Intelligent cloth inspecting method and system and electronic equipment

Abstract

The invention provides an intelligent cloth inspecting method and system and electronic equipment, and relates to the field of intelligent detection. The method comprises the following steps: scanning a bar code of a to-be-detected fabric roll, and determining the specification of the fabric roll so as to display a defect input template corresponding to the fabric specification on intelligent equipment; acquiring a plurality of image pictures of the partial fabric of the fabric roll spread on the cloth inspecting area in different light and shadow environments; identifying and acquiring fabric defects in the image pictures by adopting a cloth defect detection model to form a fabric defect set, inputting the fabric defect set into a defect recording template, and automatically judging fabric defect deduction scores according to a defect scoring standard; generating a fabric score report according to a fabric evaluation standard, each fabric defect set and all fabric defect deduction scores; and carrying out grade classification on the fabric roll subjected to cloth inspection. The cloth inspecting machine and the intelligent equipment are combined for use, the technical problems that the efficiency of manually recording fabric defects is low and errors exist during cloth inspecting are solved, the score report of the fabric roll can be directly generated, and inventory management is carried out.

Description

Technical Field

[0001] The present invention relates to the field of intelligent detection technology, and in particular to an intelligent cloth inspection method, system and electronic equipment. Background Art

[0002] When the cloth inspection machine is in operation, it provides a hardware environment for cloth inspection, continuously unfolds the fabric in sections, provides sufficient light, assists the operator to visually observe surface defects and color differences, and automatically completes the length recording and roll arrangement work simultaneously; among which, surface defects include black spots, hair, foreign matter, mosquitoes, double wefts, dense lines, sparse lines, broken warps, broken threads, holes and other surface defects. The cooperation between the cloth inspection machine and the operator is used to achieve cloth quality management for manufacturers, and then select high-quality cloth when using cloth for clothing production to improve clothing quality.

[0003] However, the traditional defect detection scheme that relies on operators’ visual inspection is prone to fatigue and has a high rate of missed detection. It not only fails to meet the clothing industry’s increasingly high quality requirements for qualified fabrics, but also the defects are usually recorded manually by operators during the factory’s fabric inspection process, which is inefficient and cannot quickly evaluate and generate fabric inspection reports. In addition, the manual fabric inspection scheme cannot be connected to the factory’s warehousing and business systems in real time, and when production problems occur, it cannot quickly detect and solve abnormalities. Summary of the invention

[0004] The purpose of the present invention is to provide a method, system and electronic equipment for intelligent cloth inspection. By combining a traditional cloth inspection machine with an intelligent device to systematically input fabric defects, a cloth inspection report can be quickly generated, which not only improves the input efficiency, but also saves the time cost of manual re-entry into the system and avoids input errors.

[0005] To achieve the above object, the present invention proposes the following technical solutions:

[0006] In the first aspect, a method for intelligent fabric inspection is proposed, comprising:

[0007] Scan the barcode of the fabric roll to be inspected on the fabric inspection machine to determine the fabric roll specifications so that the defect entry template corresponding to the fabric specifications can be displayed on the smart device;

[0008] Under different light and shadow environments, multiple images of the fabric roll spread on the inspection area are sequentially obtained;

[0009] A cloth defect detection model based on deep learning is used to sequentially identify and obtain fabric defects in each image, and after merging into a fabric defect set of a corresponding part of the fabric, the fabric defects are entered one by one in the corresponding template area of ​​the defect entry template, and the fabric defects are automatically judged and deducted according to the defect scoring standard; wherein the cloth defect detection model based on deep learning adopts the semi-supervised learning Faster R-CNN algorithm;

[0010] Receiving a defect entry completion signal, generating a fabric score report according to fabric evaluation criteria, each fabric defect set, and all fabric defect deduction scores automatically judged according to the defect scoring criteria; wherein the fabric score report lists the total deduction score of the fabric roll, the number of different fabric defects, and the total deduction score corresponding to each category of fabric defects;

[0011] According to the fabric grade evaluation standard and the fabric score report, the fabric rolls that have completed the fabric inspection are graded.

[0012] Furthermore, it also includes:

[0013] According to the specifications of the fabric roll and the size of the fabric inspection area of ​​the fabric inspection machine, a positioning template matching the fabric inspection area is set, and the positioning template includes a plurality of positioning areas;

[0014] For each fabric roll specification, a defect entry template corresponding to the positioning template of the corresponding fabric roll specification is configured on the smart device, and the defect entry template is provided with a plurality of defect positioning areas;

[0015] Establishing positioning coordinates for the image picture, so that the cloth defect detection model based on deep learning can simultaneously locate the first position information of the fabric defect when identifying and acquiring the fabric defect, and determine its second position information on the positioning template on the cloth inspection machine; wherein the first position information is the coordinate information in the positioning coordinates where the fabric defect is located, and the second position information is the positioning area where the fabric defect is located;

[0016] Determine the position deviation of the first position information and the second position information. When the position deviation is within a preset range, select the corresponding defect entry template according to the specifications of the fabric roll, the first position information or the second position information, and enter the fabric defect at the corresponding position of the defect entry template.

[0017] Furthermore, it also includes:

[0018] According to the defect scoring standard, the defect entry template is divided into a plurality of scoring areas, wherein the scoring area includes a plurality of defect location areas;

[0019] According to the deduction score of each fabric defect, corresponding deduction score items are added to each scoring area, and the deduction score items include deduction scores corresponding to different fabric defects; wherein the deduction score items of each defect positioning area in each scoring area are the same.

[0020] Furthermore, it also includes:

[0021] Determine the length of the fabric to be rolled up according to the fabric roll specifications;

[0022] According to the length of the fabric, the defect entry template corresponding to the fabric roll specification is divided into a flip text, any page of the flip text is similar to the size of the fabric inspection area, and each page of the flip text corresponds to each fabric segment photographed by the fabric roll;

[0023] When the fabric in the fabric inspection area of ​​the fabric inspection machine is inspected, the fabric on the fabric roll is released in sequence to re-cover the fabric inspection area, and the corresponding defect entry template automatically switches to the next page after completing the defect entry of the current page.

[0024] Furthermore, it also includes:

[0025] When the fabric inspection machine is working, it is determined in real time whether the fabric roll currently being inspected is a qualified fabric roll, and when the fabric roll is a qualified fabric roll, the fabric roll is graded according to the fabric grade evaluation standard and the fabric score report;

[0026] The process of determining in real time whether the fabric roll currently being inspected is a qualified fabric roll includes:

[0027] Calculate in real time the fabric score of the fabric roll currently inspected by the fabric inspection machine, and when the fabric score of the inspected fabric roll in each preset inspection cycle is lower than the corresponding score threshold, the fabric roll is unqualified;

[0028] The type, quantity and corresponding area of ​​fabric defects are calculated and input in real time. When the number of target fabric defects exceeds the preset target or the area exceeds the preset ratio, the fabric roll is unqualified.

[0029] In the second aspect, a smart cloth inspection system is proposed, comprising:

[0030] The scanning and determination module is used to scan the barcode of the fabric roll to be inspected on the fabric inspection machine to determine the fabric roll specifications so as to display the defect entry template corresponding to the fabric specifications on the smart device;

[0031] The recognition and acquisition module is used to sequentially acquire multiple images of the part of the fabric rolled on the inspection area under different light and shadow environments;

[0032] An input evaluation module is used to use a cloth defect detection model based on deep learning to sequentially identify fabric defects in each image picture, merge them into a fabric defect set of a corresponding part of the fabric, and then enter the fabric defects one by one in the corresponding template area of ​​the defect input template, and automatically judge the fabric defects and deduct scores according to the defect scoring standard; wherein the cloth defect detection model based on deep learning adopts the Faster R-CNN algorithm of semi-supervised learning;

[0033] A receiving and generating module is used to receive a defect entry end signal, and generate a fabric score report according to the fabric evaluation standard, each fabric defect set, and all fabric defect deduction scores automatically judged according to the defect scoring standard; wherein the fabric score report lists the total deduction score of the fabric roll, the number of different fabric defects, and the total deduction score corresponding to each classification of fabric defects;

[0034] The classification module is used to classify the fabric rolls that have completed the fabric inspection according to the fabric grade evaluation standard and the fabric score report.

[0035] Furthermore, it also includes:

[0036] A setting module, used to set a positioning template matching the fabric inspection area according to the specifications of the fabric roll and the size of the fabric inspection area of ​​the fabric inspection machine, wherein the positioning template includes a plurality of positioning areas;

[0037] A configuration module, for configuring, for each fabric roll specification, a defect entry template corresponding to the positioning template of the corresponding fabric roll specification on the smart device, wherein the defect entry template sets a plurality of defect positioning areas;

[0038] An acquisition and determination module is used to establish positioning coordinates for the image picture, so that the cloth defect detection model based on deep learning can identify and obtain the first position information of the fabric defect and simultaneously locate the fabric defect, and determine its second position information on the positioning template on the cloth inspection machine; wherein the first position information is the coordinate information in the positioning coordinates where the fabric defect is located, and the second position information is the positioning area where the fabric defect is located;

[0039] A judgment and entry module is used to judge the position deviation of the first position information and the second position information. When the position deviation is within a preset range, according to the specifications of the fabric roll, the first position information or the second position information, the corresponding defect entry template is selected and the fabric defect is entered at the corresponding position of the defect entry template.

[0040] Furthermore, it also includes:

[0041] A division unit, used to divide the defect entry template into a plurality of scoring areas according to a defect scoring standard, wherein the scoring area includes a plurality of defect location areas;

[0042] The adding unit is used to add corresponding deduction items to each scoring area according to the deduction scores of each fabric defect, and the deduction items include deduction scores corresponding to different fabric defects; wherein the deduction items of each defect positioning area in each scoring area are the same.

[0043] Furthermore, it also includes:

[0044] A judgment module, used for judging in real time whether the fabric roll currently being inspected is a qualified fabric roll when the fabric inspection machine is working, and classifying the fabric roll according to the fabric grade evaluation standard and the fabric score report when the fabric roll is a qualified fabric roll;

[0045] The process of determining in real time whether the fabric roll currently being inspected is a qualified fabric roll includes:

[0046] Calculate in real time the fabric score of the fabric roll currently inspected by the fabric inspection machine, and when the fabric score of the inspected fabric roll in each preset inspection cycle is lower than the corresponding score threshold, the fabric roll is unqualified;

[0047] The type, quantity and corresponding area of ​​fabric defects are calculated and input in real time. When the number of target fabric defects exceeds the preset target or the area exceeds the preset ratio, the fabric roll is unqualified.

[0048] In the third aspect, an electronic device is proposed, comprising a computer program, wherein the computer program is stored in a computer-readable storage medium; when a processor of the electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device performs the steps of the above-mentioned intelligent cloth inspection method.

[0049] It can be seen from the above technical solutions that the technical solutions of the present invention have the following beneficial effects:

[0050] The invention discloses a method, system and electronic device for intelligent cloth inspection, and the method includes: scanning the barcode of the fabric roll to be inspected on the cloth inspection machine to determine the fabric roll specifications so as to display the defect entry template corresponding to the fabric specifications on the intelligent device; sequentially obtaining multiple images of the fabric roll spreading on the cloth inspection area under different light and shadow environments; using a cloth defect detection model based on deep learning to sequentially identify and obtain fabric defects in each image, merge them into a fabric defect set of the corresponding part of the fabric, and then enter the fabric defects one by one in the corresponding template area of ​​the defect entry template, and automatically judge the fabric defects according to the defect scoring standard to deduct scores; receiving a defect entry end signal, generating a fabric score report according to the fabric evaluation standard, each fabric defect set and all fabric defect deductions automatically judged according to the defect scoring standard; and classifying the fabric roll after the cloth inspection according to the fabric grade evaluation standard and the fabric score report. The solution combines the cloth inspection machine with the intelligent device to solve the technical problems of low efficiency of manual observation and manual recording of fabric defects and errors in secondary entry during cloth inspection.

[0051] When the present invention electronically enters fabric defects, the positioning template arranged on the fabric inspection machine cooperates with the defect entry template arranged on the intelligent device to realize the rapid positioning and deduction judgment of fabric defects on fabric rolls of different specifications. The deduction items added to each defect positioning area can quickly generate a score report to judge whether the fabric roll currently inspected is qualified and the grade of the fabric roll; at the same time, the present invention can use intelligent devices to compare the quality of multiple fabric rolls, and after storing the corresponding relationship between the fabric inspection data and the barcode, it can be used for inventory management and auxiliary business promotion after the intelligent device is connected to the WMS warehousing system and the factory ERP business system. In addition, by quickly discovering problematic fabric rolls, it is helpful to timely discover generation problems, which helps to improve production efficiency and production quality.

[0052] It should be appreciated that all combinations of the foregoing concepts, as well as additional concepts described in greater detail below, may be considered to be part of the inventive subject matter of the present disclosure, provided such concepts are not mutually inconsistent.

[0053] The foregoing and other aspects, embodiments and features of the present invention can be more fully understood from the following description in conjunction with the accompanying drawings. Other additional aspects of the present invention, such as the features and / or beneficial effects of the exemplary embodiments, will be apparent from the following description or learned from the practice of the specific embodiments according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are not drawn to scale according to actual reference objects. In the accompanying drawings, each identical or nearly identical component shown in various figures may be represented by the same reference numeral. For the sake of clarity, not every component is labeled in each figure. Now, embodiments of various aspects of the present invention will be described by way of example and with reference to the accompanying drawings, in which:

[0055] Figure 1 A flow chart of the intelligent cloth inspection method disclosed in an embodiment of the present invention;

[0056] Figure 2 A flow chart of inputting fabric defects according to a defect input template disclosed in an embodiment of the present invention;

[0057] Figure 3 A flowchart of adding deduction items to a defect entry template disclosed in an embodiment of the present invention;

[0058] Figure 4 This is an example diagram of a configuration defect entry template disclosed in an embodiment of the present invention;

[0059] Figure 5 A flow chart of fabric roll classification disclosed in an embodiment of the present invention;

[0060] Figure 6 A block diagram of the structure of the intelligent cloth inspection system disclosed in an embodiment of the present invention;

[0061] Figure 7 A structural block diagram of an electronic device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Unless otherwise defined, the technical terms or scientific terms used herein should be the common meaning understood by people with general skills in the field to which the present invention belongs.

[0063] The words "first", "second" and similar words used in the patent application specification and claims of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, unless the context clearly indicates otherwise, the singular form of "a", "an" or "the" and other similar words do not indicate a quantitative limitation, but indicate the existence of at least one. "Include" or "comprises" and other similar words mean that the elements or objects appearing before "include" or "comprises" include the features, wholes, steps, operations, elements and / or components listed after "include" or "comprises", and do not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0064] Based on the traditional scheme of defect detection by operators in a visual manner, operators usually manually record fabric defects. Manual recording is not only inefficient and unable to quickly evaluate and generate fabric inspection reports, but also the manually recorded materials are easily lost. Therefore, it is often necessary to re-enter the electronic system, and recording errors are also prone to occur during the secondary entry. Therefore, the present invention aims to propose an intelligent fabric inspection method, system and electronic equipment. By identifying the barcode of the fabric roll to be inspected, the intelligent device directly enters the electronic information of fabric defects through algorithm calculation according to its rules. Not only can the fabric inspection report be generated quickly and efficiently, but also its solution can be connected with the factory's warehousing and business systems in real time, and production problems can be quickly discovered and solved when they occur.

[0065] The following is a further detailed introduction to the intelligent cloth inspection method, system and electronic device disclosed in the present invention in conjunction with the accompanying drawings.

[0066] Combination Figure 1 As shown, the intelligent cloth inspection method disclosed in the embodiment includes the following steps:

[0067] Step S102, scanning the barcode of the fabric roll to be inspected on the fabric inspection machine to determine the fabric roll specifications, so as to display the defect entry template corresponding to the fabric specifications on the smart device; the defect entry template is matched with the corresponding fabric roll specifications, so as to facilitate data statistics and score calculation;

[0068] Step S104, sequentially obtain multiple images of the portion of the fabric in the fabric roll spread on the inspection area under different light and shadow environments; defects will show different effects under different light and shadow conditions, and some defects will not show up under white light conditions, so all defects can be found under different light and shadow conditions.

[0069] Step S106, using a cloth defect detection model based on deep learning to sequentially identify and obtain fabric defects in each image, merge them into a fabric defect set of the corresponding part of the fabric, and then enter the fabric defects one by one in the corresponding template area of ​​the defect entry template, and automatically judge the fabric defect deduction score according to the defect scoring standard; wherein, the cloth defect detection model based on deep learning is a convolutional neural network as a whole, and the network adopts the semi-supervised learning Faster R-CNN algorithm. The Faster R-CNN algorithm achieves fast and accurate defect detection by introducing the RPN network and end-to-end training strategy. Fabric defects are identified through the model to avoid errors caused by manual visual identification of fabric defects and entering them into the defect entry template, and automatic deduction management can also be achieved;

[0070] Step S108, receiving a defect entry completion signal, and generating a fabric score report according to the fabric evaluation criteria, the fabric defect sets, and the deduction scores of all fabric defects automatically judged according to the defect scoring criteria; wherein the fabric score report lists the total deduction score of the fabric roll, the number of different fabric defects, and the total deduction score corresponding to each classification of fabric defects; different fabric defects have different deduction scores, for example, the deduction score for holes is higher than the deduction score for black spots.

[0071] Step S110, classify the fabric rolls that have completed the inspection according to the fabric grade evaluation standard and the fabric score report. The purpose of fabric roll grade classification is to manage inventory on the one hand, and to help business development on the other hand, such as accepting orders based on existing inventory or planning production tasks based on inventory.

[0072] The intelligent cloth inspection method disclosed in the embodiment of the present invention can quickly generate cloth inspection reports by combining a traditional cloth inspection machine with an intelligent device, such as a handheld PAD terminal, to input fabric defects into the system. Compared with the prior art, this not only improves the input efficiency but also saves the time cost of manual re-entry into the system.

[0073] In order to improve the accuracy of fabric score judgment during fabric inspection, the intelligent fabric inspection method disclosed in the embodiment also includes accurately determining the location of fabric defects, and then deducting points according to the deduction points corresponding to the different locations of the defects; the specific implementation process is as follows: Figure 2As shown, it includes: step S202, according to the specifications of the fabric roll and the size of the fabric inspection area of ​​the fabric inspection machine, setting a positioning template matching the fabric inspection area, the positioning template including a plurality of positioning areas; step S204, for each fabric roll specification, configuring a defect entry template corresponding to the positioning template of the corresponding fabric roll specification on the smart device, the defect entry template setting a plurality of defect positioning areas; the existence of the defect positioning area can accurately confirm the location of the fabric defect for subsequent fabric processing, and on the other hand, different defects have different deduction scores; step S206, establishing positioning coordinates for the image picture, so that the cloth defect detection based on deep learning can be carried out. When the fabric defect is obtained by the detection model identification, the first position information of the fabric defect is synchronously located, and the second position information on the positioning template is determined on the fabric inspection machine; wherein, the first position information is the coordinate information in the positioning coordinates where the fabric defect is located, and the second position information is the positioning area where the fabric defect is located; step S208, judge the position deviation of the first position information and the second position information, and when the position deviation is within the preset range, according to the specifications of the fabric roll, the first position information or the second position information, select the corresponding defect entry template and enter the fabric defect in the corresponding position of the defect entry template. By judging the position deviation of the first position information and the second position information, on the one hand, the detection accuracy of the cloth defect detection model based on deep learning can be verified, and on the other hand, the data information of the positioning template and the image can be matched.

[0074] And the process of accurately calculating the deduction score in the defect entry template also includes: step S302, dividing the defect entry template into a plurality of scoring areas according to the defect scoring standard, the scoring area including a plurality of defect location areas; step S304, adding corresponding deduction score items to each of the scoring areas according to the deduction score of each fabric defect, the deduction score items including the deduction scores corresponding to different fabric defects; wherein the deduction score items of each defect location area in each of the scoring areas are the same, specifically as Figure 3 As shown in the figure, fabric defects in the same scoring area will have the same deduction score, which is convenient for defect entry templates; for example, a defect in the middle of the fabric will have a higher deduction score than a defect at the edge of the fabric.

[0075] Optionally, in order to facilitate the intelligent device and the fabric inspection machine to synchronously identify and enter fabric defects, the defect entry template is designed as a page-turning text format in the embodiment, and the working process is designed as follows: Figure 4As shown, it includes: step S402, according to the fabric roll specifications, determine the length of the fabric rolled thereon; step S404, according to the length of the fabric, divide the defect entry template corresponding to the fabric roll specifications into a page-turning text, any page of the page-turning text is similar to the size of the fabric inspection area, and each page of the page-turning text corresponds to each fabric segment photographed by the fabric roll; step S406, when the fabric in the fabric inspection area of ​​the fabric inspection machine is completed, the fabric of the fabric roll is released in sequence to re-cover the fabric inspection area, and the corresponding defect entry template automatically switches to the next page after completing the defect entry of the current page. There is no need to manually switch the display page of the smart device. In the embodiment, the smart device is designed as a handheld PAD terminal with a scanning function. After the handheld PAD terminal scans the barcode of the fabric roll, it automatically jumps to the entry interface of the corresponding defect entry template.

[0076] Optionally, the intelligent fabric inspection method of the present invention further includes determining the quality of fabric rolls during fabric inspection, and classifying the qualified fabric rolls after the fabric inspection is completed; specifically, Figure 5 As shown, it includes: step S502, when the fabric inspection machine is working, it is judged in real time whether the fabric roll currently being inspected belongs to a qualified fabric roll, and when the fabric roll belongs to a qualified fabric roll, the fabric roll is graded according to the fabric grade evaluation standard and the fabric score report; wherein, the process of judging in real time whether the fabric roll currently being inspected belongs to a qualified fabric roll includes: real-time calculation of the fabric score of the fabric roll currently being inspected by the fabric inspection machine, when the fabric score of the inspected fabric roll in each preset inspection cycle is lower than the corresponding score threshold, the fabric roll is unqualified; this process is mainly for fabrics of poor quality, there are too many fabric defects leading to unqualified products, such products are directly classified during the fabric inspection process, not only can the same batch of products be tracked through barcodes for problem tracing, but also can reduce the calculation and classification after the inspection. Real-time calculation and input of the type, quantity and corresponding area of ​​fabric defects, when the number of target fabric defects exceeds the preset target or the area exceeds the preset proportion, the fabric roll is unqualified; this process is aimed at important fabric defects that affect fabric quality, when they appear or the area exceeds the preset proportion, such unqualified fabric rolls are directly managed for inventory or problem tracing.

[0077] In an embodiment of the present application, an electronic device is also provided, including a computer program, the computer program being stored in a computer-readable storage medium; when a processor of the electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device performs the steps of the above-mentioned intelligent cloth inspection method. Taking an electronic device running on a computer as an example, Figure 7As shown, the electronic device may include one or more (only one is shown in the figure) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, and a transmission device for communication functions. A person skilled in the art can understand that Figure 7 The structure shown is for illustration only and does not limit the structure of the above-mentioned electronic device.

[0078] The above program can be run in the processor, or it can be stored in the memory, that is, in the computer-readable medium, which includes permanent and non-permanent, removable and non-removable media. Information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer-readable media does not include temporary computer-readable media, such as modulated data signals and carrier waves. These computer programs can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in a block or multiple blocks may be implemented by different modules corresponding to different method steps.

[0079] In this embodiment, such a device or system is provided, which can be called an intelligent cloth inspection system. Figure 6As shown, it includes: a scanning and determining module, which is used to scan the barcode of the fabric roll to be inspected on the fabric inspection machine to determine the specifications of the fabric roll, so as to display the defect entry template of the corresponding fabric specifications on the smart device; an identification and acquisition module, which is used to sequentially obtain multiple images of the fabric roll spread on the inspection area under different light and shadow environments; an entry and judgment module, which is used to use a cloth defect detection model based on deep learning to sequentially identify and obtain fabric defects in each image, merge them into a fabric defect set of the corresponding part of the fabric, and then enter the fabric defects one by one in the corresponding template area of ​​the defect entry template, and automatically judge the fabric defect deduction score according to the defect scoring standard; wherein, the cloth defect detection model based on deep learning adopts the semi-supervised learning Faster R-CNN algorithm; a receiving and generating module, used to receive a defect entry completion signal, and generate a fabric score report according to fabric evaluation standards, a set of fabric defects, and deduction scores of all fabric defects automatically judged according to the defect scoring standards; wherein the fabric score report lists the total deduction score of the fabric roll, the number of different fabric defects, and the total deduction score corresponding to each classified fabric defect; a classification module, used to grade the fabric roll that has completed the inspection according to the fabric grade evaluation standard and the fabric score report.

[0080] The steps of the system for implementing the intelligent cloth inspection method disclosed in the above embodiment have been described and will not be repeated here.

[0081] For example, the intelligent cloth inspection system also includes: a setting module, which is used to set a positioning template matching the cloth inspection area according to the specifications of the fabric roll and the size of the cloth inspection area of ​​the cloth inspection machine, and the positioning template includes several positioning areas; a configuration module, which is used to configure a defect entry template corresponding to the positioning template of the corresponding fabric roll specifications on the intelligent device for each fabric roll specification, and the defect entry template is set with several defect positioning areas; an acquisition and determination module, which is used to establish positioning coordinates for the image picture, so that the cloth defect detection model based on deep learning can identify and obtain the fabric defect and synchronously locate the first position information of the fabric defect, and determine its second position information on the positioning template on the cloth inspection machine; wherein the first position information is the coordinate information in the positioning coordinates where the fabric defect is located, and the second position information is the positioning area where the fabric defect is located; a judgment and entry module, which is used to judge the position deviation of the first position information and the second position information, and when the position deviation is within a preset range, according to the specification of the fabric roll, the first position information or the second position information, select the corresponding defect entry template and enter the fabric defect at the corresponding position of the defect entry template. Optionally, an embodiment designs a layout of a defect entry template according to the specifications of the fabric roll to be inspected, for example, the defect entry template is related to a layout of page-turning text, that is: according to the specifications of the fabric roll, the length of the fabric rolled thereon is determined; according to the length of the fabric, the defect entry template corresponding to the specifications of the fabric roll is divided into page-turning text, and any page of the page-turning text is similar in size to the fabric inspection area; when the fabric in the fabric inspection area of ​​the fabric inspection machine completes image acquisition for defect detection and identification, the fabric of the fabric roll is released in sequence to re-cover the fabric inspection area, and the corresponding defect entry template automatically switches to the next page after completing the defect entry of the current page.

[0082] For another example, the intelligent fabric inspection system also includes: a division unit, used to divide the defect entry template into several scoring areas according to the defect scoring standard, and the scoring areas include several defect location areas; an adding unit, used to add corresponding deduction items to each of the scoring areas according to the deduction scores of each fabric defect, and the deduction items include deduction scores corresponding to different fabric defects; wherein the deduction items of each defect location area in each scoring area are the same.

[0083] For another example, the intelligent cloth inspection system also includes: a judgment module, which is used to judge in real time whether the fabric roll currently being inspected is a qualified fabric roll when the cloth inspection machine is working, and to grade the fabric roll according to the fabric grade evaluation standard and the fabric score report when the fabric roll is a qualified fabric roll; wherein, the process of judging in real time whether the fabric roll currently being inspected is a qualified fabric roll includes: real-time calculation of the fabric score of the fabric roll currently being inspected by the cloth inspection machine, when the fabric score of the inspected fabric roll in each preset inspection cycle is lower than the corresponding score threshold, the fabric roll is unqualified; real-time calculation and entry of the type, quantity and corresponding area of ​​fabric defects, when the number of target fabric defects exceeds the preset target or the area exceeds the preset ratio, the fabric roll is unqualified. By judging whether the quality of the fabric roll is qualified during the cloth inspection process, it is helpful to discover loopholes in production or inventory that cause product quality problems and to conduct early repairs.

[0084] The intelligent cloth inspection method, system and electronic equipment disclosed in the present invention combine a cloth inspection machine and an intelligent device for use, which not only solves the problems of low efficiency in manually recording fabric defects and errors in secondary entry during cloth inspection, but also realizes rapid positioning and deduction score judgment of fabric defects on fabric rolls of different specifications by designing a positioning template in conjunction with a defect entry template. After a score report is quickly generated through the deduction score items added to each defect positioning area, it is judged whether the fabric roll currently being inspected is qualified and the grade of the fabric roll. In addition, the intelligent cloth inspection method of the present invention can not only be used for inventory management, but also helps manufacturers to carry out business planning by collecting information on all fabric rolls in the inventory.

[0085] Although the present invention has been disclosed as above with preferred embodiments, it is not intended to limit the present invention. A person with ordinary knowledge in the technical field to which the present invention belongs may make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be determined by the definition of the claims.

Claims

1. A method for intelligent cloth inspection, characterized in that: include: Scan the barcode of the fabric roll to be inspected on the fabric inspection machine to determine the fabric roll specifications so that the defect entry template corresponding to the fabric specifications can be displayed on the smart device; Under different light and shadow environments, multiple images of the fabric roll spread on the inspection area are sequentially obtained; A cloth defect detection model based on deep learning is used to sequentially identify and obtain fabric defects in each image, and after merging into a fabric defect set of a corresponding part of the fabric, the fabric defects are entered one by one in the corresponding template area of ​​the defect entry template, and the fabric defects are automatically judged and deducted according to the defect scoring standard; wherein the cloth defect detection model based on deep learning adopts the semi-supervised learning Faster R-CNN algorithm; Receiving a defect entry completion signal, generating a fabric score report according to fabric evaluation criteria, each fabric defect set, and all fabric defect deduction scores automatically judged according to the defect scoring criteria; wherein the fabric score report lists the total deduction score of the fabric roll, the number of different fabric defects, and the total deduction score corresponding to each category of fabric defects; According to the fabric grade evaluation standard and the fabric score report, the fabric rolls that have completed the fabric inspection are graded.

2. The intelligent cloth inspection method according to claim 1, characterized in that: Also includes: According to the specifications of the fabric roll and the size of the fabric inspection area of ​​the fabric inspection machine, a positioning template matching the fabric inspection area is set, and the positioning template includes a plurality of positioning areas; For each fabric roll specification, a defect entry template corresponding to the positioning template of the corresponding fabric roll specification is configured on the smart device, and the defect entry template is provided with a plurality of defect positioning areas; Establishing positioning coordinates for the image picture, so that the cloth defect detection model based on deep learning can simultaneously locate the first position information of the fabric defect when identifying and acquiring the fabric defect, and determine its second position information on the positioning template on the cloth inspection machine; wherein the first position information is the coordinate information in the positioning coordinates where the fabric defect is located, and the second position information is the positioning area where the fabric defect is located; Determine the position deviation of the first position information and the second position information. When the position deviation is within a preset range, select the corresponding defect entry template according to the specifications of the fabric roll, the first position information or the second position information, and enter the fabric defect at the corresponding position of the defect entry template.

3. The intelligent cloth inspection method according to claim 2, characterized in that: Also includes: According to the defect scoring standard, the defect entry template is divided into a plurality of scoring areas, wherein the scoring area includes a plurality of defect location areas; According to the deduction score of each fabric defect, corresponding deduction score items are added to each scoring area, and the deduction score items include deduction scores corresponding to different fabric defects; wherein the deduction score items of each defect positioning area in each scoring area are the same.

4. The intelligent cloth inspection method according to claim 2, characterized in that: Also includes: Determine the length of the fabric to be rolled up according to the fabric roll specifications; According to the length of the fabric, the defect entry template corresponding to the fabric roll specification is divided into a flip text, any page of the flip text is similar to the size of the fabric inspection area, and each page of the flip text corresponds to each fabric segment photographed by the fabric roll; When the fabric in the fabric inspection area of ​​the fabric inspection machine is inspected, the fabric on the fabric roll is released in sequence to re-cover the fabric inspection area, and the corresponding defect entry template automatically switches to the next page after completing the defect entry of the current page.

5. The intelligent cloth inspection method according to claim 1, characterized in that: Also includes: When the fabric inspection machine is working, it is determined in real time whether the fabric roll currently being inspected is a qualified fabric roll, and when the fabric roll is a qualified fabric roll, the fabric roll is graded according to the fabric grade evaluation standard and the fabric score report; The process of determining in real time whether the fabric roll currently being inspected is a qualified fabric roll includes: Calculate in real time the fabric score of the fabric roll currently inspected by the fabric inspection machine, and when the fabric score of the inspected fabric roll in each preset inspection cycle is lower than the corresponding score threshold, the fabric roll is unqualified; The type, quantity and corresponding area of ​​fabric defects are calculated and input in real time. When the number of target fabric defects exceeds the preset target or the area exceeds the preset ratio, the fabric roll is unqualified.

6. An intelligent cloth inspection system, characterized in that: include: The scanning and determination module is used to scan the barcode of the fabric roll to be inspected on the fabric inspection machine to determine the fabric roll specifications so as to display the defect entry template corresponding to the fabric specifications on the smart device; The recognition and acquisition module is used to sequentially acquire multiple images of the fabric roll spread on the inspection area under different light and shadow environments; An input evaluation module is used to use a cloth defect detection model based on deep learning to sequentially identify fabric defects in each image picture, merge them into a fabric defect set of a corresponding part of the fabric, and then enter the fabric defects one by one in the corresponding template area of ​​the defect input template, and automatically judge the fabric defects and deduct scores according to the defect scoring standard; wherein the cloth defect detection model based on deep learning adopts the Faster R-CNN algorithm of semi-supervised learning; A receiving and generating module is used to receive a defect entry end signal, and generate a fabric score report according to the fabric evaluation standard, each fabric defect set, and all fabric defect deduction scores automatically judged according to the defect scoring standard; wherein the fabric score report lists the total deduction score of the fabric roll, the number of different fabric defects, and the total deduction score corresponding to each classification of fabric defects; The classification module is used to classify the fabric rolls that have completed the fabric inspection according to the fabric grade evaluation standard and the fabric score report.

7. The intelligent cloth inspection system according to claim 6, characterized in that: Also includes: A setting module, used to set a positioning template matching the fabric inspection area according to the specifications of the fabric roll and the size of the fabric inspection area of ​​the fabric inspection machine, wherein the positioning template includes a plurality of positioning areas; A configuration module, for configuring, for each fabric roll specification, a defect entry template corresponding to the positioning template of the corresponding fabric roll specification on the smart device, wherein the defect entry template sets a plurality of defect positioning areas; An acquisition and determination module is used to establish positioning coordinates for the image picture, so that the cloth defect detection model based on deep learning can identify and obtain the first position information of the fabric defect and simultaneously locate the fabric defect, and determine its second position information on the positioning template on the cloth inspection machine; wherein the first position information is the coordinate information in the positioning coordinates where the fabric defect is located, and the second position information is the positioning area where the fabric defect is located; A judgment and entry module is used to judge the position deviation of the first position information and the second position information. When the position deviation is within a preset range, according to the specifications of the fabric roll, the first position information or the second position information, the corresponding defect entry template is selected and the fabric defect is entered at the corresponding position of the defect entry template.

8. The intelligent cloth inspection system according to claim 7, characterized in that: Also includes: A division unit, used to divide the defect entry template into a plurality of scoring areas according to a defect scoring standard, wherein the scoring area includes a plurality of defect location areas; The adding unit is used to add corresponding deduction items to each scoring area according to the deduction scores of each fabric defect, and the deduction items include deduction scores corresponding to different fabric defects; wherein the deduction items of each defect positioning area in each scoring area are the same.

9. The intelligent cloth inspection system according to claim 6, characterized in that: Also includes: A judgment module, used for judging in real time whether the fabric roll currently being inspected is a qualified fabric roll when the fabric inspection machine is working, and classifying the fabric roll according to the fabric grade evaluation standard and the fabric score report when the fabric roll is a qualified fabric roll; The process of determining in real time whether the fabric roll currently being inspected is a qualified fabric roll includes: Calculate in real time the fabric score of the fabric roll currently inspected by the fabric inspection machine, and when the fabric score of the inspected fabric roll in each preset inspection cycle is lower than the corresponding score threshold, the fabric roll is unqualified; The type, quantity and corresponding area of ​​fabric defects are calculated and input in real time. When the number of target fabric defects exceeds the preset target or the area exceeds the preset ratio, the fabric roll is unqualified.

10. An electronic device, characterized in that: It includes a computer program, which is stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device performs the steps of the intelligent cloth inspection method described in any one of claims 1 to 5.

Images