Chip acquisition method and chip positioning method

Abstract

The embodiment of the present invention provides a chip acquisition method and a chip positioning method, wherein the method for acquiring the detection standard includes: acquiring an image to be detected, wherein there is a chip coding image in the image to be detected, and the chip coding image is used to mark the semiconductor chip; acquiring the chip position information of the reference image with the highest matching degree with the image to be detected in the database, and the chip position information is used to mark the position of the semiconductor chip in the reference image; based on the chip position information, acquiring the position of a detection area in the image to be detected, and the detection area is used to mark the position of the chip coding image; based on the position of the detection area, acquiring an image of the detection area; judging whether there is a chip coding image in the image of the detection area; if there is a chip coding image in the image of the detection area, identifying the chip code corresponding to the chip coding image, and storing the chip code in the database; the embodiment of the present invention aims to automatically realize the code acquisition of the chip on the chip tray.

Description

Technical Field

[0001] The present invention relates to the field of semiconductor detection, and in particular to a chip acquisition method and a chip positioning method. Background Art

[0002] In the semiconductor manufacturing process, the calibration and identification of chips on the chip tray is mainly achieved by obtaining the chip code, which needs to be captured by an expensive laser camera. The laser camera has a small image capture range and can only capture the code on one chip in a single acquisition.

[0003] At present, the codes of chips on chip trays are mainly collected by manually controlling laser cameras. However, there are many chips on the chip tray. If the code of only one chip can be collected at a time, it will take a lot of detection time, which is not conducive to the batch production of chips. In addition, manual operation is prone to problems such as missed chip collection, repeated collection, and wrong position and sequence collection. How to automatically realize the collection of codes on chips is an urgent problem to be solved in the semiconductor process. Summary of the invention

[0004] The embodiments of the present invention provide a chip acquisition method and a chip positioning method, which automatically realize the acquisition of the code of the chip on the chip tray, thereby saving the chip detection time and facilitating the batch production of the chip.

[0005] To solve the above technical problems, an embodiment of the present invention provides a chip acquisition method, including: obtaining an image to be detected, wherein there is a chip coding image in the image to be detected, and the chip coding image is used to mark the semiconductor chip; obtaining the chip position information of the reference image with the highest matching degree with the image to be detected in the database, and the chip position information is used to mark the position of the semiconductor chip in the reference image; based on the chip position information, obtaining the position of a detection area in the image to be detected, and the detection area is used to mark the position of the chip coding image; based on the position of the detection area, obtaining an image of the detection area; judging whether there is a chip coding image in the image of the detection area; if there is a chip coding image in the image of the detection area, identifying the chip code corresponding to the chip coding image, and storing the chip code in the database.

[0006] Compared with the related art, the image to be detected includes multiple chips, and the chip position information of the image to be detected is obtained through the chip position information of the reference image with the highest matching degree with the image to be detected in the database, and the position of the detection area in the image to be detected is obtained. That is, the chip position information of multiple chips in the image to be detected is obtained through the chip position information in the reference image in the database, and the acquisition of multiple chip positions in the image to be detected is automatically realized, and then it is judged whether there is a chip code in the image of the detection area according to the image, that is, the recognition of multiple chip codes is realized at the same time. The recognition of multiple chips in the image to be detected is realized simultaneously through automation, which saves the detection time of the chip and helps the batch production of chips.

[0007] In addition, judging whether there is a chip coding image in the image of the detection area includes the following steps: acquiring an image of the detection area, wherein the image of the detection area has a coding mark; generating a relationship graph between the position of the coding mark and the signal strength of the coding mark based on the position of the coding mark and the signal strength of the coding mark; judging whether the coding mark in the image of the detection area is a chip coding image based on the difference in the relationship graph and the signal strength of the coding mark at a preset position.

[0008] In addition, based on the position of the coding marker and the signal strength of the coding marker, a relationship graph between the position of the coding marker and the signal strength of the coding marker is generated, including the following steps: setting a signal vector for analyzing the coding marker in the image of the detection area; obtaining the signal strength of the coding marker on the signal vector; based on the signal vector and the signal strength of the coding marker on the signal vector, obtaining a relationship graph between the position of the coding marker and the signal strength of the coding marker.

[0009] In addition, based on the relationship diagram and the signal strength difference of the coding mark at the preset position, judging whether the coding mark in the image of the detection area is a chip coding image includes the following steps: setting a i Greater than a j , then d i =1, when a i Not greater than a j , then d i = 0, i is used to represent the sequential position index value, j is used to represent the current position index value, a n Used to characterize the signal strength of the coding mark position n, d n A1: In the initial state, let i=1, j=1, and obtain the value of d1 based on a0 and a1; A2: i is incremented by 1, and d is obtained. i A3: Determine the value of d i Is the value of d1 the same as that of d1? i =d1, then execute A4, d i≠d1, execute A5; A4: let j = i, execute A2; A5: determine whether |ij| is greater than t, if |ij|>t, execute A6, if |ij|≤t, execute A2, t is used to represent the tolerance value; A6: let j = i, s increases by 1, d i =1-d i , execute A2; A7: If s<b, execute A2; if s≥b, it is determined that there is a chip encoding image in the detection area, b is used to represent the number of standard amplitude requirements, and s is used to represent the number of statistical amplitudes at the current position.

[0010] In addition, before determining whether there is a chip coding image in the image of the detection area, it also includes: determining whether there is a coding mark in the image of the detection area; if there is a coding mark in the image of the detection area, executing the step of determining whether there is a chip coding image in the image of the detection area; determining whether there is a chip coding image in the image of the detection area specifically includes: determining whether the coding mark is a chip coding image.

[0011] In addition, identifying the chip code corresponding to the chip code image and storing the chip code in the database includes the following steps: binarizing the chip code image to obtain the chip code corresponding to the chip code image; and storing the chip code in the database. Before storing the chip code, the chip code is binarized to improve the storage efficiency of the chip code.

[0012] In addition, the chip coded image is binarized, including the following steps: obtaining an image of the detection area where the chip coded image is located to obtain x, where x is used to characterize the total number of pixels of the image of the detection area where the chip coded image is located; obtaining w and e, where e=w*x, where e is used to characterize the binarization evaluation value, and where w is used to characterize the preset binarization evaluation percentage; obtaining a first cumulative value of the signal strength of the chip coded image from low to high, and when the first cumulative value is not less than e, obtaining k1, where k1 is used to characterize the first position of obtaining the binarization threshold; obtaining a second cumulative value of the signal strength of the chip coded image from high to low, and when the second cumulative value is not less than e, obtaining k2, where k2 is used to characterize the second position of obtaining the binarization threshold; obtaining m, where m=(k1+k2) / 2, where m is used to characterize the binarization processing threshold; correcting the coding identifier with a signal strength greater than m to 1, and correcting the coding identifier with a signal strength less than m to 0.

[0013] In addition, after identifying the chip code corresponding to the chip code image and before storing the chip code in the database, it also includes: performing code detection on the chip code, and if the chip code meets the code detection rules of the code detection, executing the step of storing the chip code in the database.

[0014] In addition, the chip code is detected, including the following steps: determining whether the length of the chip code is a legal length; and determining whether each character of the chip code is a legal character.

[0015] In addition, before identifying the chip code corresponding to the chip code image, the following steps are also included: obtaining an image of the detection area corresponding to the chip code image; amplifying the image of the detection area, the amplification processing is used to amplify the chip code image; and obtaining the amplified chip code image.

[0016] An embodiment of the present invention also provides a chip positioning method to obtain chip position information in the above chip acquisition method, including: obtaining an image to be positioned based on a positioning device; dividing the image to be positioned into regions to obtain multiple sub-positioning images, each of which contains a chip; obtaining the position of the chip in each sub-positioning image; and obtaining the chip position information of the image to be positioned based on the position of the chip in each sub-positioning image and the position of the sub-positioning image in the image to be positioned.

[0017] Compared with the related art, the image to be positioned is acquired through a positioning device, and the image to be positioned is divided into regions to obtain the chip position information in the image to be positioned, and then the chip position information of the image to be positioned is stored in a database as the chip position information of the reference image. In the subsequent process of implementing the chip acquisition method, the chip position information of the image to be positioned is mapped to the image to be detected through the matching degree between the image to be detected and the reference image, thereby automatically realizing the encoding acquisition of the chip on the chip tray, thereby saving the chip detection time and facilitating the batch production of chips.

[0018] In addition, the image to be positioned is divided into regions to obtain multiple sub-positioning images, including the following steps: based on the pallet outer frame in the image to be positioned, a pallet region is obtained; and the pallet region is divided into equal regions to obtain multiple sub-positioning images of the same size.

[0019] In addition, dividing the tray area into equal areas includes the following steps: obtaining the number of longitudinal chips and the number of transverse chips in the image to be positioned; dividing the tray area into equal areas longitudinally based on the number of longitudinal chips; and dividing the tray area into equal areas transversely based on the number of transverse chips.

[0020] In addition, after obtaining the location of the chip in each sub-positioning image, it also includes: based on the location of the chip in the sub-positioning image, obtaining a two-dimensional code image of each sub-positioning image, the two-dimensional code image only covers the location of the chip; based on the location of the chip in each sub-positioning image, and the position of the sub-positioning image in the image to be positioned, obtaining the chip location information of the image to be positioned, including: based on the two-dimensional code image, obtaining the chip location information of the image to be positioned, the chip location information includes multiple two-dimensional code images, and the positions of the multiple two-dimensional code images in the image to be positioned.

[0021] In addition, based on the location of the chip in the sub-positioning image, a QR code image of each sub-positioning image is obtained, including: simultaneously adjusting the size and position of the sub-positioning image to obtain an adjusted image; if there is no non-chip coded image in the coverage area of ​​the adjusted image, and the adjusted image covers all chip coded images, the adjusted image is set as a QR code image.

[0022] In addition, the size and position of the sub-positioning images are adjusted simultaneously, including: based on the zoom-in instruction and the zoom-out instruction, the size of multiple sub-positioning images is adjusted simultaneously so that there are no non-chip coded images in the coverage area of ​​the adjusted image; based on the direction control instruction, the position of multiple sub-positioning images is adjusted simultaneously so that the adjusted image covers all chip coded images. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] One or more embodiments are exemplarily described by pictures in the corresponding drawings. Unless otherwise stated, the pictures in the drawings are not limited to scale.

[0024] Figure 1 A schematic diagram of a chip acquisition method according to an embodiment of the present invention;

[0025] Figure 2 A schematic diagram of a process for determining whether a chip encoding image exists according to an embodiment of the present invention;

[0026] Figure 3 A schematic diagram of a signal vector provided by an embodiment of the present invention;

[0027] Figure 4 A diagram showing the relationship between the position of a coding mark and the signal strength of the coding mark provided in one embodiment of the present invention;

[0028] Figure 5 A schematic diagram of a chip acquisition method according to another embodiment of the present invention;

[0029] Figure 6 A schematic flow chart of a chip positioning method provided by another embodiment of the present invention;

[0030] Figure 7A schematic diagram of a process for obtaining a sub-positioning image provided by another embodiment of the present invention;

[0031] Figure 8 A schematic flow chart of a chip positioning method provided by yet another embodiment of the present invention;

[0032] Fig. 9 A schematic diagram of an image to be located provided by yet another embodiment of the present invention;

[0033] Fig.10 A schematic diagram of a sub-positioning image provided by yet another embodiment of the present invention;

[0034] Fig.11 A schematic diagram of a two-dimensional code image provided by yet another embodiment of the present invention. DETAILED DESCRIPTION

[0035] At present, the codes of chips on the chip tray are mainly collected by manually controlling the laser camera. However, there are many chips on the chip tray. If only the code of one chip can be collected at a time, it will take a lot of detection time, which is not conducive to the batch production of chips. In addition, manual operation is prone to problems such as missed chip collection, repeated collection, and collection in the wrong position and sequence.

[0036] To solve the above problems, an embodiment of the present invention provides a chip acquisition method, including: obtaining an image to be detected, wherein there is a chip coding image in the image to be detected, and the chip coding image is used to mark the semiconductor chip; obtaining the chip position information of the reference image with the highest matching degree with the image to be detected in the database, and the chip position information is used to mark the position of the semiconductor chip in the reference image; based on the chip position information, obtaining the position of a detection area in the image to be detected, and the detection area is used to mark the position of the chip coding image; based on the position of the detection area, obtaining an image of the detection area; judging whether there is a chip coding image in the image of the detection area; if there is a chip coding image in the image of the detection area, identifying the chip code corresponding to the chip coding image, and storing the chip code in the database.

[0037] To make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the embodiments of the present invention, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can be implemented. The division of the following embodiments is for the convenience of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with each other and quoted from each other without contradiction.

[0038] Figure 1A schematic diagram of a chip acquisition method provided in an embodiment, Figure 2 A schematic diagram of a flow chart for determining whether a chip encoding image exists provided in this embodiment, Figure 3 A schematic diagram of a signal vector provided in this embodiment, Figure 4 The relationship diagram between the position of the coding mark and the signal strength of the coding mark provided in this embodiment is as follows. The chip acquisition method provided in this embodiment of the present invention is described in detail in conjunction with the accompanying drawings, as follows:

[0039] refer to Figure 1 , a chip acquisition method, comprising the following steps:

[0040] Step 101: Acquire an image to be detected.

[0041] An image to be detected is obtained, wherein a chip code image exists in the image to be detected, and the chip code image is used to mark a semiconductor chip.

[0042] Specifically, the image to be detected is an image of the acquired chip tray, and the image to be detected includes multiple chip code images. The chip code image contains a chip code, and the chip code is used to calibrate and identify the semiconductor chip. In an example, the chip code includes a variety of general coding formats such as Code-128, DataMatrix, QR-Code, etc.

[0043] Step 102, obtaining chip position information of a reference image in a database that has the highest matching degree with the image to be detected.

[0044] The chip position information of the reference image with the highest matching degree with the image to be detected is obtained in the database, and the chip position information is used to mark the position of the semiconductor chip in the reference image.

[0045] Specifically, the database stores chip location information of multiple reference images; first, the matching degree between the image to be detected and the reference image is obtained, and the matching degree is the similarity between the image to be detected and the reference image; based on the matching degree, the chip location information of the reference image with the highest matching degree with the image to be detected is obtained, and the chip location information is used to mark the position of the semiconductor chip in the reference image.

[0046] In one example, the size of the chip tray is not fixed, but the size and direction of the chips placed on the chip tray are fixed. Since the number of chips in the vertical direction and the number of chips in the horizontal direction of the chip tray are not fixed, the chip position and recognition order of the image to be tested need to be identified through the control object with the highest similarity.

[0047] Step 103, obtaining the position of the detection area in the image to be detected, and obtaining an image of the detection area based on the position of the detection area.

[0048] Based on the chip position information, the position of the detection area in the image to be detected is obtained, and the detection area is used to mark the position of the chip coding image; based on the position of the detection area, the image of the detection area is obtained.

[0049] Specifically, based on the chip position information of the control image with the highest similarity, the chip position information is mapped to the image to be detected, the position of the detection area indicated by the chip position information is obtained, and based on the position of the detection area and the image to be detected, the image of the detection area in the image to be detected is obtained.

[0050] Step 104, determining whether there is a chip code image.

[0051] It should be noted that, in other embodiments, before determining whether there is a chip coding image in the image of the detection area, it also includes: determining whether there is a coding mark in the image of the detection area; if there is a coding mark in the image of the detection area, executing the step of determining whether there is a chip coding image in the image of the detection area; determining whether there is a chip coding image in the image of the detection area specifically includes: determining whether the coding mark is a chip coding image. By determining whether there is a coding mark in the detection area, and then determining whether the coding mark is a chip coding image, the amount of data processing for the system to determine the image of the detection area is reduced, thereby speeding up the chip identification process.

[0052] Specifically, determining whether there is a chip code image in the image of the detection area includes the following steps:

[0053] refer to Figure 2 This embodiment is described in detail by taking the detection area image having a coding mark as an example. Specifically, when the detection area image has a coding mark, the following steps are included:

[0054] Step 111, obtaining an image of the detection area.

[0055] An image of the detection area is obtained, wherein the image of the detection area has a coded mark.

[0056] Step 112, setting a signal vector for analyzing the coded identifier and obtaining the signal strength of the coded identifier on the signal vector.

[0057] Specifically, refer to Figure 3 , a signal vector 120 for analyzing the coded mark is set in the image of the detection area, and the signal strength of the coded mark on the signal vector 120 is obtained.

[0058] Step 113, obtaining a relationship diagram between the position of the coding mark and the signal strength of the coding mark.

[0059] Specifically, refer to Figure 4, based on the signal vector and the signal strength of the coding marker on the signal vector, a relationship diagram between the position of the coding marker and the signal strength of the coding marker is generated.

[0060] It should be noted that the relationship diagram between the position of the coding marker and the signal strength of the coding marker in the present embodiment is a bar graph which is only for distance description. In other embodiments, the relationship diagram between the position of the coding marker and the signal strength of the coding marker may be presented in the form of a line graph or a table. Those skilled in the art will appreciate that no matter in what form the relationship diagram between the position of the coding marker and the signal strength of the coding marker is presented, it shall fall within the scope of protection of the present invention.

[0061] Continue to refer Figure 3 , step 114, determining whether the coding mark is a chip coding image.

[0062] Specifically, based on the relationship diagram and the signal strength difference of the coding mark at the preset position, it is determined whether the coding mark in the image of the detection area is a chip coding image.

[0063] Determining whether the coded mark in the image of the detection area is a chip coded image includes the following steps:

[0064] i is used to represent the sequential position index value, j is used to represent the current position index value, a n Used to characterize the signal strength of the coding mark position n, d n Used to characterize the judgment value of the coding mark position n, set when a i Greater than a j , then d i =1, when a i Not greater than a j , then di=0.

[0065] A1: In the initial state, let i=1, j=1, and obtain the value of d1 based on a0 and a1;

[0066] A2: i increases by 1, and d is obtained i The value of

[0067] A3: Judge d i Is the value of d1 the same as that of d1? i =d1, then execute A4, d i ≠d1, execute A5;

[0068] A4: Let j = i, and execute A2;

[0069] A5: Determine whether |ij| is greater than t. If |ij|>t, execute A6. If |ij|≤t, execute A2. t is used to represent the tolerance value.

[0070] A6: Let j = i, s increases by 1, d i=1-d i , execute A2;

[0071] A7: If s<b, execute A2; if s≥b, determine that there is a chip encoding image in the detection area, b is used to represent the number of standard amplitude requirements, and s is used to represent the number of statistical amplitudes at the current position.

[0072] There is a sufficiently large amplitude difference in the signal intensity, that is, a standard amplitude. When there are enough standard amplitudes in the image of the detection area, a chip encoding image exists in the image of the detection area.

[0073] If there is a chip code image in the image of the detection area, execute step 105 to identify the chip code corresponding to the chip code image and store the chip code in the database; if there is no chip code image in the image of the detection area, continue to detect whether there is a chip code image in the image of the next detection area.

[0074] Step 105 , identifying the chip code corresponding to the chip code image, and storing the chip code in a database.

[0075] It should be noted that the size of some chip codes may be extremely small, such as a code size of 4mm*4mm. In this case, the chip code is difficult to identify. In addition, in a gray level image, the average brightness difference between the code and the background is only 8 gray values. In this case, the chip code is difficult to identify.

[0076] In this embodiment, before identifying the chip code corresponding to the chip code image, the following steps are also included: obtaining an image of the detection area corresponding to the chip code image, amplifying the image of the detection area, the amplification processing is used to amplify the chip code image, and obtain the amplified chip code image; in an example, the amplification processing multiple is 1x, 1.5x, 2x, etc. Specifically, the specific magnification ratio is manually set for the system, and the chip code image is identified after amplification processing, thereby improving the recognition rate of the code.

[0077] Compared with the related art, the image to be detected includes multiple chips, and the chip position information of the image to be detected is obtained through the chip position information of the reference image with the highest matching degree with the image to be detected in the database, and the position of the detection area in the image to be detected is obtained. That is, the chip position information of multiple chips in the image to be detected is obtained through the chip position information in the reference image in the database, and the acquisition of multiple chip positions in the image to be detected is automatically realized, and then it is judged whether there is a chip code in the image of the detection area according to the image, that is, the recognition of multiple chip codes is realized at the same time. The recognition of multiple chips in the image to be detected is realized simultaneously through automation, which saves the detection time of the chip and helps the batch production of chips.

[0078] The above-mentioned various steps are divided only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the protection scope of this patent. Adding insignificant modifications to the process or introducing insignificant designs that do not change the core design of the process are all within the protection scope of this patent.

[0079] Another embodiment of the present invention relates to a chip acquisition method. Different from the previous embodiment, in this embodiment, before the chip code is stored, the chip code is binarized, thereby improving the storage efficiency of the chip code.

[0080] Figure 5 This is a flow chart of the chip acquisition method provided in this embodiment. The chip acquisition method provided in this embodiment is described in detail below in conjunction with the accompanying drawings. The parts that are the same or corresponding to the above embodiments will not be described in detail below.

[0081] refer to Figure 5 , a chip acquisition method, comprising the following steps:

[0082] Step 201: Acquire an image to be detected.

[0083] Step 202: Obtain chip location information of a reference image in a database that has the highest matching degree with the image to be detected.

[0084] Step 203, obtaining the position of the detection area in the image to be detected, and obtaining an image of the detection area based on the position of the detection area.

[0085] Step 204, determining whether there is a chip code image.

[0086] If there is a chip code image in the image of the detection area, execute step 205 to binarize the chip code image to obtain the chip code; if there is no chip code image in the image of the detection area, continue to detect whether there is a chip code image in the image of the next detection area.

[0087] Step 205: binarize the chip code image to obtain the chip code.

[0088] The chip code image is binarized to obtain the chip code corresponding to the chip code image. By finding an optimal threshold, the chip code image is converted into a binary image, the non-coded area is effectively removed, and the information of 0 and 1 in the code image is effectively classified, thereby improving the success rate of chip acquisition.

[0089] Specifically, the chip encoding image is binarized, including the following steps:

[0090] An image of the detection area where the chip code image is located is obtained to obtain x, where x is used to characterize the total number of pixels of the image of the detection area where the chip code image is located.

[0091] Obtain w and e, where e=w*x, e is used to represent the binarization evaluation value, and w is used to represent the preset binarization evaluation percentage.

[0092] A first accumulated value of the signal strength of the chip encoding image from low to high is obtained. When the first accumulated value is not less than e, k1 is obtained. k1 is used to represent the first position of obtaining the binarization threshold.

[0093] A second accumulated value of the signal intensity of the chip encoding image from high to low is obtained. When the second accumulated value is not less than e, k2 is obtained, and k2 is used to represent the second position of the binarization threshold.

[0094] Get m, where m=(k1+k2) / 2, and m is used to represent the binarization processing threshold.

[0095] The coding mark with signal strength greater than m is corrected to 1, and the coding mark with signal strength not greater than m is corrected to 0.

[0096] Step 206: Perform code detection on the chip code.

[0097] In this embodiment, after identifying the chip code corresponding to the chip code image and before storing the chip code in the database, it also includes: performing code detection on the chip code, if the chip code meets the code detection rules of the code detection, executing step 207, and storing the chip code in the database.

[0098] Specifically, the chip code is detected, including the following steps: determining whether the length of the chip code is a legal length, and determining whether each character of the chip code is a legal character.

[0099] In one example, when collecting chip codes, the collection may be successful but the code may be misjudged. Therefore, it is necessary to perform code detection on the obtained chip code. If the chip code meets the code detection rules of the database, the chip code is a compliant code. Otherwise, the chip code is a non-compliant code.

[0100] Specifically, the legal length of the encoded string is defined, where the legal length refers to a range, such as [13, 20, 22-25], which means that the range of "13", "20" or "between 22 and 25" are all legal lengths; the bit form is defined, such as English letters, decimal numbers, hexadecimal numbers, etc., such as [BG, Z, hk; 1-3, 7, 9; 0-F, 3-B], which means that ";" is used as the character rule separator, indicating that this rule is only applicable when the encoded string length is 4, the first character legal range is uppercase letters B to G or Z or lowercase English letters h to k, the second character legal range is decimal numbers between 1 and 3 or 7 or 9, the third character legal range is hexadecimal numbers between 0 and 9 or AF, and the fourth character legal range is hexadecimal numbers between 3 and 9 or AB.

[0101] Step 207, store the chip code in a database.

[0102] The above-mentioned various steps are divided only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the protection scope of this patent. Adding insignificant modifications to the process or introducing insignificant designs that do not change the core design of the process are all within the protection scope of this patent.

[0103] Since the above embodiments correspond to this embodiment, this embodiment can be implemented in conjunction with the above embodiments. The relevant technical details mentioned in the above embodiments are still valid in this embodiment, and the technical effects that can be achieved in the above embodiments can also be achieved in this embodiment. In order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the above embodiments.

[0104] Another embodiment of the present invention provides a chip positioning method, including: acquiring an image to be positioned based on a positioning device; dividing the image to be positioned into regions to acquire multiple sub-positioning images, each sub-positioning image having a chip; acquiring the position of the chip in each sub-positioning image; and acquiring chip position information of the image to be positioned based on the position of the chip in each sub-positioning image and the position of the sub-positioning image in the image to be positioned.

[0105] Figure 6 A schematic diagram of the chip positioning method provided in this embodiment, Figure 7 The flowchart of obtaining the sub-positioning image provided in this embodiment is as follows. The chip positioning method provided in this embodiment of the present invention is described in detail in conjunction with the accompanying drawings, as follows:

[0106] refer to Figure 6 , a chip positioning method, comprising the following steps:

[0107] Step 301: Acquire an image to be positioned based on a positioning device.

[0108] Step 302: Acquire multiple sub-positioning images, and acquire the location of the chip in each sub-positioning image.

[0109] The image to be positioned is divided into regions to obtain multiple sub-positioning images, each of which contains a chip, and the position of the chip in each sub-positioning image is obtained.

[0110] refer to Figure 7 , dividing the image to be positioned into regions to obtain multiple sub-positioning images, including the following steps:

[0111] Step 311, obtaining the tray area.

[0112] The tray area is acquired based on the tray outer frame in the image to be positioned.

[0113] In one example, an image of a tray chip acquired by a current camera device is acquired, and a user interface is presented, where the acquired image of the tray chip is rendered as a background.

[0114] The tray pushing area is divided into equal areas, a plurality of sub-positioning images of the same size are obtained, and the tray area is divided into light areas, including the following steps:

[0115] Step 312, obtaining the number of longitudinal chips and the number of transverse chips in the image to be positioned.

[0116] Specifically, the number of longitudinal chips and the number of transverse chips in the image to be positioned are obtained, and the tray area is divided into equal parts longitudinally based on the number of longitudinal chips, and the tray area is divided into equal parts transversely based on the number of transverse chips.

[0117] Step 313, obtaining a sub-positioning image.

[0118] In one example, the tray frame can be selected on the user interface with a mouse; the longitudinal chip number and the transverse chip number (v, c) of the tray are input; the tray frame is cut into v equal segments longitudinally and into c equal segments transversely to obtain v*c sub-positioning images of equal area; the sub-positioning images are numbered from 1 to v*c in sequence according to the rule from upper left to lower right.

[0119] Continue to refer Figure 6 , step 303, obtaining chip position information of the image to be located.

[0120] Based on the location of the chip in each sub-positioning image and the location of the sub-positioning image in the image to be positioned, the chip location information of the image to be positioned is obtained.

[0121] Compared with the related art, the image to be positioned is obtained by a positioning device, and the image to be positioned is divided into regions to obtain the chip position information in the image to be positioned, and then the chip position information of the image to be positioned is stored in a database as the chip position information of the reference image. In the subsequent process of implementing the chip acquisition method, the chip position information of the image to be positioned is mapped to the image to be detected through the matching degree between the image to be detected and the reference image, thereby automatically realizing the encoding acquisition of the chip on the chip tray, thereby saving the chip detection time and facilitating the batch production of chips.

[0122] The above-mentioned various steps are divided only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the protection scope of this patent. Adding insignificant modifications to the process or introducing insignificant designs that do not change the core design of the process are all within the protection scope of this patent.

[0123] Yet another embodiment of the present invention provides a chip positioning method. Different from the previous embodiment, in the present embodiment, in the process of obtaining the chip position information of the image to be positioned by the sub-positioning image, the QR code image of the sub-positioning image is first obtained by the sub-positioning image, and then the chip position information of the image to be positioned is obtained by the QR code image, which greatly narrows the image analysis range, effectively improves the processing speed and eliminates the interference of background factors, effectively improves the accuracy to reduce the data processing amount for obtaining the chip position information.

[0124] Figure 8 A schematic diagram of the process flow of the chip positioning method provided in this embodiment, Fig. 9 A schematic diagram of an image to be located provided in this embodiment, Fig.10 A schematic diagram of a sub-positioning image provided in this embodiment, Fig.11 This is a schematic diagram of a two-dimensional code image provided in this embodiment. The chip positioning method provided in this embodiment is described in detail below in conjunction with the accompanying drawings. The parts that are the same or corresponding to the above embodiments will not be described in detail below.

[0125] refer to Figure 8 , a chip positioning method, comprising the following steps:

[0126] Step 401: Acquire an image to be positioned based on a positioning device.

[0127] based on Fig. 9 The image to be positioned 501 in the image to be positioned obtains the sub-positioning image 502 (reference Fig.10 ).

[0128] Continue to refer Figure 8, step 402, obtaining a plurality of sub-positioning images, and obtaining the location of the chip in each sub-positioning image.

[0129] Step 403: Obtain the two-dimensional code image of each sub-positioning image.

[0130] based on Fig.10 The sub-positioning image 502 in the image obtains the two-dimensional code image 503 (reference Fig.11 ).

[0131] Specifically, based on the location of the chip in the sub-positioning image, a two-dimensional code image of each sub-positioning image is obtained, and the two-dimensional code image only covers the location of the chip.

[0132] Specifically, the sub-positioning image is resized and positioned simultaneously to obtain an adjusted image. If there is no non-chip code image in the coverage area of ​​the adjusted image, and the adjusted image covers all chip code images, the adjusted image is set as a QR code image.

[0133] More specifically, based on the zoom-in instruction and the zoom-out instruction, the sizes of multiple sub-positioning images are adjusted simultaneously so that there are no non-chip coded images in the coverage area of ​​the adjusted image; based on the direction control instruction, the positions of multiple sub-positioning images are adjusted simultaneously so that the adjusted image covers all chip coded images.

[0134] Step 404: based on the two-dimensional code image, obtain the chip location information of the image to be located.

[0135] Based on the location of the chip in each character positioning image and the location of the sub-positioning image in the image to be positioned, the chip location information of the image to be positioned is obtained, including: based on the two-dimensional code image, the chip location information of the image to be positioned is obtained, and the chip location information includes multiple two-dimensional code images and the locations of the multiple two-dimensional code images in the image to be positioned.

[0136] In one example, the area of ​​the sub-positioning image is modified into a square, and the side length of the square is the minimum value of the side length of the sub-positioning image. At this time, the square area is the adjustment image, and the adjustment image is controlled by the "+" or "-" key on the keyboard to make all the adjustment images increase or decrease at the same time. The QR code area is controlled by the arrow keys of the keyboard to make all the QR code areas move at the same time until the adjustment image covers all chip codes.

[0137] The above-mentioned various steps are divided only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the protection scope of this patent. Adding insignificant modifications to the process or introducing insignificant designs that do not change the core design of the process are all within the protection scope of this patent.

[0138] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present invention, and that in actual applications, various changes may be made in form and detail without departing from the spirit and scope of the present invention.

Claims

1. A chip acquisition method, characterized in that: include: Acquire an image to be detected, wherein the image to be detected contains a chip code image, and the chip code image is used to mark a semiconductor chip; Obtain chip position information of a reference image in a database that has the highest matching degree with the image to be detected, wherein the chip position information is used to indicate the position of the semiconductor chip in the reference image; Based on the chip position information, obtaining the position of a detection area in the image to be detected, wherein the detection area is used to mark the position of the chip code image; Based on the position of the detection area, acquiring an image of the detection area; Determining whether the chip code image exists in the image of the detection area; If the chip code image exists in the image of the detection area, the chip code corresponding to the chip code image is identified, and the chip code is stored in the database.

2. The chip acquisition method according to claim 1, characterized in that: The determining whether the chip code image exists in the image of the detection area comprises the following steps: Acquire an image of the detection area, wherein the image of the detection area has a coding mark; Based on the position of the coding mark and the signal strength of the coding mark, generating a relationship diagram between the position of the coding mark and the signal strength of the coding mark; Based on the relationship diagram and the difference in signal strength of the coding mark at the preset position, it is determined whether the coding mark in the image of the detection area is the chip coding image.

3. The chip acquisition method according to claim 2, characterized in that: The step of generating a relationship diagram between the position of the coding identifier and the signal strength of the coding identifier based on the position of the coding identifier and the signal strength of the coding identifier comprises the following steps: Setting a signal vector for analyzing the coded identifier in the image of the detection area; Obtaining the signal strength of the coding mark on the signal vector; Based on the signal vector and the signal strength of the coding marker on the signal vector, a relationship diagram between the position of the coding marker and the signal strength of the coding marker is obtained.

4. The chip acquisition method according to claim 2, characterized in that: The step of judging whether the coding mark in the image of the detection area is the chip coding image based on the relationship diagram and the signal strength difference of the coding mark at the preset position comprises the following steps: When ai is greater than aj, di=1, and when ai is not greater than aj, di=0, i is used to represent the sequential position index value, j is used to represent the current position index value, an is used to represent the signal strength of the coding mark position n, and dn is used to represent the judgment value of the coding mark position n; A1: In the initial state, let i=1, j=1, and obtain the value of b1 based on a0 and a1; A2: i increases by 1 to obtain the value of di; A3: Determine whether the values ​​of di and dj are the same. If di=dj, execute A4; if di≠dj, execute A5; A4: Let j = i, and execute A2; A5: Determine whether |ai-aj| is greater than t. If |ai-aj|>t, execute A6. If |ai-aj|≤t, execute A2. t is used to represent the tolerance value. A6: Let j=i, s increment by 1, di=1-di, and execute A2, where b is used to represent the required number of standard amplitudes, and s is used to represent the current statistical amplitude number; Repeat A1 to A6 until all code identification positions n are determined. If the current statistical amplitude times of the detection area are not less than the standard amplitude requirement times, it is determined that there is a chip code image in the detection area.

5. The chip acquisition method according to claim 1, characterized in that: include: Before determining whether the chip coding image exists in the image of the detection area, the method further includes: determining whether a coding mark exists in the image of the detection area; If the coded mark exists in the image of the detection area, executing the step of determining whether the chip coded image exists in the image of the detection area; The determining whether the chip code image exists in the image of the detection area specifically includes: determining whether the code mark is the chip code image.

6. The chip acquisition method according to claim 2, characterized in that: The step of identifying the chip code corresponding to the chip code image and storing the chip code in the database comprises the following steps: Binarizing the chip code image to obtain a chip code corresponding to the chip code image; The chip code is stored in the database.

7. The chip acquisition method according to claim 6, characterized in that: The binarization process of the chip code image comprises the following steps: Acquire an image of the detection area where the chip code image is located to obtain x, where x is used to represent the total number of pixels of the image of the detection area where the chip code image is located; Obtain w and e, where e=w*x, e is used to represent the binarization evaluation value, and w is used to represent the preset binarization evaluation percentage; Obtain a first accumulated value of the signal strength of the chip encoding image from low to high, and when the first accumulated value is not less than e, obtain k1, where k1 is used to represent the first position of obtaining a binarization threshold; Obtain a second accumulated value of the signal strength of the chip encoding image from high to low, and when the second accumulated value is not less than e, obtain k2, where k2 is used to represent a second position of obtaining a binarization threshold; Get m, where m=(k1+k2) / 2, and m is used to represent the binarization processing threshold; The coding identifier whose signal strength is greater than m is corrected to 1, and the coding identifier whose signal strength is not greater than m is corrected to 0.

8. The chip acquisition method according to claim 1, characterized in that: After identifying the chip code corresponding to the chip code image and before storing the chip code in a database, the method further includes: performing code detection on the chip code, and if the chip code meets the code detection rules of the code detection, executing the step of storing the chip code in the database.

9. The chip acquisition method according to claim 8, characterized in that: The step of performing coding detection on the chip coding comprises the following steps: Determine whether the length of the chip code is a legal length; Determine whether each character in the chip code is a legal character.

10. The chip acquisition method according to claim 1, characterized in that: Before identifying the chip code corresponding to the chip code image, the following steps are also included: Acquire an image of the detection area corresponding to the chip code image; Performing a magnification process on the image of the detection area, wherein the magnification process is used to magnify the chip code image; Obtain the enlarged chip encoding image.

11. A chip positioning method for obtaining the chip position information described in the chip acquisition method according to any one of claims 1 to 10, characterized in that: include: Acquire an image to be positioned based on a positioning device; Dividing the image to be positioned into regions to obtain a plurality of sub-positioning images, each of which has a chip; Obtaining the location of the chip in each of the sub-positioning images; Based on the location of the chip in each of the sub-positioning images and the location of the sub-positioning image in the image to be positioned, the chip location information of the image to be positioned is acquired.

12. The chip positioning method according to claim 11, characterized in that: The step of dividing the image to be positioned into regions to obtain a plurality of sub-positioning images comprises the following steps: Acquire a pallet area based on the pallet outer frame in the image to be positioned; The tray area is divided into equal areas to obtain a plurality of sub-positioning images of the same size.

13. The chip positioning method according to claim 12, characterized in that: The step of dividing the pallet area into equal areas comprises the following steps: Obtaining the number of longitudinal chips and the number of transverse chips in the image to be positioned; Based on the number of the longitudinal chips, the tray area is divided into equal parts longitudinally; Based on the number of chips in the horizontal direction, the tray area is divided into equal parts in the horizontal direction.

14. The chip positioning method according to claim 11, characterized in that: include: After obtaining the location of the chip in each of the sub-positioning images, the method further includes: Based on the location of the chip in the sub-positioning image, obtaining a two-dimensional code image of each sub-positioning image, wherein the two-dimensional code image only covers the location of the chip; The step of acquiring the chip position information of the image to be positioned based on the position of the chip in each of the sub-positioning images and the position of the sub-positioning image in the image to be positioned includes: Based on the two-dimensional code image, the chip position information of the image to be located is acquired, wherein the chip position information includes a plurality of the two-dimensional code images and positions of the plurality of the two-dimensional code images in the image to be located.

15. The chip positioning method according to claim 14, characterized in that: The step of acquiring a two-dimensional code image of each sub-positioning image based on the location of the chip in the sub-positioning image comprises: Simultaneously adjusting the size and position of the sub-positioning image to obtain an adjusted image; If there is no non-chip code image in the coverage area of ​​the adjustment image, and the adjustment image covers all chip code images, the adjustment image is set as the two-dimensional code image.

16. The chip positioning method according to claim 15, characterized in that: The sub-positioning image is resized and positioned simultaneously, including: Based on the zoom-in instruction and the zoom-out instruction, the plurality of sub-positioning images are resized simultaneously so that no non-chip encoding image exists in the coverage area of ​​the adjustment image; Based on the direction control instruction, the positions of the plurality of sub-positioning images are adjusted simultaneously so that the adjustment image covers all the chip code images.

Images