then in step 226, the computer converts these RGB values ​​into JCYZ values ​​in the CIE XYZ tristimulus color space. Then in step 230, the computer further calculates these HZ values ​​into xy values ​​in the CIE color space.

[0063] Then in step 232, the computer generates the average x and average y of all xy pixel values ​​for all pixels in the target region 48 in the current small image. In step 234, the average x and average y are stored for the small image.

[0064] In step 236, the image processing loop (steps 222-234) is repeated for all small images for a total of Nm*Nt loops. Once all Nm*Nt small images have been processed (step 236), the average values ​​of Nm*Nt x and y are stored.

[0065] In FIG9C, by tracking the rotation of the stepper motor 24 and the placement of the sample diamond 18, the computer tracks a small image corresponding to a color stone W and a sample diamond 18. For each diamond (step 250), for example for sample diamond 18 or for each color comparison stone 10, each diamond has Nt small images and Nt average values ​​of x and y. In step 252, the Nt average values ​​x and y of the diamond are read. In step 254, the Nt average values ​​x are averaged to obtain the average color value x of the diamond, and the Nt average values ​​y are averaged to obtain the average color value y of the diamond.

[0066] When Figure 9C ends, sample diamond 18 has a color value based on average values ​​x and y, color comparison stone 10 of grade D diamond has a color value based on average values ​​x and y, color comparison stone 10 of grade E diamond has a color value based on average values ​​x and y, and so on.

[0067] In Figure 9D, in step 248, Nr color comparison stones 10 of Nr diamond grades are averaged according to Nr average values ​​x and y, etc.The color grades are arranged in order and stored as a reference database. In step 240, the average values ​​x, y of sample diamond 18 are compared with the average values ​​x, y in the database to find the closest lighter color (left) color comparison stone. For example, the color grade values ​​of sample diamond 18 or color comparison stone 10 can be calculated as the projection position of a line fitted by the average values ​​x, y of color comparison stone 10. In step 242, the color comparison stone grade with the largest value that is smaller than that of sample diamond 18 is selected as the closest lighter color reference.

[0068] The left reference is effectively "rounded" to a better color grade, such that the color of the closest color comparison stone is lighter than the color of the sample gemstone. The computer sends the color grade determined in step 242 to the output sorter 64, which moves the hopper so that the target hopper 68 of the grade is aligned with the output conveyor belt 62. In step 244, the robotic arm 72 picks up sample diamond 18 from the rotating plate 30 and places sample diamond 18 into the target hopper 68 on the output conveyor belt 62. The computer may need to activate stepper motor 24 to align sample diamond 18 with output conveyor belt 62, and then align empty tray 73 with input conveyor belt 60 again to place the next DUT (steps 246, 204).

[0069] Figure 10 is a diamond color grading machine with input and output conveyor belts on the same side. In this alternative, both input conveyor belt 60 and output conveyor belt 62 are located on the right side of rotary plate 30. Input conveyor belt 60 and output conveyor belt 62 are adjacent to each other above rotary plate 30, or input conveyor belt 60 may be located above or below output conveyor belt 62. Output conveyor belt 62 may end above target hopper 68 on output sorter 64, while input conveyor belt 60 may extend above output sorter 64 to enter hopper (not shown) of input sample diamond 18 located outside output sorter 64. A single robotic arm 72 may move sample diamond 18 between rotary plate 30, input conveyor belt 60 and output conveyor belt 62.

[0070] Figure 11 is a side view of a diamond color grading machine with input and output conveyors on the same side but at different heights. In this alternative, both the input conveyor 60 and the output conveyor 62 are located to the right of the rotary plate 30. The input conveyor 60 and the output conveyor 62 are adjacent to each other above the rotary plate 30, with the input conveyor 60 above the output conveyor 62. The output conveyor 62 may terminate above the target hopper 68 on the output sorter 64, while the input conveyor 60 may extend above the output sorter 64 to enter the hopper (not shown) of the input sample diamond 18 located outside the output sorter 64. A single robotic arm 72 may move the sample diamond 18 between the rotary plate 30, the input conveyor 60, and the output conveyor 62.

[0071] Figures 12A-12B show side views of another diamond color grading machine with a ring-shaped output sorter.In Figure 12A, the input conveyor belt 60 moves the sample diamond 18' and places the sample diamond 18 into the empty mounting seat 32 on the rotating plate 30.

[0072] In Figure 12B, after evaluation, the robotic arm 72 picks up the sample diamond 18 from the rotating plate 30 and places the sample diamond 18 into the target hopper 68. The robotic arm 72 can gently place the sample diamond 18 into the target hopper 68 instead of letting the sample diamond 18 fall into the target hopper 68.

[0073] Figure 13 shows a top view of another diamond color grading machine with the ring-shaped output sorter shown in Figures 12A-12B. The output sorter 64' forms a ring around the rotating plate 30, and the hoppers 66 are arranged around the periphery of the rotating plate 30. The computer 50 instructs the output sorter 64' to rotate relative to the fixed input conveyor belt 60 and output conveyor belt 62 to rotate the target hopper 68 below the end of the output conveyor belt 62.

[0074] Figure 14 shows another mounting method on the rotating plate. The robotic arm 72 picks up the sample diamond 18* from the input conveyor belt 60 and places it into the holder 73. The holder 73 is a V-shaped support device mounted on the upper surface of the rotating plate 30. The holder 73 holds the sample diamond 18 or color stone 10 on the upper surface of the rotating plate 30 at a standard design angle. When the camera 40 is mounted directly above, as shown in Figure 15, the holder 73 provides a viewing angle of exactly 45 degrees to meet GIA observation standards through the camera 40. The viewing angle is the angle between the camera 40 and the gemstone axis, which passes through the culet of the gemstone and is perpendicular to the table facet (top surface) of the sample diamond 18 or color comparison stone 10. Furthermore, when the robotic arm 72 places the sample diamond 18 into the holder 73, the slope of the groove in the holder 73 helps guide the sample diamond 18 into place within the holder 73.

[0075] Figure 15 shows another diamond color grading machine with the camera positioned directly above the diamond rotating plate. When using the holder 73 (Figure 14) with a V-shaped bottom, the color comparison stone 10 and the sample diamond 18 are at an angle to the rotating plate 30. To achieve the viewing angle between the camera 40 and the gemstone axis (which passes through the culet of the sample diamond 18 or color comparison stone 10 in the holder 73 and is perpendicular to the table facet (top surface)), the camera 40 and the support 44 are moved to an opening at the top of the housing 46. The light source 42 can also be placed below the rotating plate 30 to provide appropriate illumination to the chamber 20. Other light sources may also be present within the housing 46 to provide optimal illumination. [Alternative Embodiments]

[0076] The inventors have also envisioned several other embodiments. For example, various combinations and variations of the apparatus and method are possible. In FIG9, color conversion, target region 48 detection, and pixel averaging can be performed after all Nm photos have been taken, or...This is performed after each photo is taken. All RGB pixels in the target area can be averaged together to obtain the average RGB value of the target area. Then, in steps 226, 230, and 232 of Figure 9B, the average RGB value is converted to an average XYZ value, and then to an average x, y value. Alternatively, all pixels can be averaged after the XYZ conversion and before the x, y conversion. Alternatively, only one RGB to xy conversion can be performed, instead of first converting RGB to XYZ and then to xy. A three-dimensional R, G, B image can also be used instead of a two-dimensional x, y image for color grading without conversion to x, y values, although this would reduce accuracy and increase computational workload.

[0077] The rotating plate 30 can be circular or other shapes, but it still provides clearance for rotation within the housing 46. The housing 46 can be spherical or other shapes. A sphere is considered to better integrate light and provide planar background illumination, but other shapes of the housing 46, even if less ideal, can provide sufficiently uniform illumination.

[0078] In addition to the light source 42, other light sources may be present inside the housing 46 to provide optimal illumination. The position and number of light sources can be modified, and the intensity and color profile of the light sources can be adjusted, for example, under program control. The program can adjust the white balance or color temperature of the light source 42 within a certain range, for example, 5500-6500K. Testing can be performed to find the optimal settings for the light source intensity and color temperature, thereby producing optimal background light uniformity within the chamber 20 to achieve color grading accuracy.

[0079] An opening or hole can be made on the side of the housing 46 to allow the input conveyor belt 60 to enter the chamber 20. Alternatively, the end of the input conveyor belt 60 can be outside the housing 46, and then a robotic arm can pick up the sample diamond 18 from the input conveyor belt 60 outside the housing 46, pass the sample diamond 18 through the hole into the chamber 20, and then place the sample diamond 18 on the mounting seat 32 on the rotating plate 30. This allows the hole on the housing 46 to be smaller, reducing the non-uniformity of the background light within the chamber 20. The alternatives in Figures 10 and 11 may offer better lighting because their input conveyor 60 and output conveyor 62 are on the same side. This allows a single robotic arm 72 to use one opening in the housing 46 without needing to create another opening for the output conveyor 62. This opening in the housing 46 can have a door or curtain that closes after the robotic arm 72 loads the sample diamond 18 onto the rotating plate 30. Such a door can provide more uniform lighting within the chamber 20 compared to leaving an opening in the housing 46. The door can be painted the same matte white as the interior of the housing 46. [OOM] While an output sorter 64 with a hopper 66 and a target hopper 68 has been described, the hopper can be a cloth bag, pouch, or other collection device with flexible sides. The output sorter 64 can operate in various modes other than linear or rotary.119562865 A Instruction Manual Page 8 / 10 'Move the hopper 66 to select the target hopper 68. The output sorter 64, input conveyor belt 69, output conveyor belt 62, and robotic arm 72 can have various variations and physical configurations.

[0081] The robotic arm 72 can have clamps to grip the sample diamond 18, or it can have a small tube with a vacuum to hold the sample diamond 18 during movement. The robotic arm 72 can rotate in various ways to better align the sample diamond 18 with the mounting base 32. When the range of motion and stroke length of the robotic arm 72 are large, it is not necessary to precisely align it with the sample diamond 18 on the rotating plate 30. The robotic arm 72 can pick up diamonds from multiple mounting bases on the rotating plate 30, thus avoiding rotation for alignment. The input conveyor belt 60 can be used, and the robotic arm can be used to put the sample diamond directly into the target hopper, thus eliminating the need for the output conveyor belt 62.

[0082] The mounting base 32 can have various shapes and features to better hold and align the sample diamond 18, and can hold the sample diamond 18 at an angle to the plane of the rotating plate 30. When the mounting base 32 has a built-in angle, the position of the camera 40 can be adjusted from the 45-degree position shown in FIG3, so that the viewing angle of the camera 40 is at 45 degrees to the axis of the sample diamond 18 and the color stone 10 on the rotating plate 30. Other viewing angles can also be used instead of 45 degrees.

[0083] The interior of the housing 46, the surface of the rotating plate 30, and the mounting base 32 or bracket 73 can be coated with the same matte white, or can be made of matte white plastic or other materials. There may be some unevenness, such as screw heads, gaps, or seams, but it is best to keep these to a minimum to improve the light uniformity within the chamber 20.

[0084] Various types of mounting bases 32 or brackets 73 can be used. Ideally, both the sample diamond 18 and the color comparison stone 10 use the same mounting base 32 or bracket 73, but the sample diamond 18 can be mounted on a different bracket 73 than the mounting base 32 of the color comparison stone 10. However, the mounting base 32 and bracket 73 should not introduce inhomogeneities in the image captured by the camera 40, or these inhomogeneities should be able to be removed when selecting the target area 48 from a large photograph. The target area 48 can be a combination of multiple areas within the diamond, all of which are included in the image processing and averaging of the diamond. The target area 48 can be discontinuous, rather than independent areas bounded by polygons. The mounting base 32 or bracket 73 can be a support device or integrated with the rotating plate 30.

[0085] The color comparison stones can all have the same carat weight, preferably the same as the carat weight of the sample diamond. The cut and clarity of all color comparison stones in the combination can also be the same or similar. The better the match between the color comparison stone 10 and the sample diamond 18, the better the color grading. However, an automatic color grading system can also be fully utilized when the match is not ideal, althoughSome accuracy may be lost. The color stones 10 can be placed on the rotating plate 30 in their known color grade order or in a random order. However, the program can be instructed when to place diamonds of different grades on the rotating plate 30 so that the program can track these diamond grades. Alternatively, the program can also determine the grade based on the x, y values ​​of the color stones and the order of the x, y values.

[0086] Another method for unloading the diamond sample 18 onto the output conveyor belt 62 is to install a ejection mechanism on the mounting base 32 to eject the sample diamond 18 from the mounting base 32 onto the output conveyor belt 62. Another method is to install a gate below the mounting base 32 on the rotating plate 30, which, when opened, allows the sample diamond 18 to fall through the gate on the rotating plate 30 onto the output conveyor belt 62 or into the target hopper 68 located below the rotating plate 30.

[0087] The mounting bases 32 or brackets 73 on the upper surface of the rotating plate 30 can be spaced at equal angles and at equal distances from the center of the rotating plate 30. Therefore, when the rotating plate 30 rotates 360 / Nm degrees (where Nm is the number of mounts 32 or brackets 73), the camera 40 will see different color comparison stones 10 or sample diamonds 18 in the same position as the previous diamonds. Another method is to use unequal angles, or for some diamonds to be farther from the center of the rotating plate 30 than others, and the program can map these variations. The mounts 32 can be non-circular or curved along a circle. When Nm > Nt, empty mounts without gemstones may appear. For example, there may be 6 mounts on the rotating plate 30, but only 3 gemstones. For best results, each gemstone should be photographed under the same lighting conditions at each position. For example, if there are 6 mounts and the last 3 mounts are empty, gemstone 1 can be photographed at photo numbers 1, 2, and 3. But gemstone 2 can be photographed at photo numbers 2, 3, and 6, and gemstone 3 at photo numbers 1, 5, and 6. In this example, although there are only 3 gemstones (Nt = 3), the rotating plate 30 can rotate Nm = 6 times. The gemstones can be placed in any empty slot on the rotating plate 30.

[0088] Although only one sample diamond 18 is shown on the rotating plate 30, there may be more than one sample diamond 18, such as Ns. In addition, the number of color stones 10 Nr can vary, and the total number of diamonds Nt = Ns + Nr can also vary. There may also be empty slots 32 or brackets 73 on the rotating plate 30 that are not occupied by diamonds. The program can filter out these unoccupied mounting positions and not include them. When the stepper motor 24 is started, the program can track each color stone 10 and its current position on the rotating plate 30, and once all Nt positions of the rotating plate 30 have been captured, the same color stone 10 is averaged at these positions.

[0089] Although CIE has been describedThe XYZ color space can be used, but other color spaces can also be used. For example, camera 40 can capture pixels using RGB, and then the processor or computer can convert RGB to XYZ. XYZ is superior to RGB because Y is brightness or intensity and does not contain color information. Therefore, in the XYZ color space, color is represented by only two variables, X and Y, instead of three variables, R, G, and B. Using two variables makes it easier to draw and compare color values. Removing the Z brightness component helps to mask variations in illumination brightness within chamber 20 and provides more accurate color grading. The computer can perform conversions between multiple color spaces, such as XYZ and xyZ. Other color spaces, such as CIE Lab, Hue / Saturation / Luminance (HSL), or Hue / Saturation / Luminance (HSV), can also be used. Various filters and image processing can also be performed.

[0090] When camera 40 outputs RGB, steps 224 and 226 of FIG9B are used. When camera 40 can output XYZ, steps 224 and 226 can be skipped or modified.

[0091] Although camera 40 has been shown, various image sensors and lens systems can be used to transmit light to the image sensors. There can be more than one camera 40 mounted on housing 46, allowing multiple images to be taken simultaneously, observing the rotating plate 30 from different angles. The angle between camera 40 and rotating plate 30 can be adjusted, or various mounting brackets or supports 44 can be used instead.

[0092] Although it has been described that camera 40 takes one image every 360 / Nm of rotation of rotating plate 30, more images can be taken with smaller rotation increments. For example, one image can be taken every 360 / (2*Nm) degrees, doubling the average number of images. This can improve accuracy. Alternatively, camera 40 can be a video camera that can capture a series of consecutive frames, which computer 50 can select according to the desired rotation interval.

[0093] There may be other mounting seats 32 where diamonds are not placed; the image processing of computer 50 can ignore these empty mounting seats. When Ns is 2 or greater, computer 50 can color grade two or more sample diamonds during a single 360-degree rotation, thereby increasing throughput.

[0094] Although diamonds have been described, other gemstones may be used instead. Although a circular or annular rotating plate 30 has been described, the rotating plate 30 may be elliptical, octagonal, square, or other shapes, but sufficient rotation clearance is still provided within the chamber 20. Computer 50 may be a personal computer (PC), controller, or processor with memory (such as semiconductor main memory), may have mass storage (such as flash drives or hard disk drives), and may have I / O interfaces (such as interfaces to networks (such as the Internet)). Computer 50 may offload some processing tasks to external servers, such as dedicated image processing servers.Neural networks can be used for certain processing tasks. The steps in Figure 9 can be implemented by a computer executing machine-readable instructions that control the stepper motor 24 and the robotic arm, conveyor belt, and camera.

[0095] Various values ​​can be calculated instead of stored. For example, once all Nm*Nt small images have been processed (step 236 in Figure 9), Nm*Nt average values ​​x and y are stored. Alternatively, the original Nm*Nt x and y values ​​can be stored instead of the average values ​​of x and y. The Nt average values ​​x and y can then be calculated when needed in Figure 9C. 14 CN 119562865 A Specification 10 / 10 pages

[0096] The input conveyor belt 60, robotic arm 72, rotary plate 30, and output conveyor belt 62 can detect continuous diamond lines as sample diamonds 18. When the hopper 66 on the output sorter 64 is full, the machine can be paused to replace the full hopper with an empty one, or to remove the sorted diamonds from the output sorter 66. Untested diamonds can be poured into the input chamber and sent to the input conveyor belt 60. Of course, the continuous diamond production line can be paused for various reasons, such as loading, unloading, error handling, maintenance, or work stoppage at the end of the day. Many color grading machines can be operated manually without the need for skilled, trained experts to examine each diamond.

[0097] Terms such as up, down, above, below, horizontal, vertical, inside, outside, etc., are relative and depend on the viewing angle, and do not mean that the invention is limited to a particular viewing angle. The equipment can be rotated so that vertical becomes horizontal and horizontal becomes vertical, so these terms depend on the viewer.

[0098] The background section of the invention may contain background information about the problem or environment of the invention, rather than describing the prior art of others. Therefore, the material included in the background section is not an admission of prior art by the applicant.

[0099] Any methods or processes described herein are implemented by machines or computers and are intended to be performed by machines, computers or other devices, and are not intended to be performed by humans alone without machine assistance. Tangible results may include reports or other machine-generated displays on display devices such as computer monitors, projection devices, audio generation devices, and associated media devices, and may include hard-copy printouts that are also machine-generated. Computer control of other machines is another tangible result.

[0100] Any advantages and benefits described herein may not necessarily apply to all embodiments of the invention. When the word “apparatus” appears in a claim element, the applicant intends that the claim element fall within the provisions of Section 112, paragraph 6 of 35 USC. Typically, one or more words precede the word “apparatus.” One or more words preceding the word “apparatus” are a label intended to facilitate reference to the claim element, not to express structural limitation. Such apparatus plus functionThe claims shall cover not only the structure described herein for performing the function and its structural equivalents, but also equivalent structures. For example, although nails and screws have different constructions, they are equivalent structures because they both perform the fastening function. Claims that do not use the term "device" do not fall under the provisions of Section 112, paragraph 6 of 35 USC. Signals are typically electronic signals, but can also be optical signals, for example, transmitted via fiber optic lines.

[0101] The above description of embodiments of the invention is provided for purposes of illustration and description. It is not intended to be exhaustive, nor is it intended to limit the invention to the precise forms disclosed. Many modifications and variations are possible based on the above teaching. The purpose is that the scope of the invention is not limited by this detailed description, but rather by the appended claims. 15 CN 119562865 A Specification Figure 1 / 16 Page Near colorless Very faint L Colorless Micro II I Figure 1 Prior art 0.332 - 0.331 - 0.329 - 0.328 - 0.327 Figure 2 Prior art 0.330 - y 0.309 0.310 0.311 0.312 0.313 0.314 0.315 X 12 Fly X / d / E : : • :D 11 EFGH 1 JKLMN OP QR ST UV WX YZ >Z ; • 1 Matter • ml \ K 16 CN 119562865 A Specification Figure 2 / 16 Page 17 CN 119562865 A Specification Figure 3 / 16 Page Figure 4B Figure 4C 18 CN 119562865 A. Instruction manual, Figure 6A, page 4 / 16, CN 119562865 A. Instruction manual, Figure 6B, page 5 / 16, CN 119562865 B. Figure 6C, CN 119562865 A. Instruction manual, Figure 6D, CN 119562865 A. Instruction manual, Figure 7D, CN 119562865 A. Instruction manual, Figure 7D, CN 119562865 A. Instruction manual, Figure 8D, CN 119562865 A. Instruction manual, Figure 8D, CN 119562865 A. Instruction manual, Figure 8D, CN 119562865 A. Instruction manual, Figure 9A, CN 119562865 A. Instruction manual ...B. Instruction manual, CN 119562865 A. Instruction manual, CN 119562865 B. Instruction manual, CN 119562865 A. Instruction manual, CN 119562865 B. Instruction manual, CN 119562865 B. Instruction manual, CN 119562865 B. Instruction manual, CN 119562865 B. Instruction manual, CN 119562 Instruction manual, Figure 9B, page 10 / 16; Figure 9B, page 11 / 16: Z252 average values ​​x, y for all Nt images of each diamond read.Calculate the total average value of the diamond based on the average value x,y, as the color average value x,y of the diamond. Figure 9C 254 26 CN 119562865 A Instruction Manual Appendix 12 / 16 Page. Establish a database of all reference diamond color average values ​​x,y / 248. Compare the color average value x,y of the DUT with the color average value x,y of each reference diamond in the database, and find the closest reference diamond color grade. The DUT color grade is rated as the closest reference diamond grade to the left. Remove the DUT from the rotating plate and place it in the DUT / 244 color grade compartment. Figure 9D 27 CN 119562865 A Instruction Manual Appendix 13 / 16 Page. Figure 10 28 CN 119562865 A Instruction Manual Appendix 14 / 16 Page. Figure 12B 29 CN 119562865 A Instruction Manual Appendix 15 / 16 Page. 30 CN 119562865 A Instruction manual, Figure 16 / 16, page 31

Claims

1. An automatic gemstone color grading machine, comprising: a rotating plate having mountings on its surface, each mounting being used to support a gemstone; wherein the gemstones on the mounting include a sample gemstone and a series of reference gemstones, wherein the series of reference gemstones have reference gemstones of different known color grades; The sample gemstone has an unknown color grade that is between at least two reference gemstones of known color grades; a stepper motor for rotating the rotating plate in one or more increments less than a full revolution; An image sensor for capturing an image of the gemstone mounted on the rotating plate; a light source for illuminating the gemstone on the rotating plate; a computer for instructing the stepper motor to rotate the rotating plate by one increment so that the sample gemstone rotates to a position previously occupied by one of the reference gemstones in the field of view of the image sensor; when the sample gemstone rotates sequentially to all positions previously occupied by the reference gemstones on the rotating plate, the computer causes the image sensor to capture an image after each rotation increment; Wherein, as the rotating plate increases in size, each colorimetric gemstone sequentially occupies the position of the sample gemstone and other colorimetric gemstones; The computer executes machine-readable instructions, causing the computer to select pixels for the sample gemstone and each reference gemstone from the image captured by the image sensor after each rotation increment, the computer averages the color index of these pixels for each gemstone at all incremental positions of the gemstone to generate a gemstone average color value for each gemstone, the computer selects a closest reference gemstone from the reference gemstones, the gemstone average color value of the closest reference gemstone having the smallest difference from the gemstone average color values ​​of the sample gemstone and the reference gemstone, and the computer outputs an indication of the closest known color grade of the gemstone as the color grade of the sample gemstone, Thus, the color grade of the sample gemstone is determined by the average of the color indices of the gemstone pixels captured by the image sensor at different rotation increments.

2. The automatic gemstone color grading machine according to claim 1, wherein the gemstone is a diamond; The negative difference between the average color value of the sample gemstone and the average color value of the gemstone closest to the gemstone is the smallest; The sample gemstone is darker in color than the closest gemstone.

3. The automatic gemstone color grading machine according to claim 2, further comprising: a housing that surrounds the rotating plate and enables the image sensor to view the gemstone on the rotating plate; The interior of the housing and the rotating plate are made of matte white material, providing a flat background with uniform color for the image captured by the image sensor.

4. The automatic gemstone color grading machine according to claim 3, wherein the housing is a sphere with openings, including an opening for the image sensor, and an opening for placing the sample gemstone on a vacant mount on the rotating plate and removing the sample gemstone from the mount on the rotating plate after the computer determines the color grade of the sample gemstone.

5. The automatic gemstone color grading machine according to claim 4, further comprising: A mechanical arm is used to pick up the sample gem from the sample gem input end and place the sample gem into an empty mounting seat on the rotating plate. The mechanical arm passes through an opening of the shell.

6. An automatic gemstone color grading machine according to claim 5, wherein after the computer determines the color grade of the sample gemstone, the robotic arm also passes through the housing to pick up the sample gemstone from the mounting seat on the rotating plate, and the robotic arm places the sample gemstone into an output bin, wherein the output bin is filled with sample gemstones of the same color grade determined by the computer.

7. The automatic gemstone color grading machine according to claim 6, further comprising: an output sorter having a plurality of output bins, each output bin being for sample gemstones of a different color grade, the output sorter being for receiving the color grade determined by the computer and moving a target bin having the color grade to an output position proximate to the robotic arm for receiving the sample gemstones from the robotic arm.

8. The automatic gemstone color grading machine of claim 6, further comprising: An input conveyor is used to move sample gemstones from a sample gemstone input bin with unknown color grade to an input position close to the robotic arm so that the robotic arm picks up the sample gemstones and places the sample gemstones on the mounting seat on the rotating plate.

9. The automatic gemstone color grading machine according to claim 3, wherein the image sensor is a camera, which is mounted on the housing at an angle of 45 degrees to the surface of the rotating plate; The light source has a fixed color temperature between 5500K and 6500K.

10. The automatic gemstone color grading machine according to claim 1, wherein the mount is a fixture that holds the gemstone on the surface of the rotating plate at a certain angle; The image sensor is mounted on the housing so that the axis of the gemstone forms an angle of 45 degrees with the image sensor.

11. The automatic gemstone color grading machine according to claim 3, wherein: The series of master color gemstones includes at least 10 gemstones having at least 10 different known color grades; The stepper motor rotates the rotating plate by at least 11 increments, and the image sensor captures images of all at least 11 increments.

12. The automatic gemstone color grading machine according to claim 3, wherein pixels in the image captured by the image sensor are converted into color coordinate values ​​x and y in an xy color space, wherein the computer has an image processor that identifies the boundaries of the gemstones in the image and selects pixels from a target area within the boundaries for averaging; For the sample gemstone and each reference gemstone, pixels of the gemstone in the target area in the images taken from all increments of the rotating plate are averaged.

13. The automatic gemstone color grading machine according to claim 12, wherein the computer selects the closest gemstone by generating differences in color coordinate average values ​​x and y, each difference being a difference between the average values ​​x and y of the sample gemstone and the average values ​​x and y of one of the reference gemstones, The closest gemstone is the gemstone that is closest in color and lighter than the sample gemstone.

14. The automatic gemstone color grading machine of claim 3, wherein each of the mounts on the rotating plate is at the same radial distance from the center of the rotating plate; wherein the mounting seats are all separated by equal distances, and each mounting seat is at an equal distance from the nearest adjacent mounting seat on the rotating plate; wherein the mounting seats are distributed along the circumference of the rotating plate; The camera captures images of all gemstones at all incremental positions of the rotating plate under the same lighting conditions.

15. A system for evaluating diamond color, comprising: a rotating plate, on whose surface there are mounts arranged along a circle, each mount being intended to accommodate a diamond; wherein Nr mountings are pre-mounted with master stones, the master stones being diamonds of known color grades, wherein the Nr master stones have Nr different color grades, wherein Nr is an integer of at least 3; wherein Nm is the total number of mounts on the rotating plate, wherein Nm is an integer of at least 4; wherein Ns mounts load and unload Ns sample diamonds of unknown color grade, wherein Ns is an integer of at least 1, wherein Nt is Ns+Nr; A camera for capturing an image of the diamond on the mounting seat on the rotating plate; a light source for illuminating the diamond on the rotating plate; a chamber that partially surrounds the rotating plate and provides a diffuse light background for the camera; an input loader for loading sample diamonds from an input diamond bin outside the chamber onto the Ns mounts on the rotating plate; an output loader for unloading sample diamonds from the Ns mounts on the rotating plate after evaluation; an output sorter for placing the sample diamonds from the output loader into sorting bins which are sorted according to the assessed color grade of the sample diamonds; A stepper motor, which is used to rotate the rotating plate; A color evaluation routine executed on a computer that controls the stepper motor, the input loader, the output loader, the output sorter, and the camera, the color evaluation routine comprising: instructing the input loader to load a sample diamond onto the rotating plate; (a) instructing the camera to take a picture of the rotating plate, the picture including all diamonds on the rotating plate; (b) instructing the stepper motor to rotate the rotating plate in one increment; Repeat steps (a) and (b) until the rotating plate is incremented Nm times; Split each of the Nm-1 photos into Nt images, each containing a diamond; For each image, selecting a target region on the image, the target region being located within the diamond boundary in the image; Reading pixel values ​​of pixels within the target area and converting each pixel value into color coordinate values ​​x and y; Calculate the average x and y color coordinates of the pixels in the target area of ​​each image; For the sample diamond and each of the master stones, calculate the average value of the gemstone color coordinate x as the average value of the color coordinate x values ​​of all images containing the specific gemstone, and calculate the average value of the gemstone color coordinate y as the average value of the color coordinate y values ​​of all images containing the specific gemstone; Generate a color grade value in x,y color space for the sample diamond and each of the master stones, wherein the color grade value is calculated as the projection position of the fitted line of the gemstone color average value x and the gemstone color average value y of the master stone; Finding a selected master stone having a maximum color grade value, wherein the color of the selected master stone is lighter than the color of the sample diamond; outputting an indication of the known color grade of the selected master stone as the estimated color grade of the sample diamond; instructing the output loader to unload the sample diamonds from the rotating plate, and instructing the output sorter to place the sample diamonds into a sorting bin of the sample diamonds having an assessed color grade, Sample diamonds are thereby loaded and unloaded onto the rotating plate and their color assessed by comparison with the coordinates of a master stone in x,y color space.

16. The system of claim 15, wherein the camera captures images having red, green, and blue (RGB) pixels; Where RGB pixels are converted to x and y color values.

17. The system of claim 15, further comprising: A robotic arm loads or unloads the sample diamond onto the rotating plate through an opening in the chamber.

18. The system of claim 17, wherein said output sorter comprises a rotating ring surrounding said chamber, the rotating ring having an output bin rotated into position.

19. The system of claim 15, wherein the x color value and the y color value of the master stone are regenerated each time a sample diamond is evaluated.

20. A method for evaluating the color of a sample diamond, comprising: placing master stones on a mount on the rotating plate, wherein the master stones are diamonds having known color grades, wherein at least seven of the master stones have at least seven different known color grades; placing a sample diamond on a mount on the rotating plate; (a) instructing a camera to take a picture of the rotating plate, the picture including all diamonds on the rotating plate; (b) instructing the stepper motor to rotate the rotating plate in one increment; Repeating steps (a) and (b) until the rotating plate is incremented at least 7 times; Split each photo into smaller images, each with a diamond; For each smaller image, selecting a target region on the smaller image, the target region being within the diamond boundary in the smaller image; Read the pixel values ​​of the pixels in the target area, and convert each pixel value into a color value x and a color value y; Calculate the color average x and color average y of the pixels in the target area of ​​each smaller image; For the sample diamond and each of the master stones, calculate the gemstone color average x as the average of the color averages x of all the smaller images containing the specific gemstone, and calculate the gemstone color average y as the average of the color averages y of all the smaller images containing the specific gemstone; Generate color grade values ​​in x,y color space for the sample diamond and each master stone, wherein the color grade values ​​are calculated as the projection positions of the fitted lines of the gemstone color average value x and the gemstone color average value y of the master stone; Finding a selected master stone having a maximum color grade value, wherein the color of the selected master stone is lighter than the color of the sample diamond; outputting an indication of the known color grade of the selected master stone as the estimated color grade of the sample diamond; instructing an output loader to remove the sample diamonds from the rotating plate and instructing an output sorter to place the sample diamonds into a sorting bin for which color grade has been assessed, Thereby, the sample diamond is loaded onto and unloaded from the rotating plate and the color is evaluated by comparison with the color value of a reference stone in the x,y color space.

Images