Garment tailoring system and method based on machine vision

Abstract

The invention relates to the technical field of computer vision recognition, in particular to a garment cutting system and method based on machine vision, and the system comprises an image collection unit which is used for shooting a fabric image; the illumination unit is used for detecting the illumination intensity of the workbench surface and adjusting the starting number of illumination equipment of the workbench; the planning unit is used for recording pattern feature point positions of all the fabric areas; the reserving unit is used for determining a reserved sewing area of each fabric area according to the shrinkage property and the extensibility; the typesetting unit is used for determining the position of each fabric area on the fabric to generate typesetting information; the cutting unit is used for determining the flatness of the fabric; the quality inspection unit is used for adjusting the illumination angle of the workbench illumination equipment; by means of the device, precise control over illumination is achieved, the situation that the fabric cannot be effectively utilized due to unevenness is reduced, the fabric utilization rate is increased, and meanwhile the accuracy and reliability of the garment tailoring system based on machine vision are further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer vision recognition, and in particular to a clothing cutting system and method based on machine vision. Background Art

[0002] The current characteristics of clothing cutting are to quickly update styles, shorten production cycles, and bring popular clothing to the market at the fastest speed. The traditional manual cutting method is relatively inefficient and prone to human errors, making it difficult to complete the cutting tasks of a large number of clothing with high quality in a short period of time. The combination of machine vision technology and automated cutting equipment can achieve high-speed and high-precision cutting operations, greatly improving the production efficiency of clothing cutting, and meeting the production rhythm requirements of rapid turnover and high frequency of new clothing. In recent years, machine vision technology has made great progress in hardware equipment (such as high-resolution, high-frame-rate industrial cameras, high-precision lenses, stable light source systems, etc.) and software algorithms (such as image processing, feature recognition, target positioning, size measurement, etc.). Industrial cameras can clearly and quickly capture image information of fabrics and cutting areas; advanced image processing algorithms can accurately extract useful features under the interference of complex backgrounds and fabric textures, such as identifying fabric edges, locating cutting patterns, detecting defects, etc.; size measurement algorithms can be accurate to millimeters or even smaller, providing accurate size basis for clothing cutting. The maturity of these technologies makes the application of machine vision in the field of clothing cutting possible and has high reliability and practicality.

[0003] Chinese patent application publication number: CN112541517A discloses a method and system for displaying clothing details, and the invention provides a method and system for displaying clothing details. The method includes obtaining a picture to be detected and a display type, detecting the picture to be detected by a pre-trained type detection network to obtain a picture of clothing to be displayed in detail; inputting the picture of clothing into a pre-trained attribute recognition network, identifying the picture in combination with the display type to output the corresponding clothing attribute value; inputting the picture of clothing into a pre-trained anchor prediction network, generating a clothing anchor graph in combination with the display type, and outputting the corresponding detail graph by cropping the clothing anchor graph; matching the clothing attribute value of the detail graph, obtaining a matching display picture from the detail graph according to the display type, and displaying the display picture while displaying the matching clothing attribute value. By using a machine to identify attributes and cut detail graphs, the efficiency is high, and through image-text matching, clothing is displayed comprehensively and meticulously.

[0004] However, the above method has the following problems: it is impossible to make the captured image clearer by adjusting the light intensity and illumination angle of the lighting equipment used to capture the image, and it is impossible to improve the quality of clothing processing through details such as patterns and fabric flatness. Summary of the invention

[0005] To this end, the present invention provides a clothing cutting system and method based on machine vision, so as to overcome the problems in the prior art that it is impossible to make the captured image clearer by adjusting the light intensity and illumination angle of the lighting equipment used for capturing the image, and it is impossible to improve the quality of clothing processing through details such as patterns and fabric flatness.

[0006] To achieve the above object, on the one hand, the present invention provides a clothing cutting system based on machine vision, comprising:

[0007] An image acquisition unit, which is used to photograph the fabric placed on the work surface before and after adjusting the lighting device and generate an initial fabric image and an adjusted fabric image, and to photograph a reference garment image and a finished garment image;

[0008] A lighting unit connected to the image acquisition unit, for detecting the light intensity of the work surface, and adjusting the number of lighting devices on the work surface according to the shadow area on the initial fabric image and the light intensity of the work surface;

[0009] A planning unit connected to the image acquisition unit, for dividing the reference clothing into a plurality of fabric regions and recording the pattern feature points of each of the fabric regions;

[0010] A reserved unit, which is used to calculate the shrinkage and extensibility of the fabric in combination with the laser displacement sensor and the fabric elasticity database, and determine the reserved stitching area of ​​each fabric area according to the shrinkage and the extensibility;

[0011] A layout unit, which is connected to the planning unit and the reservation unit respectively, and is used to determine the position of each fabric area on the fabric according to the pattern feature points and the reserved stitching area to generate layout information;

[0012] A cutting unit, which is connected to the image acquisition unit and the layout unit respectively, and is used to determine the flatness of the fabric according to the adjusted fabric image, and to cut out each fabric area on the fabric according to the layout information and sew each fabric area to generate a finished garment;

[0013] a quality inspection unit, which is connected to the image acquisition unit, the lighting unit and the cutting unit respectively, and is used to compare the weight of the finished clothes with the weight of the reference clothes to determine the qualified finished clothes, and to compare the finished clothes image of the qualified finished clothes with the reference clothes image to count the number and position of the inconsistent pattern feature points, and to send an adjustment signal according to the number and position of the inconsistent pattern feature points, wherein the adjustment signal includes adjusting the illumination angle of the workbench lighting device;

[0014] Among them, the placement positions of each fabric on the workbench are consistent, the placement positions of each fabric area on the workbench are consistent, the placement positions of the finished clothing and the reference clothing on the workbench are consistent, and the fabric includes several fabric areas.

[0015] Furthermore, the lighting unit adjusts the number of working table lighting devices to be turned on according to the shadow area on the initial fabric image and the light intensity of the working table surface, wherein:

[0016] If the shadow area on the initial fabric image is smaller than the preset shadow area, detecting the light intensity of the work surface;

[0017] If the shadow area on the initial fabric image is greater than or equal to the preset shadow area, increasing the number of lighting devices on the workbench;

[0018] The preset shadow area is positively correlated with the flat area of ​​the reference clothing with its front side facing upward.

[0019] Furthermore, the lighting unit compares the lighting intensity of the work surface with a first preset light intensity after detecting the lighting intensity of the work surface, and determines whether to reduce the number of lighting devices on the work surface according to the comparison result, wherein:

[0020] If the light intensity of the work surface is greater than or equal to the first preset light intensity, it is determined to reduce the number of lighting devices on the work surface;

[0021] Wherein, the first preset light intensity is related to the material of the reference clothing.

[0022] Furthermore, the reserved unit calculates the shrinkage and extensibility of the fabric in combination with the laser displacement sensor and the fabric elasticity database, wherein:

[0023] Establishing the fabric elasticity database;

[0024] Cut two pieces of test fabric of the same size and record the initial length values;

[0025] The laser displacement sensors are respectively arranged on the two test fabrics to respectively detect the shrinkage length value of the test fabric after shrinkage and the extension length value under the preset tension;

[0026] The preset tension is positively correlated with the thickness of the test fabric.

[0027] Furthermore, the planning unit records the pattern feature points of each fabric area, wherein:

[0028] The pattern feature points include the endpoints and bending points of the pattern boundary lines and the dividing lines of different colors in the pattern;

[0029] The pattern feature points of the same fabric area are merged and made consistent.

[0030] Furthermore, the layout unit determines the position of each fabric area on the fabric according to the pattern feature points and the reserved stitching area to generate layout information, wherein:

[0031] Determining the shape and area of ​​the fabric region according to the reserved stitching area;

[0032] Combining the characteristic points of the pattern with the shape and area of ​​the fabric region, layout is performed on the fabric to generate the layout information.

[0033] Further, the cutting unit determines the flatness of the fabric according to the adjusted fabric image, including:

[0034] Reading the adjusted fabric image in grayscale mode to calculate the grayscale value gradient of the fabric,

[0035] The number of pixel points per unit area in the fabric whose grayscale value gradient is greater than the grayscale value gradient threshold is counted and recorded as the number of high grayscale values, where:

[0036] If the number of high gray values ​​is greater than or equal to a first preset number, it is determined that the fabric is uneven;

[0037] If the number of high gray values ​​is less than a first preset number, the fabric is determined to be flat;

[0038] The first preset number is related to the material of the fabric.

[0039] Furthermore, the quality inspection unit compares the weight of the finished clothes with the weight of the reference clothes to determine the qualified finished clothes, including:

[0040] Subtracting the weight of the finished garment from the weight of the reference garment to obtain a finished garment weight difference,

[0041] Compare the absolute value of the finished product weight difference with the preset weight difference,

[0042] According to the comparison result, it is determined whether the finished clothing is qualified.

[0043] If the absolute value of the finished product weight difference is less than the preset weight difference, the finished product clothing is determined to be qualified;

[0044] If the absolute value of the finished product weight difference is greater than or equal to the preset weight difference, the finished product clothing is determined to be unqualified;

[0045] The preset weight difference is related to the material of the reference clothing.

[0046] Furthermore, the quality inspection unit compares the finished clothing image of the qualified finished clothing with the reference clothing image to count the number and position of the inconsistent pattern feature points, and adjusts the illumination angle of the workbench lighting device according to the number and position of the inconsistent pattern feature points, including:

[0047] Divide the qualified finished garments into several fabric areas,

[0048] Counting the number of inconsistent pattern feature points in each fabric area,

[0049] Compare the number of inconsistent pattern feature points in the fabric area with a second preset number,

[0050] The illumination angle of the workbench lighting device is adjusted according to the comparison result, wherein

[0051] If the number of the inconsistent pattern feature points in the fabric area is greater than or equal to the second preset number, sending the adjustment signal;

[0052] The second preset number is positively correlated with the pattern area on the fabric.

[0053] On the other hand, the present invention provides a clothing cutting method based on machine vision, comprising:

[0054] Detecting the light intensity of the work surface, and adjusting the number of lighting devices on the work surface according to the shadow area on the initial fabric image and the light intensity of the work surface;

[0055] Dividing the reference clothing into a plurality of fabric regions, and recording the pattern feature points of each of the fabric regions;

[0056] Calculating the shrinkage and extensibility of the fabric by combining the laser displacement sensor and the fabric elasticity database, and determining the reserved stitching area of ​​each fabric area according to the shrinkage and the extensibility;

[0057] Determine the position of each fabric area on the fabric according to the pattern feature points and the reserved stitching area to generate layout information;

[0058] Determining the flatness of the fabric according to the adjusted fabric image, and cutting out each fabric area on the fabric according to the layout information and sewing each fabric area to generate a finished garment;

[0059] Determining qualified finished clothes according to the weight of the finished clothes and the weight of the reference clothes;

[0060] The finished clothing image of the qualified finished clothing is compared with the reference clothing image to count the number and position of the inconsistent pattern feature points, and the illumination angle of the workbench lighting device is adjusted according to the number and position of the inconsistent pattern feature points.

[0061] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention adjusts the number of lighting devices on the workbench by analyzing the shadow area on the captured image and combining it with the light intensity of the workbench. By adjusting the number of lighting devices on, it can ensure uniform lighting and appropriate brightness on the workbench, reduce visual blind spots caused by shadow occlusion, and more quickly and accurately identify key features such as details, textures, and colors of objects. By analyzing the shadow area of ​​the image and combining it with the light intensity to adjust the number of lighting devices on, precise control of lighting is achieved. The number of devices on is increased only when more light is really needed to eliminate shadows and meet work requirements, thereby avoiding unnecessary waste of lighting, achieving the purpose of energy saving, and effectively improving the accuracy and reliability of the clothing cutting system based on machine vision.

[0062] Furthermore, the present invention determines the width of the reserved seam area of ​​the fabric by combining the shrinkage and extensibility of the fabric. The shrinkage of the fabric will cause the size of the clothing to become smaller after washing. If the corresponding seam area width is not reserved, the clothing may become too tight and uncomfortable to wear. By reserving a seam area of ​​appropriate width according to the shrinkage, the clothing can still maintain a relatively appropriate size even after multiple washes, and will not stick tightly to the body due to shrinkage. The looseness and comfort of wearing can be maintained, thereby extending the comfortable wearing period of the clothing. Reserving a reasonable seam area width helps to keep the shape of the clothing from deformation. For some clothing with specific shape requirements, such as suits, dresses, etc., reserving a seam area in combination with the fabric characteristics can ensure that the overall contour and lines of the clothing meet the original design intention when the fabric shrinks or is subjected to extension force, while reducing problems such as excessive fabric loss and seam damage caused by size changes, making the clothing more durable, and further improving the accuracy and reliability of the clothing cutting system based on machine vision.

[0063] Furthermore, the present invention determines the flatness of the fabric according to the adjustment of the fabric image. By accurately judging the flatness of the fabric, the fabric that does not meet the requirements can be screened out in advance, and the uneven fabric can be avoided from being used to make clothes, ensuring that the cut pieces are accurate in size and regular in shape, and the various parts can be better fitted and aligned during sewing, thereby improving the overall production accuracy of the clothing, reducing quality defects such as clothing pattern distortion and uneven seams caused by the flatness of the fabric itself, and improving the quality and aesthetics of the finished clothing. By using the method of adjusting the fabric image to determine the flatness, the fabric that does not meet the requirements can be excluded or targetedly processed in the early stage, avoiding unnecessary rework, making the production process smoother and more efficient, improving the overall production efficiency, shortening the production cycle of the product, and the fabric with good flatness is easier to carry out accurate cutting and typesetting planning. After the fabric flatness is learned through image analysis, the cutting layout can be reasonably arranged according to the flat area, so that the fabric is more fully utilized, and the waste generated by the ineffective utilization due to the local unevenness of the fabric is reduced. While improving the fabric utilization rate, the accuracy and reliability of the clothing cutting system based on machine vision are further improved.

[0064] Furthermore, the present invention compares the finished clothing image of qualified finished clothing with the reference clothing image to count the number and position of inconsistent pattern feature points, adjusts the illumination angle of the workbench lighting equipment according to the number and position of the inconsistent pattern feature points, accurately counts the inconsistency of the pattern feature points, and can clearly lock in the specific problems existing in the pattern presentation of the finished clothing. Different illumination angles may cause the clothing pattern to visually present different degrees of deformation, color change or shadow obstruction, etc. These visual errors are likely to interfere with the staff's judgment on the consistency of the pattern feature points. By adjusting the illumination angle of the lighting equipment according to the statistical results, the light is irradiated on the clothing at the best angle, and the visual errors caused by poor lighting are minimized, so that the staff can observe and compare the pattern feature points more clearly and accurately, complete the detection work faster, improve the work efficiency of the detection link, avoid wasting time due to repeated confirmation or misjudgment, make the entire production process smoother and more efficient, and improve the stability of each batch of products in terms of pattern features while further improving the accuracy and reliability of the clothing cutting system based on machine vision. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a structural block diagram of a clothing cutting system based on machine vision of the present invention;

[0066] Figure 2 A decision diagram for adjusting the number of working table lighting devices to be turned on according to an embodiment of the present invention;

[0067] Figure 3 A determination diagram for determining the flatness of a fabric according to an embodiment of the present invention;

[0068] Figure 4 The figure is a flow chart of the clothing cutting method based on machine vision of the present invention. DETAILED DESCRIPTION

[0069] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0070] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0071] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0072] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0073] See also Figure 1 As shown, it is a structural block diagram of a clothing cutting system based on machine vision of the present invention. An embodiment of the present invention provides a clothing cutting system based on machine vision, including:

[0074] An image acquisition unit, which is used to photograph the fabric placed on the work surface before and after adjusting the lighting device and generate an initial fabric image and an adjusted fabric image, and to photograph a reference garment image and a finished garment image;

[0075] A lighting unit connected to the image acquisition unit, for detecting the light intensity of the work surface, and adjusting the number of lighting devices on the work surface according to the shadow area on the initial fabric image and the light intensity of the work surface;

[0076] A planning unit, which is connected to the image acquisition unit, and is used to divide the reference clothing into a number of fabric regions and record the pattern feature points of each fabric region;

[0077] A reserved unit, which is used to calculate the shrinkage and extensibility of the fabric in combination with the laser displacement sensor and the fabric elasticity database, and determine the reserved stitching area of ​​each fabric area according to the shrinkage and extensibility;

[0078] A layout unit, which is connected to the planning unit and the reservation unit respectively, is used to determine the position of each fabric area on the fabric according to the pattern feature points and the reserved stitching area to generate layout information;

[0079] A cutting unit, which is connected to the image acquisition unit and the layout unit respectively, is used to determine the flatness of the fabric according to the adjusted fabric image, and to cut out various fabric areas on the fabric according to the layout information and sew the various fabric areas to generate finished clothing;

[0080] a quality inspection unit, which is connected to the image acquisition unit, the lighting unit and the cutting unit respectively, and is used to compare the weight of the finished clothes with the weight of the reference clothes to determine the qualified finished clothes, and to compare the finished clothes image of the qualified finished clothes with the reference clothes image to count the number and position of inconsistent pattern feature points, and to send an adjustment signal according to the number and position of the inconsistent pattern feature points, wherein the adjustment signal includes adjusting the illumination angle of the workbench lighting device;

[0081] Among them, the placement positions of various fabrics on the workbench are consistent, the placement positions of various fabric regions on the workbench are consistent, the placement positions of finished clothes and reference clothes on the workbench are consistent, and the fabrics include several fabric regions.

[0082] It can be understood that when the image acquisition unit captures the reference clothing image and the finished clothing image, the reference clothing and the finished clothing are both laid flat on the workbench with their front sides facing upward.

[0083] It is understandable that, for those skilled in the art, it is obvious that the lighting unit uses an illuminance meter to detect the light intensity of the work surface, and it will not be described in detail here.

[0084] It can be understood that the lighting unit calculates the shadow area on the initial fabric image, and uses the characteristic that the shadow area usually appears as a darker part in the image. By setting a suitable threshold, the image is converted into a binary image, and the pixel values ​​are only 0 and 255. Generally, 0 represents the non-shadow part and 255 represents the shadow part. Then, the number of pixels with a value of 255 is counted, and the shadow area can be calculated by combining the corresponding relationship between the actual physical size of the image and the pixels.

[0085] It can be understood that the layout unit determines the position of each fabric area on the fabric based on the pattern feature points and the reserved stitching area to generate layout information. In order to maintain the consistency of the clothing pattern, the position of the fabric area is determined on the fabric taking into account the area size and shape of the reserved stitching area. At the same time, the positions of different fabric areas are adjusted to make full use of the fabric and reduce waste. The details will not be elaborated here.

[0086] See also Figure 2 As shown, it is a determination diagram for adjusting the number of working table lighting devices to be turned on according to an embodiment of the present invention. The lighting unit adjusts the number of working table lighting devices to be turned on according to the shadow area on the initial fabric image and the light intensity of the working table surface, wherein:

[0087] If the shadow area on the initial fabric image is smaller than the preset shadow area, the light intensity of the work surface is detected;

[0088] If the shadow area on the initial fabric image is greater than or equal to the preset shadow area, the number of lighting devices on the workbench is increased;

[0089] In implementation, the preset shadow area is 0.005 square meters. If the shadow area on the initial fabric image is 0.003 square meters, which is smaller than the preset shadow area, the light intensity of the work surface is detected;

[0090] If the shadow area on the initial fabric image is 0.008 and is larger than the preset shadow area, the number of working table lighting devices turned on is increased.

[0091] The preset shadow area is positively correlated with the flat area of ​​the reference clothing with its front side facing up.

[0092] It can be understood that, the larger the area of ​​the clothing laid with its front side facing upward is, the greater the probability of generating a shadow when it is laid, the larger the area of ​​the shadow generated is, and the larger the preset shadow area is.

[0093] Specifically, the present invention adjusts the number of lighting devices on the workbench by analyzing the shadow area on the captured image and combining it with the light intensity of the workbench. By adjusting the number of lighting devices on, it can ensure that the lighting on the workbench is uniform and the brightness is appropriate, reduce visual blind spots caused by shadow obstruction, and more quickly and accurately identify key features such as details, textures, and colors of objects. By analyzing the shadow area of ​​the image and combining it with the light intensity to adjust the number of lighting devices on, precise control of lighting is achieved. The number of devices on is increased only when more light is really needed to eliminate shadows and meet work requirements, thereby avoiding unnecessary waste of lighting, achieving the purpose of energy saving, and effectively improving the accuracy and reliability of the clothing cutting system based on machine vision.

[0094] Specifically, after the lighting unit detects the light intensity of the work surface, it compares the light intensity of the work surface with the first preset light intensity, and determines whether to reduce the number of work surface lighting devices turned on according to the comparison result, wherein:

[0095] If the light intensity of the work surface is greater than or equal to the first preset light intensity, it is determined to reduce the number of lighting devices on the work surface;

[0096] In implementation, after the illumination intensity of the work surface is detected, the first preset light intensity is 500 l ux. If the illumination intensity of the work surface is 620 l ux, which is greater than the first preset light intensity, it is determined to reduce the number of work surface lighting devices turned on.

[0097] The first preset light intensity is related to the material of the reference clothing.

[0098] It is understandable that the reflection, absorption and transmission characteristics of light vary greatly from material to material. For example, the surface of cotton clothing is relatively rough, and when exposed to light, it will diffusely reflect and absorb part of the light, presenting a softer and more natural visual effect; while the surface of silk material is smooth and has a high glossiness, and the reflection of light is more regular, which is easy to produce highlights and strong reflections; synthetic materials such as polyester fiber may have different light transmittance from natural fibers, which will affect the effect after light penetrates. The preset light intensity is related to the material of the clothing, and the appropriate light intensity can be provided for these different optical characteristics.

[0099] Specifically, the reserved unit combines the laser displacement sensor and the fabric elasticity database to calculate the shrinkage and elongation of the fabric, where

[0100] Establish fabric elasticity database;

[0101] Cut two pieces of test fabric of the same size and record the initial length values;

[0102] Laser displacement sensors are respectively arranged on two test fabrics to detect the shrinkage length value of the test fabrics after shrinkage and the extension length value under the preset tension;

[0103] It is understandable that representative fabric samples should be selected from the batches of fabrics to be tested according to statistical principles. The number of samples should be sufficient to ensure that the characteristics of the entire batch of fabrics can be accurately reflected. It is generally recommended to have no less than 10 samples, and the size of the samples should be convenient for subsequent measurement operations. For example, they can be cut into squares with a side length of about 30 cm or rectangles with a length of 50 cm and a width of 10 cm. At the same time, the cutting edges of the samples should be neat and free of obvious defects to avoid interference with the measurement results. The laser displacement sensor should be calibrated so that its measurement accuracy meets the requirements. According to the measurement scene and the placement of the fabric, the laser displacement sensor should be reasonably installed to ensure that it can stably and accurately measure the displacement changes of each point on the fabric surface. The sensor is usually fixed on a stable bracket, and its position and angle are adjusted so that its laser beam is vertical. The test area of ​​the fabric is directly illuminated, and a suitable distance is maintained between the sensor and the fabric, generally between a few centimeters and tens of centimeters, in order to obtain a clear and accurate measurement signal. The elasticity-related parameters of various common fabrics (such as pure cotton, polyester fiber, wool, silk and other different materials and fabrics with different weaving methods and thicknesses) are collected. These parameters should include but are not limited to basic mechanical properties data such as initial elastic modulus, yield strength, ultimate elongation in different directions (warp and weft), as well as data such as shrinkage range and elongation range under different conditions (such as different washing methods, temperature, humidity and other environmental factors) accumulated through experiments or actual production experience in the past. Each record in the database should clearly mark the detailed information of the fabric, such as material, component ratio, weaving method, thickness, manufacturer, etc., to facilitate subsequent query and comparative analysis.

[0104] It is understandable that according to the common washing or processing methods in the actual use scenarios of fabrics, a suitable simulated shrinkage treatment method can be selected. For example, a standard washing machine washing program can be used (select parameters such as water temperature, washing time, speed and other parameters that are suitable for the fabric material, such as for cotton fabrics, the common water temperature is about 30°C, the gentle washing mode, and the washing time is about 30 minutes), or soaking treatment (the fabric sample is completely immersed in an appropriate amount of clean water, and taken out after soaking for a certain period of time. The soaking water temperature is also set according to the characteristics of the fabric, and the time can be set to 1-2 hours, etc.), and then naturally dried or dried according to the standard drying program (such as drying in a drying box at 60°C for a certain period of time, and the specific time is adjusted according to factors such as fabric thickness). The fabric sample after shrinkage treatment is placed flat on the measuring platform, and the shrinkage length value is measured by a laser displacement sensor.

[0105] It can be understood that when measuring the extensibility of fabric, one end of the fabric sample is fixed on the fixed fixture of a tensile testing device such as a tensile testing machine to ensure that the fixture clamps the fabric without causing damage to the fabric, and the other end is connected to a movable tensile fixture, so that the laser beam of the laser displacement sensor is aimed at the test area of ​​the fabric sample (generally selected in the middle position in the length direction of the fabric, where it can more evenly reflect the overall extension of the fabric), and the measurement parameters of the sensor are set so that it can accurately record the displacement change of the fabric during the stretching process in real time, that is, the extension length value.

[0106] The preset tension is positively correlated with the thickness of the test fabric.

[0107] It is understandable that thicker fabrics usually mean that they have more fiber layers or the fibers are thicker and denser, which enables them to withstand greater tension when subjected to external stretching before they begin to show obvious deformation (such as elongation, yielding, etc.). Thinner fabrics have relatively fewer fibers and a relatively thin structure, and can withstand relatively small tension. Therefore, the preset tension is positively correlated with the thickness of the test fabric.

[0108] Specifically, the present invention determines the width of the reserved stitching area of ​​the fabric by combining the shrinkage and extensibility of the fabric. The shrinkage of the fabric will cause the size of the clothing to become smaller after washing. If the corresponding stitching area width is not reserved, the clothing may become too tight and uncomfortable to wear. The stitching area of ​​appropriate width is reserved according to the shrinkage. Even after multiple washings, the clothing can still maintain a relatively appropriate size and will not stick tightly to the body due to shrinkage. The looseness and comfort of wearing can be maintained, and the comfortable wearing period of the clothing can be extended. Reserving a reasonable stitching area width helps to keep the shape of the clothing from deformation. For some clothing with specific shape requirements, such as suits, dresses, etc., the stitching area is reserved in combination with the fabric characteristics. When the fabric shrinks or is subjected to extension force, the overall contour and lines of the clothing can still meet the original design intention, while reducing the problems of excessive fabric loss and suture damage caused by size changes, making the clothing more durable, and further improving the accuracy and reliability of the clothing cutting system based on machine vision.

[0109] Specifically, the planning unit records the pattern feature points of each fabric area, where:

[0110] The characteristic points of the pattern include the endpoints and bending points of the pattern boundary lines and the dividing lines of different colors in the pattern;

[0111] The pattern feature points of the same fabric area are merged and made consistent.

[0112] It can be understood that fusing the pattern feature points in the same fabric area is equivalent to merging the pattern feature points in the same position and marking different pattern feature points in the unidentified fabric area.

[0113] Specifically, the layout unit determines the position of each fabric area on the fabric according to the pattern feature points and the reserved stitching area to generate layout information, wherein:

[0114] Determine the shape and area of ​​the fabric area based on the reserved stitching area;

[0115] Combining the characteristic points of the pattern with the shape and area of ​​the fabric region, typeset the fabric and generate typeset information.

[0116] It can be understood that when layout is performed on the fabric in combination with the shape and area of ​​the pattern feature points and the fabric area, first the area size and shape of the fabric area are recorded, then the distribution of the pattern feature points on the fabric area is determined, and then the layout direction of the fabric is determined. The area size and shape information of the fabric, the coordinates of the Luigi pattern feature points and other data are imported into the software through professional clothing CAD software or graphic layout software, and then the automatic layout function of the software is used (some software can automatically generate multiple layout schemes according to the set fabric utilization rate, cutting piece interval and other parameters) or the function of manually dragging and adjusting the cutting piece position is used to try layout.

[0117] It is understandable that the specific position of each piece on the fabric that is finally determined must be recorded. If it is in a plane coordinate system (with a corner of the fabric as the origin, establishing the horizontal and vertical coordinate axes), record the coordinate values ​​of each vertex of the piece. For example, the coordinates of the upper left corner vertex of the shirt front piece are (10 cm, 20 cm), and the coordinates of the lower right corner vertex are (40 cm, 80 cm), etc., accurately indicating the placement of the piece in the fabric, facilitating accurate positioning during subsequent cutting operations. For irregularly shaped pieces, in addition to vertex coordinates, you can also record some key curve control point coordinates or information such as angles and distances that describe their relative positional relationships.

[0118] It is understandable that the situation of the pattern feature points in the area covered by each piece should be recorded in detail. For example, the piece contains several main feature points, their relative positions in the piece (such as located in the center of the piece, on one side of the edge, etc.), and the relationship between these feature points and the shape of the piece can be presented in the form of text description combined with annotated pictures (the shape of the piece and the corresponding pattern feature points are clearly marked on the picture), which is convenient for the cutting personnel to understand and pay attention to protecting these important pattern feature points during operation.

[0119] It is understandable that the fabric utilization rate after layout is calculated by the formula (used fabric area ÷ total fabric area × 100%) to get a specific value. For example, if the used fabric area after layout is 8 square meters and the total fabric area is 10 square meters, the fabric utilization rate is 80%. At the same time, the shape and size of the remaining blank area of ​​the fabric, as well as its position in the overall fabric, are clearly recorded to provide a basis for subsequent decisions such as whether the remaining fabric can continue to be used for small parts cutting or waste treatment.

[0120] See also Figure 3 As shown, it is a determination diagram for determining the flatness of a fabric according to an embodiment of the present invention. The cutting unit determines the flatness of the fabric according to the adjusted fabric image, including:

[0121] Read and adjust the fabric image in grayscale mode to calculate the grayscale value gradient of the fabric.

[0122] The number of pixels per unit area in the fabric whose grayscale gradient is greater than the grayscale gradient threshold is counted as the number of high grayscale values, where:

[0123] If the number of high gray values ​​is greater than or equal to a first preset number, it is determined that the fabric is uneven;

[0124] If the number of high gray values ​​is less than the first preset number, the fabric is determined to be flat;

[0125] It can be understood that if the surface of the fabric is flat and smooth, the grayscale value changes relatively slowly and evenly in the image, and the corresponding grayscale value gradient is relatively small; if the fabric is wrinkled or uneven, the grayscale value of the corresponding area in the image will change suddenly, resulting in an increase in the grayscale value gradient. Therefore, the flatness of the fabric can be inferred by analyzing the grayscale value gradients in different areas of the fabric image.

[0126] In implementation, the number of high gray values ​​is 15,000. If the number of high gray values ​​is 31,852 and is greater than the first preset number, it is determined that the fabric is uneven;

[0127] If the number of high gray values ​​is 9856 and is less than the first preset number, the fabric is determined to be flat.

[0128] The first preset quantity is related to the material of the fabric.

[0129] It is understandable that for smooth and flat fabric materials, such as silk, which has a very smooth surface, fine and uniform texture, the grayscale value of pixels on the image changes relatively slowly, and the grayscale value gradient is relatively small overall, so the corresponding threshold may be set relatively low (the gradient threshold is 50-100), and under such a threshold, the number of pixels exceeding the threshold is usually small, accounting for 10%-20% of the total number of pixels; for rough and textured fabric materials, such as denim, coarse linen and other fabrics with rough surfaces, obvious and complex textures, the grayscale value in the image changes more dramatically, and naturally there will be more pixels with a larger grayscale value gradient. In this case, the threshold often needs to be set high (the gradient threshold is 150-250), and the number of pixels exceeding the threshold will account for a relatively high proportion, reaching 30%-60%.

[0130] Specifically, the present invention determines the flatness of the fabric according to the adjustment of the fabric image. By accurately judging the flatness of the fabric, the fabric that does not meet the requirements can be screened out in advance, and the uneven fabric can be avoided from being used to make clothing, ensuring that the size of the cut pieces is accurate and the shape is regular, and the parts can be better aligned during sewing, thereby improving the overall production accuracy of the clothing, reducing the quality defects such as clothing pattern distortion and uneven seams caused by the flatness of the fabric itself, and improving the quality and aesthetics of the finished clothing. The method of adjusting the fabric image to determine the flatness can exclude or carry out targeted treatment of the fabric that does not meet the requirements in the early stage, avoid unnecessary rework, make the production process smoother and more efficient, improve the overall production efficiency, shorten the production cycle of the product, and the fabric with good flatness is easier to carry out accurate cutting and typesetting planning. After the fabric flatness is learned by analyzing the image, the cutting layout can be reasonably arranged according to the flat area, so that the fabric is more fully utilized, and the waste generated by the ineffective utilization due to the local unevenness of the fabric is reduced. While improving the fabric utilization rate, the accuracy and reliability of the clothing cutting system based on machine vision are further improved.

[0131] Specifically, the quality inspection unit compares the weight of the finished clothes with the weight of the reference clothes to determine the qualified finished clothes, including:

[0132] Subtract the weight of the finished garment from the weight of the reference garment to get the finished garment weight difference.

[0133] Compare the absolute value of the finished product weight difference with the preset weight difference.

[0134] The finished garments are judged to be qualified according to the comparison results.

[0135] If the absolute value of the finished product weight difference is less than the preset weight difference, the finished product clothing is judged to be qualified;

[0136] If the absolute value of the finished product weight difference is greater than or equal to the preset weight difference, the finished product clothing is judged to be unqualified;

[0137] In implementation, the preset weight difference is 100 grams. If the absolute value of the finished product weight difference is 86 grams, which is less than the preset weight difference, the finished product clothing is determined to be qualified.

[0138] If the absolute value of the finished product weight difference is 246 grams, which is greater than the preset weight difference, the finished product clothing is judged to be unqualified.

[0139] The preset weight difference is related to the material of the reference garment.

[0140] It is understandable that the fabrics of different clothes have different densities. When the same area of ​​fabric is added, the weight will be different, so the preset weight difference is different.

[0141] Specifically, the quality inspection unit compares the finished clothing image of the qualified finished clothing with the reference clothing image to count the number and position of inconsistent pattern feature points, and adjusts the illumination angle of the workbench lighting device according to the number and position of inconsistent pattern feature points, including:

[0142] Divide qualified finished garments into several fabric areas,

[0143] Count the number of inconsistent pattern feature points in each fabric area,

[0144] The number of inconsistent pattern feature points in the fabric area is compared with a second preset number, and the illumination angle of the workbench lighting device is adjusted according to the comparison result, wherein

[0145] If the number of inconsistent pattern feature points in the fabric area is greater than or equal to a second preset number, an adjustment signal is issued;

[0146] In implementation, the second preset number is 5. If the number of inconsistent pattern feature points in the fabric area is 7 and is greater than the second preset number, an adjustment signal is issued.

[0147] The second preset number is positively correlated with the size of the pattern area on the fabric.

[0148] It is understandable that the larger the pattern area on the fabric, the more pattern feature points are generated, the larger the number of inconsistent pattern feature points detected, and therefore the larger the second preset number.

[0149] Specifically, the present invention compares the finished clothing image of qualified finished clothing with the reference clothing image to count the number and position of inconsistent pattern feature points, adjusts the illumination angle of the workbench lighting equipment according to the number and position of inconsistent pattern feature points, accurately counts the inconsistency of pattern feature points, and can clearly lock in the specific problems existing in the pattern presentation of finished clothing. Different illumination angles may cause the clothing pattern to visually present different degrees of deformation, color change or shadow occlusion, etc. These visual errors are likely to interfere with the staff's judgment on the consistency of pattern feature points. By adjusting the illumination angle of the lighting equipment according to the statistical results, the light is irradiated on the clothing at the best angle, and the visual errors caused by poor lighting are minimized, so that the staff can observe and compare the pattern feature points more clearly and accurately, complete the detection work faster, improve the work efficiency of the detection link, avoid wasting time due to repeated confirmation or misjudgment, make the entire production process smoother and more efficient, and improve the stability of each batch of products in terms of pattern features, while further improving the accuracy and reliability of the clothing cutting system based on machine vision.

[0150] See also Figure 4 As shown, it is a flow chart of a clothing cutting method based on machine vision of the present invention. The present invention provides a clothing cutting method based on machine vision, comprising:

[0151] Step S1 detects the light intensity of the work surface, and adjusts the number of lighting devices on the work surface according to the shadow area on the initial fabric image and the light intensity of the work surface;

[0152] Step S2, dividing the reference clothing into a number of fabric regions, and recording the pattern feature points of each fabric region;

[0153] Step S3, calculating the shrinkage and extensibility of the fabric by combining the laser displacement sensor and the fabric elasticity database, and determining the reserved stitching area of ​​each fabric area according to the shrinkage and extensibility;

[0154] Step S4, determining the position of each fabric area on the fabric according to the pattern feature points and the reserved stitching area to generate layout information;

[0155] Step S5, determining the flatness of the fabric according to the adjusted fabric image, and cutting out various fabric regions on the fabric according to the layout information and sewing the various fabric regions to generate finished clothing;

[0156] Step S6, determining qualified finished clothes according to the weight of the finished clothes and the weight of the reference clothes;

[0157] Step S7, comparing the finished clothing image of the qualified finished clothing with the reference clothing image to count the number and position of inconsistent pattern feature points, and adjusting the illumination angle of the workbench lighting device according to the number and position of inconsistent pattern feature points.

[0158] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0159] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A clothing cutting system based on machine vision, characterized in that: include: An image acquisition unit, which is used to photograph the fabric placed on the work surface before and after adjusting the lighting device and generate an initial fabric image and an adjusted fabric image, and to photograph a reference garment image and a finished garment image; A lighting unit connected to the image acquisition unit, for detecting the light intensity of the work surface, and adjusting the number of lighting devices on the work surface according to the shadow area on the initial fabric image and the light intensity of the work surface; A planning unit connected to the image acquisition unit, for dividing the reference clothing into a plurality of fabric regions and recording the pattern feature points of each of the fabric regions; A reserved unit, which is used to calculate the shrinkage and extensibility of the fabric in combination with the laser displacement sensor and the fabric elasticity database, and determine the reserved stitching area of ​​each fabric area according to the shrinkage and the extensibility; A layout unit, which is connected to the planning unit and the reservation unit respectively, and is used to determine the position of each fabric area on the fabric according to the pattern feature points and the reserved stitching area to generate layout information; A cutting unit, which is connected to the image acquisition unit and the layout unit respectively, and is used to determine the flatness of the fabric according to the adjusted fabric image, and to cut out each fabric area on the fabric according to the layout information and sew each fabric area to generate a finished garment; a quality inspection unit, which is connected to the image acquisition unit, the lighting unit and the cutting unit respectively, and is used to compare the weight of the finished clothes with the weight of the reference clothes to determine the qualified finished clothes, and to compare the finished clothes image of the qualified finished clothes with the reference clothes image to count the number and position of the inconsistent pattern feature points, and to send an adjustment signal according to the number and position of the inconsistent pattern feature points, wherein the adjustment signal includes adjusting the illumination angle of the workbench lighting device; Among them, the placement positions of the fabrics on the workbench are consistent, the placement positions of the fabric areas on the workbench are consistent, the finished clothing and the reference clothing are consistent in placement position on the workbench, and the fabrics include several fabric areas.

2. The machine vision-based clothing cutting system according to claim 1, characterized in that: The lighting unit adjusts the number of working table lighting devices to be turned on according to the shadow area on the initial fabric image and the light intensity of the working table surface, wherein: If the shadow area on the initial fabric image is smaller than the preset shadow area, detecting the light intensity of the work surface; If the shadow area on the initial fabric image is greater than or equal to the preset shadow area, increasing the number of lighting devices on the workbench; The preset shadow area is positively correlated with the flat area of ​​the reference clothing with its front side facing upward.

3. The machine vision-based clothing cutting system according to claim 2, characterized in that: The lighting unit compares the light intensity of the work surface with the first preset light intensity after detecting the light intensity of the work surface, and determines whether to reduce the number of lighting devices on the work surface according to the comparison result, wherein: If the light intensity of the work surface is greater than or equal to the first preset light intensity, it is determined to reduce the number of lighting devices on the work surface; Wherein, the first preset light intensity is related to the material of the reference clothing.

4. The machine vision-based clothing cutting system according to claim 3, characterized in that: The reserved unit calculates the shrinkage and extensibility of the fabric in combination with the laser displacement sensor and the fabric elasticity database, wherein: Establishing the fabric elasticity database; Cut two pieces of test fabric of the same size and record the initial length values; The laser displacement sensors are respectively arranged on the two test fabrics to respectively detect the shrinkage length value of the test fabric after shrinkage and the extension length value under the preset tension; The preset tension is positively correlated with the thickness of the test fabric.

5. The machine vision-based clothing cutting system according to claim 4, characterized in that: The planning unit records the pattern feature points of each fabric area, wherein: The pattern feature points include the endpoints and bending points of the pattern boundary lines and the dividing lines of different colors in the pattern; The pattern feature points of the same fabric area are merged and made consistent.

6. The machine vision-based clothing cutting system according to claim 5, characterized in that: The layout unit determines the position of each fabric area on the fabric according to the pattern feature points and the reserved stitching area to generate layout information, wherein: Determining the shape and area of ​​the fabric region according to the reserved stitching area; Combining the characteristic points of the pattern with the shape and area of ​​the fabric region, layout is performed on the fabric to generate the layout information.

7. The machine vision-based clothing cutting system according to claim 6, characterized in that: The cutting unit determines the flatness of the fabric according to the adjusted fabric image, including: Reading the adjusted fabric image in grayscale mode to calculate the grayscale value gradient of the fabric, The number of pixel points per unit area in the fabric whose grayscale value gradient is greater than the grayscale value gradient threshold is counted and recorded as the number of high grayscale values, where: If the number of high gray values ​​is greater than or equal to a first preset number, it is determined that the fabric is uneven; If the number of high gray values ​​is less than a first preset number, the fabric is determined to be flat; The first preset number is related to the material of the fabric.

8. The machine vision-based clothing cutting system according to claim 7, characterized in that: The quality inspection unit compares the weight of the finished clothes with the weight of the reference clothes to determine the qualified finished clothes, including: Subtracting the weight of the finished garment from the weight of the reference garment to obtain a finished garment weight difference, Compare the absolute value of the finished product weight difference with the preset weight difference, According to the comparison result, it is determined whether the finished clothing is qualified. If the absolute value of the finished product weight difference is less than the preset weight difference, the finished product clothing is determined to be qualified; If the absolute value of the finished product weight difference is greater than or equal to the preset weight difference, the finished product clothing is determined to be unqualified; The preset weight difference is related to the material of the reference clothing.

9. The machine vision-based clothing cutting system according to claim 8, characterized in that: The quality inspection unit compares the finished clothing image of the qualified finished clothing with the reference clothing image to count the number and position of the inconsistent pattern feature points, and adjusts the illumination angle of the workbench lighting device according to the number and position of the inconsistent pattern feature points, including: Divide the qualified finished garments into several fabric areas, Counting the number of inconsistent pattern feature points in each fabric area, Compare the number of inconsistent pattern feature points in the fabric area with a second preset number, The illumination angle of the workbench lighting device is adjusted according to the comparison result, wherein If the number of the inconsistent pattern feature points in the fabric area is greater than or equal to the second preset number, sending the adjustment signal; The second preset number is positively correlated with the pattern area on the fabric.

10. A method for cutting clothing based on machine vision using the clothing cutting system based on machine vision according to any one of claims 1 to 9, characterized in that: include: Detecting the light intensity of the work surface, and adjusting the number of lighting devices on the work surface according to the shadow area on the initial fabric image and the light intensity of the work surface; Dividing the reference clothing into a plurality of fabric regions, and recording the pattern feature points of each of the fabric regions; Calculating the shrinkage and extensibility of the fabric by combining the laser displacement sensor and the fabric elasticity database, and determining the reserved stitching area of ​​each fabric area according to the shrinkage and the extensibility; Determine the position of each fabric area on the fabric according to the pattern feature points and the reserved stitching area to generate layout information; Determining the flatness of the fabric according to the adjusted fabric image, and cutting out each fabric area on the fabric according to the layout information and sewing each fabric area to generate a finished garment; Determining qualified finished clothes according to the weight of the finished clothes and the weight of the reference clothes; The finished clothing image of the qualified finished clothing is compared with the reference clothing image to count the number and position of the inconsistent pattern feature points, and the illumination angle of the workbench lighting device is adjusted according to the number and position of the inconsistent pattern feature points.

Images