Woven label pattern proofreading method and device, medium and product

Abstract

The invention relates to the technical field of proofreading, in particular to a woven label pattern proofreading method and device, a medium and a product, and the method comprises the steps: carrying out the character recognition based on a woven label sample image and a woven label manuscript image, carrying out the text proofreading based on a to-be-compared woven label text and a standard woven label text, and determining a text proofreading result. And performing pattern contour extraction based on the woven label sample image and the woven label manuscript image, performing contour proofreading based on the pattern contour to be compared and the standard pattern contour, and determining a contour proofreading result. And then, color parameter acquisition is carried out based on the woven label sample image and the woven label manuscript image, color proofreading is carried out based on the to-be-compared color parameters and the standard color parameters, and a color proofreading result is determined. And finally, based on a text proofreading result, a contour proofreading result and a color proofreading result, obtaining a woven label pattern proofreading result. The comprehensive woven label pattern proofreading mode can significantly improve the woven label pattern proofreading quality, and the intelligent woven label pattern proofreading method improves the proofreading efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of proofreading, and in particular to a method, device, medium and product for proofreading woven label writing. Background Art

[0002] In the textile industry, woven labels are an important part of clothing, shoes, hats, bags and other products. The text, patterns and graphic designs on them not only affect the aesthetics of the products, but are also directly related to the brand image and market competitiveness. Through woven label writing and proofreading, we can ensure that the content on the woven label is accurate and completely consistent with the design draft or customer requirements, thereby maintaining the stability and consistency of product quality.

[0003] Related technologies usually use manual proofreading of sampled woven label products one by one to ensure that the woven label samples are consistent with the design draft, that is, manual proofreading can timely discover and correct problems such as spelling errors, pattern disproportion, color deviation, etc. However, in mass production, due to the low efficiency and poor accuracy of manual proofreading, it is difficult to adapt to large-scale and high-speed production needs, and it has become a bottleneck restricting production progress.

[0004] Therefore, how to improve the efficiency and accuracy of woven label writing proofreading is a problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0005] The purpose of this application is to provide a woven label writing proofreading method, equipment, medium and product to solve at least one of the above technical problems.

[0006] The above invention objectives of the present application are achieved through the following technical solutions: In the first aspect, the present application provides a woven label writing proofreading method, which adopts the following technical solution: A woven label writing proofreading method, comprising: Acquire a woven label sample image and a woven label manuscript image, perform text recognition based on the woven label sample image and the woven label manuscript image, determine the woven label text to be compared and the standard woven label text; and perform text proofreading based on the woven label text to be compared and the standard woven label text, and determine the text proofreading result; Extracting pattern contours based on the woven label sample image and the woven label manuscript image to determine the contour of the pattern to be compared and the contour of the standard pattern; and performing contour proofreading based on the contour of the pattern to be compared and the contour of the standard pattern to determine the contour proofreading result; Performing color parameter collection based on the woven label sample image and the woven label original image to determine the color parameters to be compared and the standard color parameters; and performing color calibration based on the color parameters to be compared and the standard color parameters to determine the color calibration result; Based on the text proofreading result, the outline proofreading result and the color proofreading result, a woven label writing proofreading result is obtained.

[0007] By adopting the above technical solution, a woven label sample image and a woven label manuscript image are obtained, and text recognition is performed based on the woven label sample image and the woven label manuscript image to determine the woven label text to be compared and the standard woven label text, and text proofreading is performed based on the woven label text to be compared and the standard woven label text to determine the text proofreading result. Then, pattern contour extraction is performed based on the woven label sample image and the woven label manuscript image to determine the pattern contour to be compared and the standard pattern contour, and contour proofreading is performed based on the pattern contour to be compared and the standard pattern contour to determine the contour proofreading result. Furthermore, color parameter collection is performed based on the woven label sample image and the woven label manuscript image to determine the color parameters to be compared and the standard color parameters, and color proofreading is performed based on the color parameters to be compared and the standard color parameters to determine the color proofreading result. Finally, based on the text proofreading result, the contour proofreading result and the color proofreading result, the woven label writing proofreading result is obtained. The proofreading results of woven label sample images and woven label original images from three aspects, namely text proofreading, outline proofreading and color proofreading, are integrated to comprehensively cover various errors and problems that may occur in the process of woven label writing. The comprehensive woven label writing proofreading method can significantly improve the proofreading quality of woven label writing, and the intelligent woven label writing proofreading method improves the proofreading efficiency.

[0008] In a preferred example, the present application can be further configured as follows: performing text proofreading based on the woven label text to be compared and the standard woven label text to determine the text proofreading result includes: Performing an element-by-element comparison based on the woven label text to be compared and the standard woven label text, and determining a text element comparison result; Performing a text font comparison based on the woven label text to be compared and the standard woven label text, and determining a text font comparison result; Performing text typesetting comparison based on the woven label text to be compared and the standard woven label text, and determining a text typesetting comparison result; The text element comparison result, the text font comparison result and the text typesetting comparison result are comprehensively considered to determine the text proofreading result.

[0009] In a preferred example, the present application may be further configured as follows: performing contour calibration based on the contour of the pattern to be compared and the contour of the standard pattern, and determining the contour calibration result, includes: Performing a mask operation based on the standard pattern contour to determine a standard contour mask, and performing a mask operation based on the pattern contour to be compared to determine a contour mask to be compared, wherein the mask is a binary image, and the pixel value within the contour area is 1, and the pixel value outside the contour area is 0; Performing difference calculation based on the standard contour mask and the contour mask to be compared to obtain a contour difference value; A contour difference threshold is obtained, and when the contour difference value is not greater than the contour difference threshold, the contour correction result is determined to be contour consistent; otherwise, the contour correction result is determined to be contour abnormal.

[0010] In a preferred example, the present application may be further configured as follows: performing color calibration based on the color parameters to be compared and the standard color parameters to determine the color calibration result includes: Performing a color mode conversion based on the color parameters to be compared and the standard color parameters to obtain target color parameters to be compared and target color parameters to be compared under the same color mode; Performing color difference calculation based on the target color parameter to be compared and the target color parameter to be compared to determine a color difference value; A color difference threshold is obtained, and when the color difference value is not greater than the color difference threshold, the color calibration result is determined to be color qualified; otherwise, the color calibration result is determined to be color abnormal.

[0011] In a preferred example, the present application can be further configured as follows: Using material testing equipment to extract material features of woven label samples and determine multi-dimensional material features, wherein the multi-dimensional material features include: fiber structure features, woven label texture features, and spectral features; Acquire standard material features, perform material inspection based on the multi-dimensional material features and the standard material features, and determine a material inspection result; Using machine vision technology, perform a process inspection on the woven label sample image to determine a process inspection result; Accordingly, based on the text proofreading result, the outline proofreading result and the color proofreading result, a woven label writing proofreading result is obtained, including: Based on the text proofreading result, the outline proofreading result, the color proofreading result, the material inspection result and the process inspection result, a woven label writing proofreading result is obtained.

[0012] In a preferred example, the present application may be further configured as follows: after obtaining the woven label writing proofreading result based on the text proofreading result, the outline proofreading result and the color proofreading result, the method further includes: Extracting abnormal features based on the woven label writing proofreading result, and generating a woven label writing abnormality report based on the extracted abnormal features; Based on the woven label writing abnormality report, a woven label abnormality analysis is performed to determine production risk points and process optimization information, so as to quickly locate the problematic links in the woven label writing process and make timely optimization adjustments.

[0013] In a second aspect, the present application provides an electronic device, which adopts the following technical solution: at least one processor; Memory; At least one application program, wherein the at least one application program is stored in a memory and configured to be executed by at least one processor, and the at least one application program is configured to: execute the above-mentioned woven label writing proofreading method.

[0014] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute the above-mentioned woven label writing and proofreading method.

[0015] In a fourth aspect, the present application provides a computer program product, which adopts the following technical solution: A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the computer program implements the above-mentioned woven label writing and proofreading method.

[0016] In summary, the present application includes at least one of the following beneficial technical effects: Acquire a woven label sample image and a woven label manuscript image, perform text recognition based on the woven label sample image and the woven label manuscript image, determine the woven label text to be compared and the standard woven label text, perform text proofreading based on the woven label text to be compared and the standard woven label text, and determine the text proofreading result. Then, perform pattern contour extraction based on the woven label sample image and the woven label manuscript image, determine the pattern contour to be compared and the standard pattern contour, perform contour proofreading based on the pattern contour to be compared and the standard pattern contour, and determine the contour proofreading result. Furthermore, perform color parameter acquisition based on the woven label sample image and the woven label manuscript image, determine the color parameters to be compared and the standard color parameters, perform color proofreading based on the color parameters to be compared and the standard color parameters, and determine the color proofreading result. Finally, obtain the woven label writing proofreading result based on the text proofreading result, the contour proofreading result, and the color proofreading result. The proofreading results of woven label sample images and woven label original images from three aspects, namely text proofreading, outline proofreading and color proofreading, are integrated to comprehensively cover various errors and problems that may occur in the process of woven label writing. The comprehensive woven label writing proofreading method can significantly improve the proofreading quality of woven label writing, and the intelligent woven label writing proofreading method improves the proofreading efficiency.

[0017] Based on the element comparison of the woven label text to be compared and the standard woven label text, the text element comparison result is determined. At the same time, based on the woven label text to be compared and the standard woven label text, the text font comparison is performed to determine the text font comparison result. Moreover, based on the text typesetting comparison of the woven label text to be compared and the standard woven label text, the text typesetting comparison result is determined. Finally, the text proofreading result is determined by comprehensively combining the text element comparison results, text font comparison results and text typesetting comparison results. Comprehensive text proofreading from three aspects: text element items, text fonts and text typesetting can more comprehensively discover the differences between the woven label text to be compared and the standard woven label text. The comprehensive proofreading method can not only ensure that the text content of the woven label is correct, but also that the presentation of the text meets the standard, thereby improving the accuracy and completeness of the text proofreading. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of a method for proofreading woven label writing in one embodiment of the present application; Figure 2 It is a structural schematic diagram of a woven label writing and proofreading device according to one embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device according to one embodiment of the present application. DETAILED DESCRIPTION

[0019] The following combination Figures 1 to 3 This application is described in further detail.

[0020] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, a person skilled in the art may make non-creative modifications to the present embodiment as needed, but such modifications are protected by the patent law as long as they are within the scope of the present application.

[0021] In order to make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is a part of the embodiment of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application. It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the data related to the object is involved in the embodiment of the present application, it needs to be obtained through the authorization and consent of the object, the authorization and consent of the relevant departments, and in accordance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiment, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained, and the embodiment also needs to be implemented with the authorization and consent of the object.

[0022] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0023] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0024] The embodiment of the present application provides a method for proofreading woven label writing, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this. Figure 1 As shown, the method includes step S101, step S102, step S103 and step S104, wherein: Step S101: acquiring a woven label sample image and a woven label manuscript image, performing text recognition based on the woven label sample image and the woven label manuscript image, determining a woven label text to be compared and a standard woven label text; and performing text proofreading based on the woven label text to be compared and the standard woven label text, and determining a text proofreading result.

[0025] For the embodiments of the present application, woven labels are important components of clothing, luggage and other products. The accuracy and aesthetics of their text content and patterns directly affect the overall quality and brand image of the woven label products. Therefore, proofreading is strictly carried out in accordance with the original design draft provided by the customer to ensure that every detail on the woven label meets the design requirements of the woven label original draft, thereby improving the product quality of the woven label.

[0026] Specifically, the woven label sample image is a woven label sample taken by a high-definition camera or scanner and other equipment. The woven label sample image is an image with clear image and uniform light. The woven label manuscript image is usually an electronic file used in the production of the woven label, for example, a CAD design drawing or a high-definition picture, wherein the resolution and clarity of the woven label manuscript image meet the accuracy requirements of subsequent multiple operations. In order to reduce the interference of color information on text recognition, the woven label sample image and the woven label manuscript image are preprocessed, that is, the colored woven label sample image and the woven label manuscript image are converted into grayscale images, and the noise in the image is removed by filtering and other methods to improve the image quality of the woven label sample image and the woven label manuscript image. Then, in the preprocessed woven label sample image and the woven label manuscript image, the image segmentation technology is used to locate the area including the text, and the image segmentation technology includes but is not limited to edge detection, texture analysis and other methods. Then, optical character recognition technology is used to extract text information from the located text area, and the woven label text to be compared corresponding to the woven label sample image and the standard woven label text corresponding to the woven label manuscript image are obtained. After that, text proofreading is performed based on the woven label text to be compared and the standard woven label text to determine the text proofreading result. There are many ways to implement text proofreading. In one feasible way, the woven label text to be compared and the standard woven label text are compared element by element to determine the text element comparison result; the woven label text to be compared and the standard woven label text are compared in text fonts to determine the text font comparison result; the woven label text to be compared and the standard woven label text are compared in text typesetting to determine the text typesetting comparison result; the text element comparison result, the text font comparison result and the text typesetting comparison result are comprehensively determined to determine the text proofreading result. Comprehensive text proofreading from three aspects, namely text element items, text fonts and text typesetting, can more comprehensively discover the differences between the woven label text to be compared and the standard woven label text. The comprehensive proofreading method can not only ensure that the text content of the woven label is correct, but also that the presentation of the text is in line with the standard, thereby improving the accuracy and completeness of the text proofreading.

[0027] Step S102: extracting pattern contours based on the woven label sample image and the woven label manuscript image to determine the contour of the pattern to be compared and the contour of the standard pattern; and performing contour calibration based on the contour of the pattern to be compared and the contour of the standard pattern to determine the contour calibration result.

[0028] For the embodiments of the present application, woven label writing is an important part of textile identification and has extremely high requirements for the accuracy of the pattern. Any slight deviation may affect the quality and appearance of the final product. Therefore, by performing contour proofreading on the woven label sample image and the woven label original image, it is ensured that the woven label sample and the original are consistent in pattern contour, thereby reducing product quality problems caused by pattern deviation.

[0029] Specifically, preprocessing is performed based on the woven label sample image and the woven label manuscript image, wherein the preprocessing includes but is not limited to: grayscale, noise suppression, image enhancement, etc., that is, for grayscale, the color image is converted into a grayscale image to simplify the subsequent processing process and reduce the amount of calculation, that is, the conversion into a grayscale image is achieved by methods such as weighted average method, maximum method or minimum method; for noise suppression, filtering technology (for example, Gaussian filtering, median filtering, etc.) is applied to remove noise in the image and improve image quality. Noise suppression is an important step before contour extraction, which helps to reduce the impact of noise on contour extraction results; for image enhancement, the pattern contour information in the image is enhanced by contrast adjustment, sharpening and other methods to make the contour clearer and easier to identify. Then, edge detection is performed based on the preprocessed woven label sample image and the woven label manuscript image, and the edge information in the image is identified, that is, edge detection is performed on the preprocessed image using an edge detection algorithm. Then, based on the edge detection result, the contour extraction algorithm is applied to extract the complete contour of the pattern to be compared and the standard pattern contour, that is, the contour extraction algorithm can construct the complete contour line of the woven label pattern based on the edge information. Of course, in order to improve the accuracy and aesthetics of the contour, the extracted contour of the pattern to be compared and the standard pattern contour are optimized, for example, burrs are removed, contour lines are smoothed, etc., and the optimized contour line is subjected to subsequent contour proofreading operations.

[0030] After that, contour calibration is performed based on the contour of the pattern to be compared and the contour of the standard pattern to determine the contour calibration result. The contour calibration result includes but is not limited to: contour consistency and contour abnormality. Through contour calibration, it can be ensured that the contour of the pattern to be compared is consistent with the standard pattern, reducing quality problems caused by pattern deviation. There are many ways to implement contour calibration. In one feasible method, a mask operation is performed based on the contour of the standard pattern to determine the standard contour mask, and a mask operation is performed based on the contour of the pattern to be compared to determine the contour mask to be compared, wherein the mask is a binary image, and the pixel value within the contour area is 1, and the pixel value outside the contour area is 0; a difference calculation is performed based on the standard contour mask and the contour mask to be compared to obtain a contour difference value; a contour difference threshold is obtained, and when the contour difference value is not greater than the contour difference threshold, the contour calibration result is determined to be contour consistency; otherwise, the contour calibration result is determined to be contour abnormality. In another feasible manner, contour feature extraction is performed based on the contour of the pattern to be compared and the contour of the standard pattern, and contour features are determined respectively, including but not limited to: contour perimeter, contour area, contour centroid, contour direction, etc., and the contour features will be used for subsequent contour matching and comparison; the contour features of the pattern to be compared are matched with the contour features of the standard pattern to determine the similarity between the contour of the pattern to be compared and the contour of the standard pattern; a similarity threshold is obtained, and when the similarity of the contour comparison is higher than the similarity threshold, the contour proofreading result is determined to be contour consistency; otherwise, the contour proofreading result is determined to be contour abnormality.

[0031] Step S103: color parameter collection is performed based on the woven label sample image and the woven label original image to determine the color parameters to be compared and the standard color parameters; and color calibration is performed based on the color parameters to be compared and the standard color parameters to determine the color calibration result.

[0032] For the embodiments of the present application, during the woven label production process, due to the influence of various factors such as materials, processes, and equipment, the color of the woven label sample may deviate from the original. Through color proofreading, the color deviation can be discovered and corrected in time to ensure that the color of the woven label sample remains consistent with the original.

[0033] Therefore, based on the woven label sample image and the woven label manuscript image, color parameters to be compared and standard color parameters are determined, that is, the electronic device sends a color parameter collection instruction to the color measuring instrument, and the color parameters of the woven label product are accurately measured by a professional color measuring instrument, such as a spectrophotometer or a colorimeter. The electronic device and the color measuring instrument are connected wirelessly so that the electronic device can obtain the color parameters to be compared corresponding to the woven label sample image and the standard color parameters corresponding to the woven label manuscript image. The parameter values ​​of the color parameters to be compared and the standard color parameters include but are not limited to: RGB value, LAB value, hue, brightness, saturation, etc. Furthermore, color proofreading is performed based on the color parameters to be compared and the standard color parameters to determine the color proofreading result, wherein color proofreading is performed based on the color parameters to be compared and the standard color parameters to determine the color proofreading result including but not limited to: qualified color and abnormal color. There are many specific implementation methods for color proofreading. In one feasible method, a color mode conversion is performed based on the color parameters to be compared and the standard color parameters to obtain the target color parameters to be compared and the target color parameters to be compared under the same color mode; a color difference calculation is performed based on the target color parameters to be compared and the target color parameters to be compared to determine the color difference value; a color difference threshold is obtained, and when the color difference value is not greater than the color difference threshold, the color proofreading result is determined to be qualified in color; otherwise, the color proofreading result is determined to be abnormal in color.

[0034] Step S104: obtaining the woven label writing proofreading result based on the text proofreading result, the outline proofreading result and the color proofreading result.

[0035] For the embodiment of the present application, the woven label writing proofreading result is obtained based on the text proofreading result, the outline proofreading result and the color proofreading result, that is, the woven label writing proofreading result integrates the proofreading results of the woven label sample image and the woven label original image from the three aspects of text proofreading, outline proofreading and color proofreading, which can comprehensively cover various errors and problems that may occur in the woven label writing process. The comprehensive woven label writing proofreading method can significantly improve the proofreading quality of the woven label writing, and the intelligent woven label writing proofreading method improves the proofreading efficiency.

[0036] It can be seen that in the embodiment of the present application, a woven label sample image and a woven label manuscript image are obtained, and text recognition is performed based on the woven label sample image and the woven label manuscript image to determine the woven label text to be compared and the standard woven label text, and text proofreading is performed based on the woven label text to be compared and the standard woven label text to determine the text proofreading result. Then, pattern contour extraction is performed based on the woven label sample image and the woven label manuscript image to determine the pattern contour to be compared and the standard pattern contour, and contour proofreading is performed based on the pattern contour to be compared and the standard pattern contour to determine the contour proofreading result. Furthermore, color parameter acquisition is performed based on the woven label sample image and the woven label manuscript image to determine the color parameters to be compared and the standard color parameters, and color proofreading is performed based on the color parameters to be compared and the standard color parameters to determine the color proofreading result. Finally, based on the text proofreading result, the contour proofreading result and the color proofreading result, the woven label writing proofreading result is obtained. The proofreading results of woven label sample images and woven label original images from three aspects, namely text proofreading, outline proofreading and color proofreading, are integrated to comprehensively cover various errors and problems that may occur in the process of woven label writing. The comprehensive woven label writing proofreading method can significantly improve the proofreading quality of woven label writing, and the intelligent woven label writing proofreading method improves the proofreading efficiency.

[0037] Furthermore, in order to improve the accuracy and completeness of text proofreading, in an embodiment of the present application, text proofreading is performed based on the woven label text to be compared and the standard woven label text, and the text proofreading result is determined, including: Performing element-by-element comparison based on the woven label text to be compared and the standard woven label text, and determining the text element comparison result; Performing a text font comparison based on the woven label text to be compared and the standard woven label text, and determining a text font comparison result; Performing text typesetting comparison based on the woven label text to be compared and the standard woven label text, and determining the text typesetting comparison result; The text proofreading result is determined by comprehensively comparing the text element results, text font comparison results and text typesetting comparison results.

[0038] For the embodiment of the present application, in the process of woven label production, there may be spelling errors in the text content. In order to ensure that the final text content of the woven label product is consistent with the standard woven label text, an element-by-element comparison is performed based on the woven label text to be compared and the standard woven label text to determine the text element comparison result, that is, the text content of the woven label text to be compared and the standard woven label text is compared word by word to check whether there are typos, missing words, extra words or reversed order, etc., wherein the text element comparison results include: normal element comparison and abnormal element comparison.

[0039] At the same time, a text font comparison is performed based on the woven label text to be compared and the standard woven label text to determine the text font comparison result, wherein the text font comparison result includes: abnormal font comparison and normal font comparison. For text font comparison, font recognition technology is used to identify the fonts in the woven label text to be compared and the standard woven label text, and key features related to the font are extracted, such as the thickness of the strokes, the structure of the font, the spacing, the inclination, etc. of the font. Then, the font features in the woven label text to be compared and the standard woven label text are compared character by character, and by comparing the strokes, structure and other details of each character, it is determined whether the two are consistent in font. When the two are consistent in font, the text font comparison result is determined to be a normal font comparison; otherwise, the text font comparison result is determined to be an abnormal font comparison.

[0040] At the same time, based on the text typesetting comparison of the woven label text to be compared and the standard woven label text, the text typesetting comparison result is determined, that is, the layout features in the woven label text to be compared and the standard woven label text are extracted, and the layout features include but are not limited to: the spacing between characters, the line spacing, the paragraph format, etc., and the layout features in the woven label text to be compared and the standard woven label text are compared one by one. When there is inconsistency in the layout features, the text typesetting comparison result is determined to be an abnormal typesetting comparison; otherwise, the text typesetting comparison result is determined to be a normal typesetting comparison. Finally, the text element comparison result, the text font comparison result and the text typesetting comparison result are comprehensively determined to determine the text proofreading result. Comprehensively performing text proofreading from three aspects: text element items, text fonts and text typesetting can more comprehensively discover the differences between the woven label text to be compared and the standard woven label text. The comprehensive proofreading method can not only ensure that the text content of the woven label is correct, but also that the presentation of the text meets the standard, thereby improving the accuracy and completeness of the text proofreading.

[0041] It can be seen that in the embodiment of the present application, the text element comparison result is determined based on the element comparison item by item of the woven label text to be compared and the standard woven label text. At the same time, the text font comparison is performed based on the woven label text to be compared and the standard woven label text to determine the text font comparison result. Moreover, the text typesetting comparison is performed based on the woven label text to be compared and the standard woven label text to determine the text typesetting comparison result. Finally, the text element comparison result, the text font comparison result and the text typesetting comparison result are comprehensively determined to determine the text proofreading result. Comprehensively performing text proofreading from the three aspects of text element items, text fonts and text typesetting can more comprehensively find the differences between the woven label text to be compared and the standard woven label text. The comprehensive proofreading method can not only ensure that the text content of the woven label is correct, but also that the presentation method of the text meets the standard, thereby improving the accuracy and completeness of the text proofreading.

[0042] Further, in order to improve the accuracy and flexibility of contour proofreading, in an embodiment of the present application, contour proofreading is performed based on the contour of the pattern to be compared and the contour of the standard pattern, and the contour proofreading result is determined, including: Performing a mask operation based on the standard pattern contour to determine the standard contour mask, and performing a mask operation based on the pattern contour to be compared to determine the contour mask to be compared, wherein the mask is a binary image, the pixel value within the contour area is 1, and the pixel value outside the contour area is 0; A difference calculation is performed based on the standard contour mask and the contour mask to be compared to obtain a contour difference value; A contour difference threshold is obtained. When the contour difference value is not greater than the contour difference threshold, the contour correction result is determined to be contour consistent; otherwise, the contour correction result is determined to be contour abnormal.

[0043] For the embodiment of the present application, a mask is a binary image composed of 0 and 1, which is used to control or limit certain operations or access to specific areas. In image processing, a mask can block the image to be processed through a selected image, graphic or object to control the area or process of image processing. During the contour proofreading operation, by constructing a mask to represent the contour area, the boundary of the contour can be clearly defined. The precise method makes the contour difference calculation more accurate, thereby improving the accuracy of the contour proofreading. Of course, the strictness of the contour proofreading can also be flexibly controlled by adjusting the contour difference threshold, thereby improving the flexibility of the contour proofreading.

[0044] Specifically, mask operations are performed based on the standard pattern contour and the contour of the pattern to be compared, respectively, to obtain a standard contour mask corresponding to the standard pattern contour and a contour mask to be compared corresponding to the contour of the pattern to be compared, wherein the mask is a binary image of the same size and shape as the contour, the pixel value in the contour area is 1, and the pixel value outside the contour area is 0. Preferably, the standard contour mask and the contour mask to be compared are optimized, for example, smoothing the edges, removing noise, etc., to improve the accuracy of contour calibration. Further, a difference calculation is performed based on the standard contour mask and the contour mask to be compared to obtain a contour difference value, wherein the contour difference value is used to characterize the degree of difference between the standard pattern contour and the contour of the pattern to be compared. For the difference calculation, the standard contour mask and the contour mask to be compared are traversed pixel by pixel, and for each pair of pixels at corresponding positions (i.e., pixels at the same position in the two mask images), the pixel values ​​of the two are compared. When the pixel values ​​of the two are the same, the pixel values ​​of the two are considered to match; otherwise, the pixel values ​​of the two are considered to not match. During the traversal process, a timer is used to record the number of mismatched pixels, that is, each time a pair of mismatched pixels is found, the value of the counter is increased by 1, and finally, the value of the counter is used as the contour difference value. The electronic device pre-stores a contour difference threshold, which is determined by technicians based on a large number of experiments and debugging. The size of the contour difference threshold can be adjusted by the user according to the actual situation, and the embodiment of the present application is no longer limited. When the contour difference value is not greater than the contour difference threshold, the contour correction result is determined to be contour consistent; otherwise, the contour correction result is determined to be contour abnormal.

[0045] It can be seen that in the embodiment of the present application, a masking operation is performed based on the standard pattern contour to determine the standard contour mask, and a masking operation is performed based on the pattern contour to be compared to determine the contour mask to be compared. Then, a difference calculation is performed based on the standard contour mask and the contour mask to be compared to obtain a contour difference value. When the contour difference value is not greater than the contour difference threshold, the contour proofreading result is determined to be contour consistency; otherwise, the contour proofreading result is determined to be contour abnormality. During the contour proofreading operation, by constructing a mask to represent the contour area, the boundary of the contour can be clearly defined, and the precise method makes the contour difference calculation more accurate, thereby improving the accuracy of the contour proofreading. Of course, the strictness of the contour proofreading can also be flexibly controlled by adjusting the contour difference threshold, thereby improving the flexibility of the contour proofreading.

[0046] Furthermore, in order to ensure that the color of the woven label sample is consistent with the original, and to avoid rework or re-production due to unqualified color in the later stage, in the embodiment of the present application, color calibration is performed based on the color parameters to be compared and the standard color parameters, and the color calibration result is determined, including: Performing color mode conversion based on the color parameters to be compared and the standard color parameters to obtain target color parameters to be compared and target color parameters to be compared under the same color mode; Performing color difference calculation based on the target color parameter to be compared and the target color parameter to be compared to determine the color difference value; A color difference threshold is obtained, and when the color difference value is not greater than the color difference threshold, the color calibration result is determined to be color qualified; otherwise, the color calibration result is determined to be color abnormal.

[0047] For the embodiments of the present application, during the woven label production process, due to the influence of various factors such as materials, processes, and equipment, the color of the woven label sample may deviate from the original. Through color proofreading, the color deviation can be discovered and corrected in time to ensure that the color of the woven label sample is consistent with the original, thereby avoiding rework or re-production due to unqualified color in the later stage, saving time and resources for woven label production, and reducing production costs.

[0048] Specifically, in order to eliminate the differences that may exist in different color spaces or color modes, a color mode conversion is performed based on the color parameters to be compared and the standard color parameters to obtain the target color parameters to be compared and the target color parameters to be compared in the same color mode, wherein the color mode may be RGB (red, green, blue), CMYK (cyan, magenta, yellow, black), HSV (hue, saturation, brightness), etc. After the color mode conversion, it is also necessary to ensure that the dimensions and units of the target color parameters to be compared and the target standard color parameters in the color space are consistent. By converting the color parameters to be compared and the standard color parameters to the same color mode and performing color parameter alignment, the subsequent calculation of color differences is more accurate and reliable. Then, the color difference calculation is performed based on the target color parameters to be compared and the target color parameters to be compared to determine the color difference value, wherein the color difference measurement method may be the Euclidean distance, that is, directly calculating the straight-line distance between two points in the color space. Then, a color difference threshold is obtained. The color difference threshold is pre-stored in the electronic device. The color difference threshold is determined by technicians based on a large number of experiments and debugging. The size of the color difference threshold can be adjusted by the user according to the actual situation. The embodiment of the present application does not limit it. The color difference threshold is used to determine whether the color difference is within the acceptable range. Finally, a size comparison is performed based on the color difference threshold and the color difference value. When the color difference value is not greater than the color difference threshold, the color calibration result is determined to be qualified; otherwise, the color calibration result is determined to be abnormal.

[0049] It can be seen that in the embodiment of the present application, the color mode conversion is performed based on the color parameters to be compared and the standard color parameters to obtain the target color parameters to be compared and the target color parameters to be compared under the same color mode. Then, the color difference calculation is performed based on the target color parameters to be compared and the target color parameters to be compared to determine the color difference value. When the color difference value is not greater than the color difference threshold, the color proofreading result is determined to be color qualified; otherwise, the color proofreading result is determined to be color abnormal. Through color proofreading, color deviations can be discovered and corrected in a timely manner to ensure that the color of the woven label sample is consistent with the original, avoiding the need for rework or re-production due to unqualified color in the later stage, saving time and resources for woven label production, and reducing production costs.

[0050] Furthermore, in order to ensure the overall quality of the woven label products and improve the qualification rate of the woven label products, in the embodiment of the present application, it also includes: Use material testing equipment to extract material features of woven label samples and determine multi-dimensional material features, where the multi-dimensional material features include: fiber structure features, woven label texture features, and spectral features; Obtain standard material features, perform material inspection based on multi-dimensional material features and standard material features, and determine material inspection results; Use machine vision technology to conduct process inspection on woven label sample images and determine the process inspection results; Accordingly, based on the text proofreading results, the outline proofreading results and the color proofreading results, the woven label writing proofreading results are obtained, including: Based on the text proofreading results, outline proofreading results, color proofreading results, material inspection results and process inspection results, the woven label writing proofreading results are obtained.

[0051] For the embodiment of the present application, the material characteristics of the woven label sample are extracted by using the material detection equipment to determine the multi-dimensional material characteristics, which include: fiber structure characteristics, woven label texture characteristics, and spectral characteristics. For the fiber structure characteristics, the fiber structure characteristics mainly characterize the physical form and arrangement of the fibers in the woven label sample, including the thickness, shape, length, and mutual relationship and arrangement density of the fibers; for the woven label texture characteristics, the woven label texture characteristics mainly characterize the visual and tactile characteristics such as the pattern, texture, and roughness of the surface of the woven label sample; for the spectral characteristics, the spectral characteristics mainly characterize the spectral characteristics generated when the woven label sample interacts with light, including spectral data such as absorption, reflection, and transmission, which can reflect the chemical composition, molecular structure, and physical state of the fabric. Then, the standard material characteristics are obtained, which are the material characteristics corresponding to the woven label manuscript obtained from an authoritative organization, a professional website, an official database, or a certified standard sample. Furthermore, material inspection is performed based on the multidimensional material features and the standard material features, that is, the multidimensional material features and the standard material features are compared item by item. When there is a mismatch in the comparison, the material inspection result is determined to be abnormal material; otherwise, the material inspection result is determined to be normal material.

[0052] Furthermore, the machine vision technology is used to perform a process inspection on the woven label sample image, that is, the image processing algorithm is used to identify defects, broken lines, frame skipping and other problems on the woven label, and the edge detection algorithm is used to evaluate the neatness and burrs of the woven label edge. Based on the image recognition results and edge detection results, the process standards corresponding to the woven label products are matched. When a situation that does not meet the process standards is detected, the process inspection result is determined to be a process abnormality; otherwise, the process inspection result is determined to be a normal process. Correspondingly, based on the text proofreading results, the contour proofreading results, the color proofreading results, the material inspection results and the process inspection results, the woven label writing proofreading results are obtained. In the woven label writing proofreading method, by comparing the materials of the woven label sample and the original manuscript, it can be ensured that the materials used in the final woven label product are completely consistent with the design requirements, ensuring the overall quality of the woven label product, and through process comparison, it is helpful to timely discover and correct deviations in the production process, and improve the qualified rate of woven label products.

[0053] It can be seen that in the embodiment of the present application, the material detection equipment is used to extract the material characteristics of the woven label sample, determine the multi-dimensional material characteristics, and perform material inspection based on the multi-dimensional material characteristics and the standard material characteristics to determine the material inspection results. At the same time, the machine vision technology is used to perform process inspection on the woven label sample image to determine the process inspection results. In the method of woven label writing and proofreading, by comparing the materials of the woven label sample and the original manuscript, it can be ensured that the material used in the final woven label product is completely consistent with the design requirements, ensuring the overall quality of the woven label product, and through process comparison, it is helpful to timely discover and correct deviations in the production process, thereby improving the qualified rate of woven label products.

[0054] Furthermore, in order to reduce production risks and improve product quality stability, in the embodiment of the present application, after obtaining the woven label writing proofreading result based on the text proofreading result, the outline proofreading result and the color proofreading result, the following steps are also included: Extract abnormal features based on the proofreading results of woven label writing, and generate woven label writing abnormality report based on the extracted abnormal features; Based on the abnormal report of woven label writing, woven label abnormality analysis is carried out to determine the production risk points and process optimization information, so as to quickly locate the problematic links in the woven label writing process and make timely optimization adjustments.

[0055] For the embodiment of the present application, the proofreading result of the woven label writing integrates the proofreading results of the woven label sample image and the woven label manuscript image from the three aspects of text proofreading, contour proofreading and color proofreading, which can comprehensively cover various errors and problems that may occur in the woven label writing process. Therefore, based on the proofreading result of the woven label writing, abnormal features are extracted, and the specific content of the abnormal features is at least one of the text abnormal features, contour abnormal features and color abnormal features, which is determined by the actual situation of the woven label sample. For the text abnormal features, the relevant situations of spelling errors of text elements, text font mismatches and text typesetting dislocations are recorded in detail; for the contour abnormal features, the contour difference value between the pattern to be compared and the standard pattern is recorded, which is used to characterize the degree of difference between the standard pattern contour and the contour of the pattern to be compared; for the color abnormal features, the color deviation value between the woven label sample and the woven label manuscript is recorded. Furthermore, classification and quantification are performed based on the extracted abnormal features. Classification can help to better understand the nature and source of the abnormality, while quantification is to express the degree of abnormality in numerical form to facilitate subsequent analysis and comparison, and generate a woven label writing abnormality report based on the classified and quantified abnormal features.

[0056] Furthermore, based on the abnormal information in the abnormal report of woven label writing, the production standards and specifications of woven label writing are compared to find out the parts that do not meet the standards or specifications, and the abnormal information that does not meet the standards or specifications is risk assessed to determine the production risks that may be caused. Then, according to the risk assessment results, the production risk points are determined, among which the production risk points include but are not limited to: equipment failure, raw material quality, improper process parameter settings, etc. Then, based on the production risk points, specific process optimization information is proposed, and the process optimization information includes but is not limited to: adjusting process parameters, improving equipment maintenance, optimizing raw material procurement, etc., so as to quickly locate the links with problems in the woven label writing process and make timely optimization adjustments. The extraction of abnormal features and the generation of abnormal reports of woven label writing provide strong support for the precise positioning of production risk points. Through in-depth analysis of abnormal features, it can be clear which links or factors are the main causes of woven label writing quality problems. This precise positioning helps enterprises take targeted measures to reduce production risks and improve product quality stability.

[0057] It can be seen that in the embodiment of the present application, abnormal features are extracted based on the woven label writing proofreading results, and a woven label writing abnormality report is generated based on the extracted abnormal features. Then, the woven label abnormality analysis is performed based on the woven label writing abnormality report to determine the production risk points and process optimization information, so as to quickly locate the problematic links in the woven label writing process and make timely optimization adjustments. Accurate positioning helps enterprises take targeted measures to reduce production risks and improve product quality stability.

[0058] The above embodiment introduces a woven label writing and proofreading method from the perspective of method flow, and the following embodiment introduces a woven label writing and proofreading device from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0059] The present application embodiment provides a woven label writing proofreading device, such as Figure 2 As shown, the woven label writing and proofreading device may specifically include: The text proofreading module 210 is used to obtain a woven label sample image and a woven label manuscript image, perform text recognition based on the woven label sample image and the woven label manuscript image, determine the woven label text to be compared and the standard woven label text; and perform text proofreading based on the woven label text to be compared and the standard woven label text to determine the text proofreading result; The contour proofreading module 220 is used to extract the pattern contour based on the woven label sample image and the woven label manuscript image, determine the contour of the pattern to be compared and the contour of the standard pattern; and perform contour proofreading based on the contour of the pattern to be compared and the contour of the standard pattern to determine the contour proofreading result; The color proofreading module 230 is used to collect color parameters based on the woven label sample image and the woven label original image, determine the color parameters to be compared and the standard color parameters; and perform color proofreading based on the color parameters to be compared and the standard color parameters to determine the color proofreading result; The proofreading result integration module 240 is used to obtain the woven label writing proofreading result based on the text proofreading result, the outline proofreading result and the color proofreading result.

[0060] For the embodiment of the present application, a woven label sample image and a woven label manuscript image are obtained, and text recognition is performed based on the woven label sample image and the woven label manuscript image, and the woven label text to be compared and the standard woven label text are determined, and text proofreading is performed based on the woven label text to be compared and the standard woven label text to determine the text proofreading result. Then, pattern contour extraction is performed based on the woven label sample image and the woven label manuscript image, and the pattern contour to be compared and the standard pattern contour are determined, and contour proofreading is performed based on the pattern contour to be compared and the standard pattern contour to determine the contour proofreading result. Furthermore, color parameter acquisition is performed based on the woven label sample image and the woven label manuscript image, and the color parameters to be compared and the standard color parameters are determined, and color proofreading is performed based on the color parameters to be compared and the standard color parameters to determine the color proofreading result. Finally, based on the text proofreading result, the contour proofreading result and the color proofreading result, the woven label writing proofreading result is obtained. The proofreading results of woven label sample images and woven label original images from three aspects, namely text proofreading, outline proofreading and color proofreading, are integrated to comprehensively cover various errors and problems that may occur in the process of woven label writing. The comprehensive woven label writing proofreading method can significantly improve the proofreading quality of woven label writing, and the intelligent woven label writing proofreading method improves the proofreading efficiency.

[0061] In a possible implementation of the embodiment of the present application, when the text proofreading module 210 performs text proofreading based on the woven label text to be compared and the standard woven label text and determines the text proofreading result, it is used to: Performing element-by-element comparison based on the woven label text to be compared and the standard woven label text, and determining the text element comparison result; Performing a text font comparison based on the woven label text to be compared and the standard woven label text, and determining a text font comparison result; Performing text typesetting comparison based on the woven label text to be compared and the standard woven label text, and determining the text typesetting comparison result; The text proofreading result is determined by comprehensively comparing the text element results, text font comparison results and text typesetting comparison results.

[0062] In a possible implementation of the embodiment of the present application, when the contour proofreading module 220 performs contour proofreading based on the contour of the pattern to be compared and the contour of the standard pattern and determines the contour proofreading result, it is used to: Performing a mask operation based on the standard pattern contour to determine the standard contour mask, and performing a mask operation based on the pattern contour to be compared to determine the contour mask to be compared, wherein the mask is a binary image, the pixel value within the contour area is 1, and the pixel value outside the contour area is 0; A difference calculation is performed based on the standard contour mask and the contour mask to be compared to obtain a contour difference value; A contour difference threshold is obtained. When the contour difference value is not greater than the contour difference threshold, the contour correction result is determined to be contour consistent; otherwise, the contour correction result is determined to be contour abnormal.

[0063] In a possible implementation of the embodiment of the present application, when the color proofreading module 230 performs color proofreading based on the color parameters to be compared and the standard color parameters and determines the color proofreading result, it is used to: Performing color mode conversion based on the color parameters to be compared and the standard color parameters to obtain target color parameters to be compared and target color parameters to be compared under the same color mode; Performing color difference calculation based on the target color parameter to be compared and the target color parameter to be compared to determine the color difference value; A color difference threshold is obtained, and when the color difference value is not greater than the color difference threshold, the color calibration result is determined to be color qualified; otherwise, the color calibration result is determined to be color abnormal.

[0064] A possible implementation of the embodiment of the present application is a woven label writing and proofreading device, further comprising: The material process inspection module is used to extract material features of woven label samples using material testing equipment to determine multi-dimensional material features, where the multi-dimensional material features include: fiber structure features, woven label texture features, and spectral features; Obtain standard material features, perform material inspection based on multi-dimensional material features and standard material features, and determine material inspection results; Use machine vision technology to conduct process inspection on woven label sample images and determine the process inspection results; Accordingly, based on the text proofreading results, the outline proofreading results and the color proofreading results, the woven label writing proofreading results are obtained, including: Based on the text proofreading results, outline proofreading results, color proofreading results, material inspection results and process inspection results, the woven label writing proofreading results are obtained.

[0065] A possible implementation of the embodiment of the present application is a woven label writing and proofreading device, further comprising: The abnormality analysis module is used to extract abnormal features based on the woven label writing proofreading results, and generate a woven label writing abnormality report based on the extracted abnormal features; Based on the abnormal report of woven label writing, woven label abnormality analysis is carried out to determine the production risk points and process optimization information, so as to quickly locate the problematic links in the woven label writing process and make timely optimization adjustments.

[0066] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the woven label writing and proofreading device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0067] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0068] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0069] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0070] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0071] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0072] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0073] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0074] The embodiment of the present application provides a computer program product, which includes a computer program, and the computer program is implemented as a method in any of the above embodiments when executed by a processor. Compared with the related art, the embodiment of the present application obtains a woven label sample image and a woven label manuscript image, performs text recognition based on the woven label sample image and the woven label manuscript image, determines the woven label text to be compared and the standard woven label text, and performs text proofreading based on the woven label text to be compared and the standard woven label text, and determines the text proofreading result. Then, pattern contour extraction is performed based on the woven label sample image and the woven label manuscript image, determines the pattern contour to be compared and the standard pattern contour, and performs contour proofreading based on the pattern contour to be compared and the standard pattern contour, and determines the contour proofreading result. Then, color parameter acquisition is performed based on the woven label sample image and the woven label manuscript image, determines the color parameter to be compared and the standard color parameter, and performs color proofreading based on the color parameter to be compared and the standard color parameter, and determines the color proofreading result. Finally, the proofreading results of woven label writing are obtained based on the text proofreading results, contour proofreading results and color proofreading results. The proofreading results of woven label sample images and woven label original images from the three aspects of text proofreading, contour proofreading and color proofreading are integrated, which can fully cover various errors and problems that may occur in the process of woven label writing. The comprehensive woven label writing proofreading method can significantly improve the proofreading quality of woven label writing, and the intelligent woven label writing proofreading method improves the proofreading efficiency.

[0075] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0076] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for proofreading woven label writing, characterized in that: include: Acquire a woven label sample image and a woven label manuscript image, perform text recognition based on the woven label sample image and the woven label manuscript image, determine the woven label text to be compared and the standard woven label text; and perform text proofreading based on the woven label text to be compared and the standard woven label text, and determine the text proofreading result; Extracting pattern contours based on the woven label sample image and the woven label original image to determine the contour of the pattern to be compared and the contour of the standard pattern; and performing contour calibration based on the contour of the pattern to be compared and the contour of the standard pattern to determine a contour calibration result; Performing color parameter collection based on the woven label sample image and the woven label original image to determine the color parameters to be compared and the standard color parameters; and performing color calibration based on the color parameters to be compared and the standard color parameters to determine the color calibration result; Based on the text proofreading result, the outline proofreading result and the color proofreading result, a woven label writing proofreading result is obtained.

2. The method for proofreading woven label writing according to claim 1, characterized in that: The text proofreading based on the woven label text to be compared and the standard woven label text to determine the text proofreading result includes: Performing an element-by-element comparison based on the woven label text to be compared and the standard woven label text, and determining a text element comparison result; Performing a text font comparison based on the woven label text to be compared and the standard woven label text, and determining a text font comparison result; Performing text typesetting comparison based on the woven label text to be compared and the standard woven label text, and determining a text typesetting comparison result; The text element comparison result, the text font comparison result and the text typesetting comparison result are comprehensively considered to determine the text proofreading result.

3. The method for proofreading woven label writing according to claim 1, characterized in that: The step of performing contour calibration based on the contour of the pattern to be compared and the contour of the standard pattern and determining the contour calibration result comprises: Performing a mask operation based on the standard pattern contour to determine a standard contour mask, and performing a mask operation based on the pattern contour to be compared to determine a contour mask to be compared, wherein the mask is a binary image, and the pixel value within the contour area is 1, and the pixel value outside the contour area is 0; Performing difference calculation based on the standard contour mask and the contour mask to be compared to obtain a contour difference value; A contour difference threshold is obtained, and when the contour difference value is not greater than the contour difference threshold, the contour correction result is determined to be contour consistent; otherwise, the contour correction result is determined to be contour abnormal.

4. The method for proofreading woven label writing according to claim 1, characterized in that: The color calibration is performed based on the color parameter to be compared and the standard color parameter to determine the color calibration result, including: Performing a color mode conversion based on the color parameters to be compared and the standard color parameters to obtain target color parameters to be compared and target color parameters to be compared under the same color mode; Performing color difference calculation based on the target color parameter to be compared and the target color parameter to be compared to determine a color difference value; A color difference threshold is obtained, and when the color difference value is not greater than the color difference threshold, the color calibration result is determined to be color qualified; otherwise, the color calibration result is determined to be color abnormal.

5. The method for proofreading woven label writing according to claim 1, characterized in that: Also includes: Using material testing equipment to extract material features of woven label samples and determine multi-dimensional material features, wherein the multi-dimensional material features include: fiber structure features, woven label texture features, and spectral features; Acquire standard material features, perform material inspection based on the multi-dimensional material features and the standard material features, and determine a material inspection result; Using machine vision technology, perform a process inspection on the woven label sample image to determine a process inspection result; Accordingly, based on the text proofreading result, the outline proofreading result and the color proofreading result, a woven label writing proofreading result is obtained, including: Based on the text proofreading result, the outline proofreading result, the color proofreading result, the material inspection result and the process inspection result, a woven label writing proofreading result is obtained.

6. The method for proofreading woven label writing according to claim 5, characterized in that: After obtaining the woven label writing proofreading result based on the text proofreading result, the outline proofreading result and the color proofreading result, the method further includes: Extracting abnormal features based on the woven label writing proofreading result, and generating a woven label writing abnormality report based on the extracted abnormal features; Based on the woven label writing abnormality report, a woven label abnormality analysis is performed to determine production risk points and process optimization information, so as to quickly locate the problematic links in the woven label writing process and make timely optimization adjustments.

7. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the woven label writing proofreading method according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the woven label writing and proofreading method according to any one of claims 1 to 6.

9. A computer program product, characterized in that The invention comprises a computer program, wherein the computer program is executed by a processor to implement the woven label writing and proofreading method according to any one of claims 1 to 6.

Images