CN115201211A - Quality control method and system for intelligent visual textile product - Google Patents
Quality control method and system for intelligent visual textile product Download PDFInfo
- Publication number
- CN115201211A CN115201211A CN202211121217.9A CN202211121217A CN115201211A CN 115201211 A CN115201211 A CN 115201211A CN 202211121217 A CN202211121217 A CN 202211121217A CN 115201211 A CN115201211 A CN 115201211A
- Authority
- CN
- China
- Prior art keywords
- textile
- image acquisition
- result
- identification
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/36—Textiles
- G01N33/367—Fabric or woven textiles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
- G01N35/00584—Control arrangements for automatic analysers
- G01N35/00594—Quality control, including calibration or testing of components of the analyser
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Multimedia (AREA)
- Textile Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The invention provides a quality control method and a system of an intelligent visual textile product, which relate to the related technical field of data processing.A first unfolding device, an initial image acquisition device and a position detection device are arranged according to textile information by acquiring the textile information, and the initial image acquisition device and the position detection device are utilized to acquire images to obtain an initial image acquisition set, and the initial image acquisition set is subjected to image initial processing and then characteristic identification to obtain a characteristic identification result; constructing an identification coordinate system, and obtaining a feature positioning coordinate based on the image information, the textile information and the identification coordinate system corresponding to the feature identification result; the textile to be detected is conveyed to the second unfolding device with the control speed smaller than the first control speed for retesting to generate a quality detection result of the textile to be detected, and the technical problems that in the prior art, the accuracy of the quality detection result of the textile product is low, the detection efficiency is low, and real-time quality detection visualization cannot be realized are solved.
Description
Technical Field
The invention relates to the technical field related to data processing, in particular to a quality control method and system for intelligent visual textile products.
Background
China is a large country for textile production and export, the Chinese textile industry develops for many years, has obvious competitive advantages, has the most complete industrial chain in the world and the highest processing matching level, continuously enhances the self-regulation capacity of a plurality of developed industrial clusters for coping with market risks, and provides a solid guarantee for keeping the steady development pace of the industry.
With the rapid development of economy and the progress of science and technology in China, the quality of life of people is gradually improved, the requirement standard for materials is higher and higher, a textile is used as one of necessities of life of people, the detection link of the textile increasingly embodies the importance and the necessity of the textile, in order to meet the related requirements of people, the strength for detecting the textile is fully increased, and a foundation is laid for the development of the textile industry in the future.
At present, the quality detection of textiles mainly comprises the detection of detection personnel, the detection of a detection machine and the combination of the detection personnel and the detection machine, wherein for the detection of the detection personnel, due to long-time and high-intensity manual operation, subjective judgment is easily influenced, and the conditions of low quality detection precision and low efficiency are caused; although the detection machine and the computer are applied to the textile quality detection, the partial detection precision and efficiency are improved, but some problems still exist, and the quality monitoring of the textile products cannot be realized in a real-time visualization manner.
Disclosure of Invention
The application provides a quality control method and a quality control system for intelligent visual textile products, which are used for solving the technical problems that the accuracy of a quality detection result of a textile product is low, the detection efficiency is low and the real-time quality detection visualization cannot be realized in the prior art, and the quality detection accuracy of the textile product is improved under the condition of improving the detection efficiency, so that the technical effects of providing directions for the research and development and the improvement of the textile product are achieved while the use requirements of consumers on the textile product are met.
In view of the above problems, the present application provides a quality control method and system for intelligent visual textile products.
In a first aspect, an embodiment of the present application provides a quality control method for an intelligent visual textile product, where the method is applied to a quality detection system, the quality detection system is in communication connection with a first unfolding device, a second unfolding device, a position detection device, an initial image acquisition device, and a retest image acquisition device, and the method includes: collecting textile information, arranging the first unfolding device according to the textile information, and setting a first control speed, wherein the first control speed is the speed of the first unfolding device for conveying the textile to be tested; laying the initial image acquisition device and the position detection device according to the laying result of the first unfolding device; when the position detection device detects a signal of the textile to be detected, generating a detection signal, setting acquisition control parameters of the initial image acquisition device according to the first control speed and the detection signal, and controlling image acquisition of the textile to be detected based on the acquisition control parameters to obtain an initial image acquisition set; performing image initial processing on the initial image acquisition set to obtain a processed image set, and performing feature recognition on the processed image set to obtain a feature recognition result; constructing an identification coordinate system based on the acquisition control parameters, and carrying out coordinate restoration based on the image information, the textile information and the identification coordinate system corresponding to the feature identification result to obtain feature positioning coordinates; conveying the textile to be tested to the second unfolding device, wherein the second unfolding device has a second control speed, and the second control speed is lower than the first control speed; and acquiring the images of the textiles to be detected by the retest image acquisition device based on the characteristic positioning coordinates and the second control speed, and generating a quality detection result of the textiles to be detected based on a retest image acquisition result.
In a second aspect, an embodiment of the present application provides a quality control system for intelligent visual textile products, the system includes: the system comprises an information acquisition module, a first expansion device and a second expansion device, wherein the information acquisition module is used for acquiring textile information, arranging the first expansion device according to the textile information and setting a first control speed, and the first control speed is the speed of the first expansion device for conveying a textile to be detected; the device laying module is used for laying an initial image acquisition device and a position detection device according to the first unfolding device laying result; the initial image acquisition module is used for generating a detection signal when the position detection device detects a signal of the textile to be detected, setting acquisition control parameters of the initial image acquisition device according to the first control speed and the detection signal, and controlling image acquisition of the textile to be detected based on the acquisition control parameters to obtain an initial image acquisition set; the image characteristic identification module is used for carrying out image initial processing on the initial image acquisition set to obtain a processed image set, and carrying out characteristic identification on the processed image set to obtain a characteristic identification result; the characteristic positioning coordinate acquisition module is used for constructing an identification coordinate system based on the acquisition control parameters, and carrying out coordinate restoration based on the image information, the textile information and the identification coordinate system corresponding to the characteristic identification result to obtain a characteristic positioning coordinate; the textile conveying module is used for conveying the textile to be tested to the second unfolding device, the second unfolding device has a second control speed, and the second control speed is smaller than the first control speed; and the quality detection result generation module is used for acquiring the images of the textiles to be detected through the retest image acquisition device based on the characteristic positioning coordinates and the second control speed, and generating the quality detection result of the textiles to be detected based on the retest image acquisition result.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the quality control method and system for the intelligent visual textile product, textile information is collected, the first unfolding device is arranged according to the textile information, and a first control speed is set, wherein the first control speed is the speed of the first unfolding device for conveying the textile to be tested; laying the initial image acquisition device and the position detection device according to the laying result of the first unfolding device; when the position detection device detects a signal of the textile to be detected, generating a detection signal, setting acquisition control parameters of the initial image acquisition device according to the first control speed and the detection signal, and controlling image acquisition of the textile to be detected based on the acquisition control parameters to obtain an initial image acquisition set; performing image initial processing on the initial image acquisition set to obtain a processed image set, and performing feature recognition on the processed image set to obtain a feature recognition result; constructing an identification coordinate system based on the acquisition control parameters, and carrying out coordinate restoration based on the image information, the textile information and the identification coordinate system corresponding to the feature identification result to obtain feature positioning coordinates; conveying the textile to be tested to a second unfolding device, wherein the second unfolding device has a second control speed, and the second control speed is less than the first control speed; and acquiring the images of the textiles to be detected by the retest image acquisition device based on the characteristic positioning coordinates and the second control speed, and generating a quality detection result of the textiles to be detected based on a retest image acquisition result. The technical problems that in the prior art, the accuracy of the quality detection result of the textile product is low, the detection efficiency is low, and the real-time quality detection visualization cannot be realized are solved, so that the quality detection precision of the textile product is improved under the condition of improving the detection efficiency, the use requirement of a consumer on the textile product is met, and the technical effect of providing direction for the research and development and improvement of the textile product is achieved.
Drawings
Fig. 1 is a schematic flow chart of a quality control method for intelligent visual textile products provided by the present application;
fig. 2 is a schematic flow chart of obtaining feature positioning coordinates in the quality control method for intelligent visual textile products provided by the present application;
fig. 3 is a schematic flow chart of a retest image acquisition result obtained in the quality control method for an intelligent visual textile product provided by the present application;
fig. 4 is a schematic structural diagram of a quality control system of an intelligent visual textile product provided by the present application;
description of reference numerals: the system comprises an information acquisition module 100, a device arrangement module 200, an initial image acquisition module 300, an image characteristic identification module 400, a characteristic positioning coordinate acquisition module 500, a textile conveying module 600 and a quality detection result generation module 700.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The application provides a quality control method and a quality control system for intelligent visual textile products, and the method and the system are used for solving the technical problems that in the prior art, the accuracy of a quality detection result of the textile product is low, the detection efficiency is low, and the real-time quality detection visualization cannot be realized, so that the quality detection accuracy of the textile product is improved under the condition of improving the detection efficiency, the use requirements of consumers on the textile product are met, and meanwhile, the technical effect of providing directions for the research and development and improvement of the textile product is achieved.
Example one
As shown in fig. 1, the present application provides a quality control method for intelligent visual textile products, the method is applied to a quality detection system, the quality detection system is in communication connection with a first unfolding device, a second unfolding device, a position detection device, an initial image acquisition device and a retest image acquisition device, and the method comprises:
s100: collecting textile information, arranging the first unfolding device according to the textile information, and setting a first control speed, wherein the first control speed is the speed of the first unfolding device for conveying the textile to be tested;
particularly, the fabrics includes the yarn, the woven fabrics, knitted fabrics, the knitting etc., the application field of fabrics is extensive, the fabrics is in the building field, industry field, the aerospace field, the medicine field, the automobile field, the protection field, daily resident life field etc. all play crucial effect, along with the rapid development of science and technology and economy, performance requirement to the fabrics is also higher and higher, the quality control of fabrics is the key step that guarantees that the fabrics can satisfy people's demand, how accurate efficient detects and control the fabrics quality becomes the problem that needs the solution at present urgently.
Before the textile leaves a factory, the quality of the textile needs to be detected, in the embodiment of the application, information of the textile is collected to obtain information of the type, the purpose, the size and the like of the textile, the first unfolding device is arranged according to the information of the textile, the first unfolding device is arranged and comprises a position arrangement of the first unfolding device and/or a type arrangement of the first unfolding device, preferably, the first unfolding device comprises a conveying device, the first unfolding device is used for unfolding the textile onto the conveying device and can control the conveying speed to convey the textile to the next link, the conveying speed of the first unfolding device is set according to the information of the textile, namely, the first control speed is set, and the textile is conveyed.
S200: laying the initial image acquisition device and the position detection device according to the laying result of the first unfolding device;
specifically, the initial image acquisition device and the position detection device are arranged according to the arrangement result of the first unfolding device, wherein the initial image acquisition device corresponds to the first unfolding device and is used for acquiring images of textiles on the first unfolding device, and the position detection device is used for detecting whether the textiles reach a certain position or not to prepare for subsequent image acquisition.
S300: when the position detection device detects a signal of the textile to be detected, generating a detection signal, setting acquisition control parameters of the initial image acquisition device according to the first control speed and the detection signal, and controlling image acquisition of the textile to be detected based on the acquisition control parameters to obtain an initial image acquisition set;
specifically, when the position detection device detects that the textile to be detected on the first unfolding device reaches a signal of a certain position, a detection signal is generated, acquisition control parameters of the initial image acquisition device are set according to the first control speed and the detection signal, the acquisition control parameters of the image acquisition device mainly comprise the time for the initial image acquisition device to start acquisition and acquisition parameters related to the initial image acquisition process, the acquisition time of the initial image acquisition device is set according to the first control speed corresponding to the first unfolding device and the detection signal, and the initial image acquisition device is used for carrying out image acquisition on the textile on the first unfolding device to obtain an initial image acquisition set.
S400: performing image initial processing on the initial image acquisition set to obtain a processed image set, and performing feature recognition on the processed image set to obtain a feature recognition result;
specifically, in the process of image acquisition by using the image acquisition device, the electronic elements are affected by the surrounding complex working environment to generate interference, the imaging quality is affected, and image noise is generated. In order to eliminate the influence of image noise on the accuracy of subsequent image feature extraction and recognition, image preprocessing is performed on an acquired initial image acquisition set before image feature extraction is performed, for example, linear mean filtering or nonlinear median filtering or image enhancement processing is adopted to obtain an image set after preprocessing, and feature extraction and recognition are performed on the image set after preprocessing, for example, HOG feature extraction, LBP feature extraction and the like, so as to obtain a feature recognition result.
S500: constructing an identification coordinate system based on the acquisition control parameters, and carrying out coordinate restoration based on the image information, the textile information and the identification coordinate system corresponding to the feature identification result to obtain feature positioning coordinates;
specifically, after acquiring the acquisition control parameters of the initial image acquisition device according to the first control speed of the first unfolding device and the detection signals when the textile is detected by the position detection device, an identification coordinate system is established based on the acquisition control parameters, the identification coordinate system is the identification coordinate system of the textile to be detected on the first unfolding device by the initial image acquisition device, and coordinate restoration is performed on the basis of image information, textile information and the identification coordinate system corresponding to the characteristic identification result to obtain characteristic positioning coordinates, and the characteristic positioning coordinates are real coordinates corresponding to different positions of the textile to provide a basis for the layout of the subsequent retest image acquisition device.
Further, as shown in fig. 2, step S500 in the method provided in the embodiment of the present application further includes:
s510: constructing a single image effective interval according to the acquisition control parameters;
s520: constructing the identification coordinate system for the single image effective interval, wherein the identification coordinate system is a two-dimensional rectangular coordinate system;
s530: performing feature coordinate recognition of the recognition coordinate system based on the feature recognition result to obtain a coordinate recognition result, wherein the coordinate recognition result comprises an abscissa recognition result and an ordinate recognition result;
s540: acquiring image label information corresponding to the feature identification result, and updating the ordinate identification result based on the image label information, the single-image effective interval and the textile information to acquire an updated ordinate identification result;
s550: and obtaining the feature positioning coordinate based on the updated ordinate recognition result and the abscissa recognition result.
Specifically, because the area acquired by the image acquisition device at one time is limited, a single image effective interval is constructed according to the acquisition control parameters of the initial image acquisition device, and the identification coordinate system is constructed for the single image effective interval, wherein the identification coordinate system is a two-dimensional rectangular coordinate system, illustratively, when the position detection device is used for detecting the signal of the textile to be detected, the time for starting acquisition of the initial image acquisition device is calculated according to the control speed and the detection signal of the first unfolding device, and the two-dimensional rectangular coordinate system is established by taking the horizontal position of the initial image acquisition device as the origin; the method comprises the steps of utilizing an initial image acquisition device to acquire an image of a textile to be detected, identifying characteristic coordinates of an identification coordinate system according to a characteristic identification result to obtain a coordinate identification result, wherein the coordinate identification result comprises an abscissa identification result and an ordinate identification result, obtaining image label information corresponding to the characteristic identification result, updating the ordinate identification result based on the image label information, a single-image effective interval and textile information to obtain an updated ordinate identification result, obtaining the characteristic positioning coordinates based on the updated ordinate identification result and the abscissa identification result, exemplarily, assuming that the size of the textile to be detected is 15m, the initial image acquisition device is required to acquire 5 times to acquire the full appearance of the textile to be detected, the single-image effective interval is 3m, carrying out image labeling on images of different acquired areas according to an acquisition sequence, such as 3236 zft 3236, obtaining the coordinate identification result based on the characteristic identification result, taking the horizontal position of the initial image acquisition device as an origin, obtaining the coordinate identification result, wherein the coordinate identification result is the abscissa and the ordinate corresponding to different acquired images, the identification result is an image label corresponding to 372, and the coordinate identification result is an image corresponding to 3763 (the coordinate identification result is an image corresponding to 372), and the characteristic positioning result is an image corresponding to 3763).
S600: conveying the textile to be tested to a second unfolding device, wherein the second unfolding device has a second control speed, and the second control speed is less than the first control speed;
specifically, after the characteristic positioning coordinates of the textile to be detected are obtained, the textile to be detected is conveyed to the second unfolding device, and the second unfolding device is provided with a second control speed, wherein the second control speed is smaller than the first control speed, so that quality retesting is performed on the textile to be detected, and the accuracy of quality detection of the textile to be detected is improved.
S700: and acquiring the image of the textile to be detected by the retest image acquisition device based on the characteristic positioning coordinate and the second control speed, and generating a quality detection result of the textile to be detected based on a retest image acquisition result.
Particularly, a retest image acquisition device is arranged, the retest image acquisition device corresponds to the second unfolding device and is used for acquiring images of textiles to be detected on the second unfolding device, the position detection device is also used when the fabrics to be detected on the second unfolding device are acquired by the retest image acquisition device according to the characteristic positioning coordinates of the textiles to be detected and the second control speed of the second unfolding device, and the quality detection result of the textiles to be detected is generated according to the retest image acquisition result.
Further, as shown in fig. 3, step S700 in the method provided in the embodiment of the present application further includes:
s710: laying the retest image acquisition devices based on the characteristic positioning coordinates, and recording the laying coordinates;
s720: setting retest acquisition control parameters of the retest image acquisition device based on the layout coordinates, the feature positioning coordinates and the second control speed;
s730: and controlling the retest image acquisition device to acquire the images of the textiles to be detected through the retest acquisition control parameters to obtain a retest image acquisition result.
Specifically, according to the obtained characteristic positioning coordinates of the textile to be detected, namely, real coordinates corresponding to a certain characteristic of the textile, a retest image acquisition device is arranged, and the coordinates of the retest image acquisition device are recorded, wherein the retest image acquisition control parameters of the retest image acquisition device are set according to the coordinates of the arranged retest image acquisition device, the characteristic positioning coordinates of the textile to be detected and a second control speed of a second unfolding device, the retest image acquisition control parameters of the retest image acquisition device are parameters related to image acquisition by moving the retest image acquisition device to a characteristic positioning coordinate position corresponding to an abnormal characteristic according to the characteristic positioning coordinates, the second control speed and the coordinates of the retest image acquisition device, the retest image acquisition result is obtained by controlling the retest image acquisition device to acquire the textile image to be detected through the retest image acquisition control parameters, the retest image acquisition result of a part with an abnormal problem in an initial image acquisition result is completed, and the detection accuracy of the quality of the textile product is improved.
Further, after obtaining the initial set of image acquisitions, the method further comprises:
s310: performing expansion evaluation on the textile to be tested on the initial image acquisition set to obtain an expansion evaluation result;
s320: when the part which does not meet the expected expansion evaluation threshold exists in the expansion evaluation result, generating an abnormal expansion identification instruction;
s330: re-detecting and marking the textile to be detected according to the abnormal unfolding marking instruction, and generating unfolding control feedback information;
s340: and re-detecting the textile to be detected based on the re-detection identification, and performing control optimization on the unfolded textile of the first unfolding device based on the unfolding control feedback information.
Specifically, after an initial image collection set is obtained by an initial image collection device, in order to prevent the first unfolding device from influencing the unfolding state of the textile to be tested and further influencing the feature recognition of the subsequent textile to be tested, the unfolding effect of the first unfolding device is detected, and specifically, the unfolding evaluation of the textile to be tested is performed according to the initial image collection set, preferably, the unfolding evaluation method can be completed by using a neural network model, the unfolding evaluation model is trained by using a large number of unfolding images of the textile to be tested, the unfolding evaluation model is established, and the unfolding evaluation model is used for carrying out unfolding evaluation processing on the input initial image collection set to obtain the unfolding evaluation result of the first unfolding device; setting an expected expansion evaluation threshold, wherein the expected expansion evaluation threshold can be obtained according to past experience, when the expansion evaluation result of a first expansion device has a part which does not meet the expected expansion evaluation threshold, generating an abnormal expansion identification instruction to indicate that a textile to be detected in some places is not fully expanded, re-detecting the textile to be detected according to the abnormal expansion identification instruction, generating expansion control feedback information for the first expansion device, re-detecting the textile to be detected based on the re-detection identification, and performing expansion textile control optimization of the first expansion device based on the expansion control feedback information to fully expand the textile to be detected, so as to fully prepare for subsequent image acquisition, reduce the influence of the first expansion device on the image acquisition, improve the accuracy of the image acquisition of the textile to be detected, reduce the time and the data waste of subsequent unqualified image processing, and indirectly further improve the accuracy of textile quality detection.
Further, after obtaining the feature recognition result, the method further includes:
s810: judging whether the feature identification result is an identification result with abnormal features;
s820: and when the characteristic identification result is the identification result without abnormal characteristics, shunting the textile to be detected to a detection non-abnormal assembly line through the first unfolding device, and adding one to the count of normal products to be detected.
Specifically, in the embodiment of the application, after a feature recognition result is obtained, whether abnormal features exist in the feature recognition result is judged, when the recognition result of the abnormal features does not exist in the feature recognition result, it is indicated that the textile to be detected has no surface quality problem, the textile to be detected is shunted and conveyed to a detection non-abnormal production line by using a first unfolding device, the detection result of the textile to be detected is recorded, the count of detected normal products is increased by one, the automatic detection of the abnormal features is achieved, and the detection efficiency is improved.
Further, the method further comprises:
s830: when the characteristic identification result is an identification result with abnormal characteristics, shunting the textile to be tested to the second unfolding device through the first unfolding device;
s840: and when the quality detection result is the identification result without abnormal characteristics, shunting the textile to be detected to a detection non-abnormal production line through the second unfolding device, and counting the number of normal products for detection by one.
Specifically, if the identification result of the abnormal features exists in the feature identification result, the textile to be detected is shunted to the second unfolding device by the first unfolding device, the textile to be detected is retested, when the retesting result is the identification result of the abnormal features, the textile to be detected is shunted and transported to a detection non-abnormal production line by the second unfolding device, the textile to be detected is recorded, and the count of the detected normal products is increased by one.
Further, the method provided by the embodiment of the present application further includes:
s850: when the quality detection result is an identification result with abnormal characteristics, generating abnormal identification information according to the abnormal characteristics;
s860: and performing classified abnormal counting based on the abnormal identification information, and shunting the textile to be detected to an abnormal assembly line corresponding to the classified abnormal counting through the second unfolding device.
Specifically, further, when the second unfolding device detects that the textile to be tested has an identification result of abnormal features by using the retest image acquisition device, abnormal identification information is generated according to the abnormal features, and the identification information is convenient for identifying the abnormal features on one hand and is convenient for subsequent data processing on the other hand; and carrying out abnormal classification counting according to the abnormal identification information, wherein the abnormal classification comprises that the surface has a hair bulb, the surface has a hook wire, the surface has a fold and the like, and the textile to be detected is shunted to an abnormal assembly line corresponding to the classified abnormal counting through the second unfolding device so as to be subjected to subsequent treatment.
To sum up, the quality control method of the intelligent visual textile product provided by the embodiment of the application has the following technical effects:
1. according to the quality control method of the intelligent visual textile product, textile information is collected, the first unfolding device is arranged according to the textile information, and a first control speed is set, wherein the first control speed is the speed of the first unfolding device for conveying the textile to be tested; laying the initial image acquisition device and the position detection device according to the laying result of the first unfolding device; when the position detection device detects a signal of the textile to be detected, generating a detection signal, setting acquisition control parameters of the initial image acquisition device according to the first control speed and the detection signal, and controlling image acquisition of the textile to be detected based on the acquisition control parameters to obtain an initial image acquisition set; performing image initial processing on the initial image acquisition set to obtain a processed image set, and performing feature recognition on the processed image set to obtain a feature recognition result; constructing an identification coordinate system based on the acquisition control parameters, and carrying out coordinate restoration based on the image information, the textile information and the identification coordinate system corresponding to the feature identification result to obtain feature positioning coordinates; conveying the textile to be tested to a second unfolding device, wherein the second unfolding device has a second control speed, and the second control speed is less than the first control speed; and acquiring the images of the textiles to be detected by the retest image acquisition device based on the characteristic positioning coordinates and the second control speed, and generating a quality detection result of the textiles to be detected based on a retest image acquisition result. The technical problems that in the prior art, the accuracy of the quality detection result of the textile product is low, the detection efficiency is low, and the real-time quality detection visualization cannot be realized are solved, so that the quality detection precision of the textile product is improved under the condition of improving the detection efficiency, the use requirement of a consumer on the textile product is met, and the technical effect of providing direction for the research and development and improvement of the textile product is achieved.
2. According to the embodiment of the application, after the acquisition control parameters of the initial image acquisition device are obtained according to the first control speed of the first unfolding device and the detection signals when the textile is detected by the position detection device, the identification coordinate system is established based on the acquisition control parameters, the identification coordinate system is the identification coordinate system of the textile to be detected on the first unfolding device by the initial image acquisition device, the characteristic positioning coordinates are obtained by performing coordinate restoration on the image information, the textile information and the identification coordinate system corresponding to the characteristic identification result, and the characteristic positioning coordinates are real coordinates corresponding to different positions of the textile and provide basis for the arrangement of the subsequent retest image acquisition device.
3. In order to prevent the influence of first expansion device to the fabrics that await measuring expansion state in the embodiment of this application, and then influence the characteristic identification of follow-up fabrics that await measuring, detect the expansion effect of first expansion device, when having unsatisfied anticipated expansion evaluation threshold value part in the expansion evaluation result, generate unusual expansion identification instruction, according to unusual expansion identification instruction carries out the retest sign of the fabrics that await measuring generates expansion control feedback information, reaches and fully expands the fabrics that await measuring, and then does abundant preparation for follow-up image acquisition, reduces the influence of first expansion device to image acquisition, improves the purpose to the fabrics image acquisition's that awaits measuring accuracy.
Example two
Based on the same inventive concept as the quality control method of an intelligent visual textile product in the foregoing embodiment, as shown in fig. 4, the present application provides a quality control system of an intelligent visual textile product, the system including:
the system comprises an information acquisition module 100, a first expansion device and a second expansion device, wherein the information acquisition module 100 is used for acquiring textile information, arranging the first expansion device according to the textile information and setting a first control speed, and the first control speed is the speed of the first expansion device for conveying a textile to be tested;
a device laying module 200, wherein the device laying module 200 is used for laying an initial image acquisition device and a position detection device according to the first unfolding device laying result;
an initial image acquisition module 300, where the initial image acquisition module 300 is configured to generate a detection signal when the position detection device detects a signal of the textile to be detected, set an acquisition control parameter of the initial image acquisition device according to the first control speed and the detection signal, and control image acquisition of the textile to be detected based on the acquisition control parameter to obtain an initial image acquisition set;
the image feature recognition module 400 is configured to perform initial image processing on the initial image collection set to obtain a processed image set, and perform feature recognition on the processed image set to obtain a feature recognition result;
a feature positioning coordinate obtaining module 500, where the feature positioning coordinate obtaining module 500 is configured to construct an identification coordinate system based on the acquisition control parameter, and perform coordinate restoration based on the image information corresponding to the feature identification result, the textile information, and the identification coordinate system to obtain a feature positioning coordinate;
the textile conveying module 600 is used for conveying the textile to be tested to a second unfolding device, the second unfolding device has a second control speed, and the second control speed is smaller than the first control speed;
a quality detection result generating module 700, where the quality detection result generating module 700 is configured to perform image acquisition on the to-be-detected textile by using a retest image acquisition device based on the feature positioning coordinates and the second control speed, and generate a quality detection result of the to-be-detected textile based on a retest image acquisition result.
Further, the feature location coordinate acquiring module 500 in the system is further configured to:
constructing a single image effective interval according to the acquisition control parameters;
constructing the identification coordinate system for the single image effective interval, wherein the identification coordinate system is a two-dimensional rectangular coordinate system;
performing feature coordinate recognition of the recognition coordinate system based on the feature recognition result to obtain a coordinate recognition result, wherein the coordinate recognition result comprises an abscissa recognition result and an ordinate recognition result;
acquiring image label information corresponding to the feature identification result, and updating the ordinate identification result based on the image label information, the single-image effective interval and the textile information to acquire an updated ordinate identification result;
and obtaining the feature positioning coordinate based on the updated ordinate recognition result and the abscissa recognition result.
Further, the quality detection result generation module 700 in the system is further configured to:
laying the retest image acquisition devices based on the characteristic positioning coordinates, and recording the laying coordinates;
setting retest acquisition control parameters of the retest image acquisition device based on the layout coordinates, the feature positioning coordinates and the second control speed;
and controlling the retest image acquisition device to acquire the images of the textiles to be detected through the retest acquisition control parameters to obtain a retest image acquisition result.
Further, the system further comprises:
the unfolding evaluation module is used for carrying out unfolding evaluation on the textile to be tested on the initial image acquisition set to obtain an unfolding evaluation result;
an abnormal expansion identification instruction generation module, configured to generate an abnormal expansion identification instruction when a part that does not meet an expected expansion evaluation threshold exists in the expansion evaluation result;
the feedback information generation module is used for re-detecting the identification of the textile to be detected according to the abnormal unfolding identification instruction and generating unfolding control feedback information;
and the control optimization module is used for re-detecting the textile to be detected based on the re-detection identification and performing control optimization on the unfolded textile of the first unfolding device based on the unfolding control feedback information.
Further, the system further comprises:
the characteristic identification result judging module is used for judging whether the characteristic identification result is an identification result with abnormal characteristics;
abnormal-free distribution module, abnormal-free distribution module is used for working as when the characteristic identification result is the identification result without abnormal characteristics, then pass through first expansion device will the fabrics that await measuring shunts to the abnormal assembly line that does not have of detection to will detect normal product count and increase one.
Further, the system further comprises:
the abnormality processing module is used for shunting the textile to be tested to the second unfolding device through the first unfolding device when the characteristic identification result is an identification result with abnormal characteristics;
and the shunting first sub-module is used for shunting the textile to be detected to a detection non-abnormal assembly line through the second unfolding device and adding one to the count of the detected normal products when the quality detection result is the identification result without abnormal characteristics.
Further, the system further comprises:
the abnormity processing sub-module is used for generating abnormity identification information according to the abnormity characteristics when the quality detection result is the identification result with the abnormity characteristics;
and the shunting second sub-module is used for performing classified exception counting based on the exception identification information, and shunting the textile to be detected to an exception assembly line corresponding to the classified exception counting through the second unfolding device.
For a specific working process of the module disclosed in the above embodiment of the present application, reference may be made to the content of the corresponding method embodiment, which is not described herein again.
Those skilled in the art can make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A quality control method of an intelligent visual textile product is characterized in that the method is applied to a quality detection system which is in communication connection with a first unfolding device, a second unfolding device, a position detection device, an initial image acquisition device and a retest image acquisition device, and the method comprises the following steps:
collecting textile information, arranging the first unfolding device according to the textile information, and setting a first control speed, wherein the first control speed is the speed of the first unfolding device for conveying the textile to be tested;
laying the initial image acquisition device and the position detection device according to the laying result of the first unfolding device;
when the position detection device detects a signal of the textile to be detected, generating a detection signal, setting acquisition control parameters of the initial image acquisition device according to the first control speed and the detection signal, and controlling image acquisition of the textile to be detected based on the acquisition control parameters to obtain an initial image acquisition set;
performing image initial processing on the initial image acquisition set to obtain a processed image set, and performing feature recognition on the processed image set to obtain a feature recognition result;
constructing an identification coordinate system based on the acquisition control parameters, and performing coordinate restoration based on the image information, the textile information and the identification coordinate system corresponding to the feature identification result to obtain feature positioning coordinates;
conveying the textile to be tested to the second unfolding device, wherein the second unfolding device has a second control speed, and the second control speed is lower than the first control speed;
and acquiring the images of the textiles to be detected by the retest image acquisition device based on the characteristic positioning coordinates and the second control speed, and generating a quality detection result of the textiles to be detected based on a retest image acquisition result.
2. The method of claim 1, wherein the method further comprises:
constructing a single image effective interval according to the acquisition control parameters;
constructing the identification coordinate system for the single image effective interval, wherein the identification coordinate system is a two-dimensional rectangular coordinate system;
identifying the characteristic coordinates of the identification coordinate system based on the characteristic identification result to obtain a coordinate identification result, wherein the coordinate identification result comprises an abscissa identification result and an ordinate identification result;
acquiring image label information corresponding to the feature identification result, and updating the ordinate identification result based on the image label information, the single-image effective interval and the textile information to acquire an updated ordinate identification result;
and obtaining the feature positioning coordinate based on the updated ordinate recognition result and the abscissa recognition result.
3. The method of claim 1, wherein the method further comprises:
laying the retest image acquisition devices based on the characteristic positioning coordinates, and recording the laying coordinates;
setting retest acquisition control parameters of the retest image acquisition device based on the layout coordinates, the feature positioning coordinates and the second control speed;
and controlling the retest image acquisition device to acquire the images of the textiles to be detected through the retest acquisition control parameters to obtain a retest image acquisition result.
4. The method of claim 3, wherein the method further comprises:
performing expansion evaluation on the textile to be tested on the initial image acquisition set to obtain an expansion evaluation result;
when the part which does not meet the expected expansion evaluation threshold exists in the expansion evaluation result, generating an abnormal expansion identification instruction;
re-detecting and marking the textile to be detected according to the abnormal unfolding marking instruction, and generating unfolding control feedback information;
and re-detecting the textile to be detected based on the re-detection identification, and performing control optimization on the unfolded textile of the first unfolding device based on the unfolding control feedback information.
5. The method of claim 1, wherein the method further comprises:
judging whether the feature identification result is an identification result with abnormal features;
and when the characteristic identification result is the identification result without abnormal characteristics, shunting the textile to be detected to a detection non-abnormal production line through the first unfolding device, and adding one to the count of the detected normal products.
6. The method of claim 5, wherein the method further comprises:
when the characteristic identification result is an identification result with abnormal characteristics, shunting the textile to be tested to the second unfolding device through the first unfolding device;
and when the quality detection result is the identification result without abnormal characteristics, shunting the textile to be detected to a detection non-abnormal production line through the second unfolding device, and adding one to the count of the detected normal products.
7. The method of claim 6, wherein the method further comprises:
when the quality detection result is an identification result with abnormal characteristics, generating abnormal identification information according to the abnormal characteristics;
and performing classified abnormal counting based on the abnormal identification information, and shunting the textile to be detected to an abnormal assembly line corresponding to the classified abnormal counting through the second unfolding device.
8. A quality control system for intelligently visualizing textile products, the system comprising:
the system comprises an information acquisition module, a first expansion device and a second expansion device, wherein the information acquisition module is used for acquiring textile information, arranging the first expansion device according to the textile information and setting a first control speed, and the first control speed is the speed of the first expansion device for conveying a textile to be tested;
the device laying module is used for laying an initial image acquisition device and a position detection device according to the first unfolding device laying result;
the initial image acquisition module is used for generating a detection signal when the position detection device detects a signal of the textile to be detected, setting acquisition control parameters of the initial image acquisition device according to the first control speed and the detection signal, and controlling image acquisition of the textile to be detected based on the acquisition control parameters to obtain an initial image acquisition set;
the image characteristic identification module is used for carrying out image initial processing on the initial image acquisition set to obtain a processed image set, and carrying out characteristic identification on the processed image set to obtain a characteristic identification result;
the characteristic positioning coordinate acquisition module is used for constructing an identification coordinate system based on the acquisition control parameters, and carrying out coordinate restoration based on the image information, the textile information and the identification coordinate system corresponding to the characteristic identification result to obtain a characteristic positioning coordinate;
the textile conveying module is used for conveying the textile to be tested to a second unfolding device, the second unfolding device has a second control speed, and the second control speed is smaller than the first control speed;
and the quality detection result generation module is used for acquiring the images of the textiles to be detected through the retest image acquisition device on the basis of the characteristic positioning coordinates and the second control speed, and generating the quality detection result of the textiles to be detected on the basis of the retest image acquisition result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211121217.9A CN115201211A (en) | 2022-09-15 | 2022-09-15 | Quality control method and system for intelligent visual textile product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211121217.9A CN115201211A (en) | 2022-09-15 | 2022-09-15 | Quality control method and system for intelligent visual textile product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115201211A true CN115201211A (en) | 2022-10-18 |
Family
ID=83572628
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211121217.9A Pending CN115201211A (en) | 2022-09-15 | 2022-09-15 | Quality control method and system for intelligent visual textile product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115201211A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115421465A (en) * | 2022-10-31 | 2022-12-02 | 北京聚新工程技术有限公司 | Optimized self-adaptive control method and system for textile equipment |
| CN116309492A (en) * | 2023-03-24 | 2023-06-23 | 江苏牛掌柜科技有限公司 | Linen evaluation method and system based on Internet of things |
| CN116428972A (en) * | 2023-01-29 | 2023-07-14 | 平湖市凯鑫塑业股份有限公司 | On-line detection method and system for quality of luggage fittings |
| CN116966332A (en) * | 2023-09-22 | 2023-10-31 | 南通亚壹生物科技有限公司 | Textile automatic sterilization method and system based on intelligent recognition |
| CN117147699A (en) * | 2023-10-31 | 2023-12-01 | 江苏蓝格卫生护理用品有限公司 | Medical non-woven fabric detection method and system |
| CN118150576A (en) * | 2024-03-11 | 2024-06-07 | 苏州楚硕汽车科技有限公司 | Appearance defect detection device for new energy automobile trim |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105867197A (en) * | 2016-05-31 | 2016-08-17 | 广东溢达纺织有限公司 | Automatic textile material sorting, sticking and receiving device and method |
| CN106918600A (en) * | 2017-04-07 | 2017-07-04 | 江苏博虏智能科技有限公司 | A kind of web surface defects detection and labeling method based on machine vision |
| CN107044987A (en) * | 2017-04-07 | 2017-08-15 | 江苏博虏智能科技有限公司 | A kind of web surface defects detection unit and its characterization processes |
| CN107064160A (en) * | 2017-04-01 | 2017-08-18 | 佛山市南海天富科技有限公司 | The textile surface flaw detection method and system detected based on conspicuousness |
| CN108301182A (en) * | 2017-12-22 | 2018-07-20 | 真玫智能科技（深圳）有限公司 | Intelligent cloth inspecting machine and control method applied to the intelligence cloth inspecting machine |
| CN109580645A (en) * | 2018-12-20 | 2019-04-05 | 深圳灵图慧视科技有限公司 | Defects identification equipment |
| CN111784691A (en) * | 2020-07-27 | 2020-10-16 | 泉州迈斯特新材料科技有限公司 | Textile flaw detection method |
| CN213364613U (en) * | 2020-10-16 | 2021-06-04 | 青岛恒昌机器人科技有限公司 | Textile quality detection robot |
| CN214107924U (en) * | 2020-06-19 | 2021-09-03 | 深圳拓谱信息技术有限公司 | Cloth cut-parts check out test set |
| CN113706528A (en) * | 2021-10-27 | 2021-11-26 | 南通祥元纺织有限公司 | Textile quality detection method and system based on image recognition |
| CN113866185A (en) * | 2021-12-06 | 2021-12-31 | 上海艾豚科技有限公司 | Wool top flaw detection equipment |
-
2022
- 2022-09-15 CN CN202211121217.9A patent/CN115201211A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105867197A (en) * | 2016-05-31 | 2016-08-17 | 广东溢达纺织有限公司 | Automatic textile material sorting, sticking and receiving device and method |
| CN107064160A (en) * | 2017-04-01 | 2017-08-18 | 佛山市南海天富科技有限公司 | The textile surface flaw detection method and system detected based on conspicuousness |
| CN106918600A (en) * | 2017-04-07 | 2017-07-04 | 江苏博虏智能科技有限公司 | A kind of web surface defects detection and labeling method based on machine vision |
| CN107044987A (en) * | 2017-04-07 | 2017-08-15 | 江苏博虏智能科技有限公司 | A kind of web surface defects detection unit and its characterization processes |
| CN108301182A (en) * | 2017-12-22 | 2018-07-20 | 真玫智能科技（深圳）有限公司 | Intelligent cloth inspecting machine and control method applied to the intelligence cloth inspecting machine |
| CN109580645A (en) * | 2018-12-20 | 2019-04-05 | 深圳灵图慧视科技有限公司 | Defects identification equipment |
| CN214107924U (en) * | 2020-06-19 | 2021-09-03 | 深圳拓谱信息技术有限公司 | Cloth cut-parts check out test set |
| CN111784691A (en) * | 2020-07-27 | 2020-10-16 | 泉州迈斯特新材料科技有限公司 | Textile flaw detection method |
| CN213364613U (en) * | 2020-10-16 | 2021-06-04 | 青岛恒昌机器人科技有限公司 | Textile quality detection robot |
| CN113706528A (en) * | 2021-10-27 | 2021-11-26 | 南通祥元纺织有限公司 | Textile quality detection method and system based on image recognition |
| CN113866185A (en) * | 2021-12-06 | 2021-12-31 | 上海艾豚科技有限公司 | Wool top flaw detection equipment |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115421465A (en) * | 2022-10-31 | 2022-12-02 | 北京聚新工程技术有限公司 | Optimized self-adaptive control method and system for textile equipment |
| CN115421465B (en) * | 2022-10-31 | 2023-01-17 | 北京聚新工程技术有限公司 | Optimized self-adaptive control method and system for textile equipment |
| CN116428972A (en) * | 2023-01-29 | 2023-07-14 | 平湖市凯鑫塑业股份有限公司 | On-line detection method and system for quality of luggage fittings |
| CN116428972B (en) * | 2023-01-29 | 2024-02-06 | 平湖市凯鑫塑业股份有限公司 | On-line detection method and system for quality of luggage fittings |
| CN116309492A (en) * | 2023-03-24 | 2023-06-23 | 江苏牛掌柜科技有限公司 | Linen evaluation method and system based on Internet of things |
| CN116966332A (en) * | 2023-09-22 | 2023-10-31 | 南通亚壹生物科技有限公司 | Textile automatic sterilization method and system based on intelligent recognition |
| CN116966332B (en) * | 2023-09-22 | 2023-12-01 | 南通亚壹生物科技有限公司 | Textile automatic sterilization method and system based on intelligent recognition |
| CN117147699A (en) * | 2023-10-31 | 2023-12-01 | 江苏蓝格卫生护理用品有限公司 | Medical non-woven fabric detection method and system |
| CN117147699B (en) * | 2023-10-31 | 2024-01-02 | 江苏蓝格卫生护理用品有限公司 | Medical non-woven fabric detection method and system |
| CN118150576A (en) * | 2024-03-11 | 2024-06-07 | 苏州楚硕汽车科技有限公司 | Appearance defect detection device for new energy automobile trim |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115201211A (en) | Quality control method and system for intelligent visual textile product | |
| CN107483014B (en) | A kind of photovoltaic panel failure automatic detection method | |
| CN102879401B (en) | Method for automatically detecting and classifying textile flaws based on pattern recognition and image processing | |
| CN108364291A (en) | Grey cloth rapid detection method based on computer vision technique | |
| CN109993094A (en) | Fault in material intelligent checking system and method based on machine vision | |
| CN105701476A (en) | Machine vision-based automatic identification system and method for production line products | |
| CN109881356B (en) | Hosiery machine knitting needle online detection device and method based on SVM image classification | |
| CN109672863A (en) | A kind of construction personnel's safety equipment intelligent monitoring method based on image recognition | |
| CN105973148A (en) | Pen point appearance size standardization detection system based on machine vision | |
| CN106056597A (en) | Object visual detection method and device | |
| CN111539276A (en) | Method for detecting safety helmet in real time in power scene | |
| CN107578041A (en) | A kind of detecting system | |
| CN106248680A (en) | A kind of engine commutator quality detecting system based on machine vision and detection method | |
| CN107704882A (en) | A kind of kinds of laundry recognition methods and system based on digital image processing techniques | |
| CN108921840A (en) | Display screen peripheral circuit detection method, device, electronic equipment and storage medium | |
| CN115144399B (en) | Assembly quality detection method and device based on machine vision | |
| CN114155610A (en) | Panel assembly key action identification method based on upper half body posture estimation | |
| CN110009019A (en) | Magnetic material crackle intelligent checking system and method | |
| CN106650735B (en) | A kind of LED character automatic positioning recognition methods | |
| CN111767826A (en) | Timing fixed-point scene abnormity detection method | |
| CN109137448B (en) | Intelligent fabric pattern arranging and weft straightening system based on machine vision | |
| CN112528855B (en) | Electric power operation dressing standard identification method and device | |
| CN113780224B (en) | Unmanned inspection method and system for transformer substation | |
| CN104731324A (en) | Gesture inner plane rotating detecting model generating method based on HOG+SVM framework | |
| CN114897056A (en) | Pump superposition fault detection method and system based on knowledge graph |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221018 |