CN116630233A - Glass defect detection method, device, computer equipment and storage medium - Google Patents

Glass defect detection method, device, computer equipment and storage medium Download PDF

Info

Publication number
CN116630233A
CN116630233A CN202310405172.6A CN202310405172A CN116630233A CN 116630233 A CN116630233 A CN 116630233A CN 202310405172 A CN202310405172 A CN 202310405172A CN 116630233 A CN116630233 A CN 116630233A
Authority
CN
China
Prior art keywords
glass
defect
image
detected
module
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
Application number
CN202310405172.6A
Other languages
Chinese (zh)
Inventor
闫强帅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Kaihong Digital Industry Development Co Ltd
Original Assignee
Shenzhen Kaihong Digital Industry Development Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Kaihong Digital Industry Development Co Ltd filed Critical Shenzhen Kaihong Digital Industry Development Co Ltd
Priority to CN202310405172.6A priority Critical patent/CN116630233A/en
Publication of CN116630233A publication Critical patent/CN116630233A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/0008—Industrial image inspection checking presence/absence
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • 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
    • B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
    • B07C2501/0072—Sorting of glass
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P40/00—Technologies relating to the processing of minerals
    • Y02P40/50—Glass production, e.g. reusing waste heat during processing or shaping
    • Y02P40/57—Improving the yield, e-g- reduction of reject rates

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Quality & Reliability (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The application relates to the technical field of glass detection, and particularly discloses a glass defect detection method, a device, computer equipment and a storage medium. The method comprises the following steps: transmitting the glass to be detected to an image acquisition module to obtain an image to be processed; processing the image to be processed, and identifying based on a glass defect identification algorithm to obtain an identification result; if the defect exists, the position, the type and the size of the defect are obtained, and the defect grade is determined; the glass is conveyed to a position corresponding to the grade. The method can collect an image to be processed through the image collecting module, preprocess the image and identify defects through the image processing algorithm and the glass defect identifying algorithm, determine whether the glass to be detected has defects, obtain relevant data of the defects when the defects exist, determine defect grades, and transmit the glass to corresponding storage positions according to the defect grades, so that the terminal equipment centralized control detecting equipment is realized to detect and classify the defects of the glass, and the detecting efficiency is improved.

Description

Glass defect detection method, device, computer equipment and storage medium
Technical Field
The present application relates to the field of glass detection technologies, and in particular, to a method and apparatus for detecting glass defects, a computer device, and a storage medium.
Background
When the glass has defects such as scratches, stains, bubbles, defects and the like, the positions of the defects and the types of the defects on the glass can be judged visually, but the defects have larger limitations and lower efficiency. With the continuous development of machine learning and image processing technologies, the current glass defect condition can be judged through a glass defect detection product, and meanwhile, the identified image information with the defect information and other data are transmitted to a display device for display for an operator to check. However, the existing glass defect detection products are generally complete machine products, the display module and the detection module exist in one device, and when a plurality of glass defect detection devices exist, operators are required to operate a large amount of devices at the same time, so that the workload is increased, the detection efficiency is reduced, and therefore, how to improve the efficiency of glass defect detection becomes a problem to be solved.
Disclosure of Invention
The application provides a glass defect detection method, a device, computer equipment and a storage medium, so as to improve the efficiency of glass defect detection.
In a first aspect, the present application provides a method for detecting glass defects, the method comprising:
the glass transmission module transmits glass to be detected to the image acquisition module, and the image acquisition module acquires an image to be processed of the glass to be detected;
the image processing module processes the image to be processed based on the image processing algorithm to obtain a preprocessed image, and recognizes the preprocessed image based on the glass defect recognition algorithm to obtain a recognition result;
when the identification result shows that the glass to be detected has defects, the terminal equipment acquires a defect position, a defect type and a defect size based on the identification result, determines a defect grade of the glass to be detected based on the defect position, the defect type and the defect size, and transmits the glass to be detected to a storage position corresponding to the defect grade by the glass transmission module.
Further, the glass conveying module conveys glass to be detected to an image acquisition module, and the image acquisition module acquires an image to be processed of the glass to be detected, and the glass conveying module comprises:
the glass conveying module conveys the glass to be detected to the image acquisition module according to a preset speed;
when the glass to be detected reaches the image acquisition module, the light module starts light according to an illumination mode;
based on the preset speed, the image acquisition module controls the image pickup device to acquire the image of the glass to be detected, and the image to be processed is obtained.
Further, when the glass to be detected reaches the image acquisition module, before the light module starts the light according to the illumination mode, the method further comprises:
the terminal equipment obtains the glass shape, the glass type and the preset speed of the glass to be detected, and generates an illumination mode of the light module based on the shape and the glass type of the glass to be detected.
Further, based on the preset speed, the image acquisition module controls the image capturing device to acquire an image of the glass to be detected, and obtains the image to be processed, including:
the terminal equipment obtains the image acquisition time and the image acquisition frequency of the camera equipment based on the transmission distance and the preset speed;
the image acquisition module controls the image pickup device to acquire the image to be processed based on the image acquisition time and the image acquisition frequency.
Further, the method for identifying the glass defect based on the glass defect identification algorithm, before obtaining the identification result, further includes:
training the pre-training algorithm based on the defect glass and the defect condition of the defect glass to obtain the recognition accuracy of the pre-training algorithm for recognizing the defect;
and when the identification accuracy is greater than a preset accuracy threshold, determining the pre-training algorithm as the glass defect identification algorithm.
Further, when the identification result indicates that the glass to be detected has a defect, the terminal device obtains a defect position, a defect type and a defect size based on the identification result, including:
the terminal equipment receives and stores the identification result sent by the image processing module, analyzes the identification result, and obtains the defect position, the defect type and the defect size of the glass to be detected for the user to check.
Further, determining a defect level of the glass to be inspected based on the defect location, the defect type, and the defect size includes:
the terminal equipment obtains a defect index of the glass to be detected according to a preset weight coefficient, the defect position, the defect type and the defect size;
and the terminal equipment obtains the defect grade based on a preset defect grade comparison table and the defect index.
In a second aspect, the present application also provides a glass defect detection apparatus, the apparatus comprising:
the glass transmission module is used for transmitting the glass to be detected to the image acquisition module, and the image acquisition module acquires the image to be processed of the glass to be detected;
the recognition result obtaining module is used for processing the image to be processed based on the image processing algorithm to obtain a preprocessed image, and recognizing the preprocessed image based on the glass defect recognition algorithm to obtain a recognition result;
the terminal equipment is used for acquiring a defect position, a defect type and a defect size based on the identification result when the identification result shows that the glass to be detected has defects, and determining the defect grade of the glass to be detected based on the defect position, the defect type and the defect size;
and the glass classification module is used for conveying the glass to be detected to a storage position corresponding to the defect grade by the glass conveying module.
In a third aspect, the present application also provides a computer device comprising a memory and a processor; the memory is used for storing a computer program; the processor is used for executing the computer program and realizing the glass defect detection method when executing the computer program.
In a fourth aspect, the present application also provides a computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to implement a glass defect detection method as described above.
The application discloses a glass defect detection method, a device, computer equipment and a storage medium, wherein a glass transmission module transmits glass to be detected to an image acquisition module, and the image acquisition module acquires an image to be processed of the glass to be detected; the image processing module processes the image to be processed based on the image processing algorithm to obtain a preprocessed image, and recognizes the preprocessed image based on the glass defect recognition algorithm to obtain a recognition result; when the identification result shows that the glass to be detected has defects, the terminal equipment acquires defect positions, defect types and defect sizes based on the identification result, and determines defect grades of the glass to be detected based on the defect positions, the defect types and the defect sizes; and the glass conveying module conveys the glass to be detected to a storage position corresponding to the defect grade. The method can control the image acquisition module to acquire the image of the glass to be detected through the terminal equipment, preprocess the image and identify the defects through the image processing algorithm and the glass defect identification algorithm, determine whether the glass to be detected has defects, obtain defect positions, defect types and defect sizes of the defects when the defects exist, determine defect grades of the glass to be detected according to the defect positions, the defect types and the defect sizes, and transmit the glass to corresponding storage positions according to the defect grades, so that the terminal equipment can intensively control the glass defect detection equipment to detect and classify the defects of the glass, and the glass defect detection efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart illustrating a first embodiment of a method for detecting glass defects according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a device connection of a glass defect detection method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a defect detecting apparatus for a glass defect detecting method according to an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating an apparatus for a glass defect detection method according to an embodiment of the present application;
FIG. 5 is a flow chart illustrating a second embodiment of a method for detecting glass defects according to an embodiment of the present application;
FIG. 6 is a flow chart illustrating a third embodiment of a method for detecting glass defects according to an embodiment of the present application;
FIG. 7 is a flow chart illustrating a fourth embodiment of a method for detecting glass defects according to an embodiment of the present application;
FIG. 8 is a schematic block diagram of a glass defect detection apparatus according to an embodiment of the present application;
fig. 9 is a schematic block diagram of a computer device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.
It is to be understood that the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
The embodiment of the application provides a glass defect detection method, a glass defect detection device, computer equipment and a storage medium. The glass defect detection method can be applied to a server, and the glass defect detection equipment is controlled in a centralized manner to detect and classify the defects of the glass, so that the efficiency of glass defect detection is improved. The server may be an independent server or a server cluster.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic flow chart of a glass defect detection method according to an embodiment of the application. The glass defect detection method can be applied to a server and used for detecting and classifying the defects of the glass by controlling the glass defect detection equipment in a centralized manner, so that the efficiency of glass defect detection is improved.
As shown in fig. 1, the glass defect detection method specifically includes steps S101 to S104.
S101, the glass conveying module conveys glass to be detected to an image acquisition module, and the image acquisition module acquires an image to be processed of the glass to be detected.
In one embodiment, as shown in FIG. 2, a glass defect inspection system includes a terminal device and at least one defect inspection device, wherein for an actual glass production environment, one or more glass production lines, and thus one or more glass defect inspection devices, may be present at the same time in a glass production area. Therefore, for the environment that a plurality of glass defect devices exist at the same time, the glass defect devices can be uniformly connected to one display control terminal, namely the terminal device, so that the operation such as the running state and behavior control of all the devices is realized, the operation steps of operators are greatly reduced, and the management of all the devices can be conveniently and rapidly realized.
In one embodiment, as shown in FIG. 3, the defect detection apparatus includes an image acquisition module, an image processing module, a light module, and a glass transfer module.
In one embodiment, the transporting module mainly transports the produced glass products to the image collecting module of the glass defect detecting equipment through the production line by using the conveying device to collect the images of the glass products.
In one embodiment, the image acquisition module mainly uses one or more image acquisition devices (cameras) which are arranged in a linear manner to stably and comprehensively input all image data of the glass product within a certain period of time, so that the image processing module can conveniently judge the type and position location of the defect according to the acquired image data.
In one embodiment, the illumination module mainly provides basic ambient illumination for a certain closed environment image acquisition module, so that the image acquisition module can acquire high-quality glass image information.
In one embodiment, the image processing module mainly adopts a processor carrying a preset operation system with a glass defect recognition algorithm and an image processing algorithm, and is responsible for obtaining whether the picture has defect information such as glass defects, defect size, defect position and the like according to the glass image data acquired by the image acquisition module. And the module can send data to terminal equipment carrying a preset operating system or receive corresponding control instructions from the terminal equipment through a network, and transmits instruction information to other modules.
In one embodiment, the display control terminal, i.e. the terminal device, receives the processing result data of the image processing module and displays the processing result data to the operator, and provides a visual operation interface for the operator to facilitate the operator to set the control parameters of each module, and adjust the device state to achieve the situation required by the operator.
In one embodiment, as shown in fig. 4, the transmission module sends the glass product to be detected to the image acquisition module at a constant speed according to a set speed, meanwhile, the light module is turned on and adjusted to a proper brightness according to an illumination mode, and when the glass product enters the image acquisition module, the camera starts to acquire pictures according to a set frame rate, so as to obtain the image to be processed of the glass product.
S102, the image processing module processes the image to be processed based on the image processing algorithm to obtain a preprocessed image, and recognizes the preprocessed image based on the glass defect recognition algorithm to obtain a recognition result.
Based on the glass defect recognition algorithm, recognizing the preprocessed image, and before obtaining a recognition result, further comprising: training the pre-training algorithm based on the defect glass and the defect condition of the defect glass to obtain the recognition accuracy of the pre-training algorithm for recognizing the defect; and when the identification accuracy is greater than a preset accuracy threshold, determining the pre-training algorithm as the glass defect identification algorithm.
When the identification result is that the glass to be detected has defects, the terminal equipment acquires the defect positions, the defect types and the defect sizes based on the identification result, and the method comprises the following steps: the terminal equipment receives and stores the identification result sent by the image processing module, analyzes the identification result, and obtains the defect position, the defect type and the defect size of the glass to be detected for the user to check.
In one embodiment, the image acquisition module sequentially sends images to the image processing module according to the time sequence and the position sequence of photographing, and the image processing module firstly processes the images to be processed according to an image processing algorithm, so that the images are clearer, and the accuracy of defect identification is improved.
In one embodiment, the pre-training algorithm is trained by acquiring enough glass defect pictures with different defects in advance, and the current algorithm is determined as a glass defect recognition algorithm when the recognition accuracy of the algorithm reaches a preset accuracy threshold.
In one embodiment, after preprocessing an image to be processed, inputting the preprocessed image after processing into a glass defect recognition algorithm to obtain position information, type information and size information of defects in each picture, and summarizing all image recognition data of the glass product to obtain all glass defect data information of the glass product.
And S103, when the identification result shows that the glass to be detected has defects, the terminal equipment acquires defect positions, defect types and defect sizes based on the identification result, and determines defect grades of the glass to be detected based on the defect positions, the defect types and the defect sizes.
In one embodiment, the terminal device obtains the defect grade of the glass to be detected according to a preset defect grade comparison table, and visually displays all data information of the glass to be detected, so that an operator can conveniently obtain the processing data of the device in real time.
In one embodiment, a defect value corresponding to the defect position of the glass to be detected can be obtained according to the defect position comparison table and the defect position of the glass to be detected, a defect value corresponding to the defect type is obtained according to the defect type comparison table, and a defect value corresponding to the defect size is obtained according to the defect size comparison table.
In one embodiment, the defect index of the glass to be detected may be obtained by giving corresponding weights to the defect position, the defect type, and the defect size according to the degree of importance.
In one embodiment, according to a preset defect level comparison table, a defect level corresponding to the defect index is obtained as the defect level of the glass to be detected currently.
And S104, the glass conveying module conveys the glass to be detected to a storage position corresponding to the defect grade.
In one embodiment, the current glass is sent to different processing paths through the glass conveying module according to the defect grade of the glass to be detected obtained by the terminal equipment. For example, glass products having the same defect level are sent to one storage location, and all glass products having a defect level of 1 are sent to one storage location.
Referring to fig. 5, fig. 5 is a schematic flow chart of a glass defect detection method according to an embodiment of the application. The glass defect detection method can be applied to a server and used for detecting and classifying the defects of the glass by controlling the glass defect detection equipment in a centralized manner, so that the efficiency of glass defect detection is improved.
As shown in fig. 5, the step S101 of the glass defect detecting method specifically includes steps S201 to S203.
S201, the glass conveying module conveys the glass to be detected to the image acquisition module according to a preset speed;
s202, when the glass to be detected reaches the image acquisition module, the light module starts light according to an illumination mode;
and S203, based on the preset speed, the image acquisition module controls the image pickup device to acquire the image of the glass to be detected, and the image to be processed is obtained.
When the glass to be detected reaches the image acquisition module, before the light module starts light according to the illumination mode, the method further comprises the following steps: the terminal equipment obtains the glass shape, the glass type and the preset speed of the glass to be detected, and generates an illumination mode of the light module based on the shape and the glass type of the glass to be detected.
In one embodiment, since the shapes and types of the glass products are not necessarily the same, in order for the lighting module to illuminate the glass to be inspected in all aspects, the illumination pattern will vary with the shape of the glass to be inspected. For example, planar glass only needs to be illuminated in one direction, while circular glass needs to be illuminated from a different direction. For example, unidirectional glass has a color that differs from that of ordinary glass, and thus, the brightness of the lamp light also needs to be changed correspondingly for different types of glass.
In one embodiment, the transmission module sends the glass product to be detected to the image acquisition module at a constant speed according to a set speed, meanwhile, the light module is turned on and adjusted to a proper brightness according to an illumination mode, and when the glass product enters the image acquisition module, the camera starts to acquire pictures according to a set frame rate, so that a to-be-processed image of the glass product is obtained.
Referring to fig. 6, fig. 6 is a schematic flow chart of a glass defect detection method according to an embodiment of the application. The glass defect detection method can be applied to a server and used for detecting and classifying the defects of the glass by controlling the glass defect detection equipment in a centralized manner, so that the efficiency of glass defect detection is improved.
As shown in fig. 6, the step S203 of the glass defect detecting method specifically includes steps S301 to S302.
S301, the terminal equipment obtains the image acquisition time and the image acquisition frequency of the camera equipment based on the transmission distance and the preset speed;
s302, the image acquisition module controls the image pickup device to acquire the image to be processed based on the image acquisition time and the image acquisition frequency.
In one embodiment, the transmission device is guaranteed to run at a constant speed, then one or more cameras are used for guaranteeing that information in the longitudinal direction of the glass can be completely collected at the same time, so that the collection frequency of the image collection device is reset, the place where the next collection starts is guaranteed to be just the place where the last collection range ends, and the integrity of the image to be processed, which is collected by the glass to be detected, is guaranteed.
In one embodiment, the time when the glass to be detected arrives at the image acquisition module can be obtained according to the preset conveying speed and conveying distance, the time is taken as the time when the image acquisition device starts to work, and the image capturing equipment is not necessarily concentrated at a certain position, so that the resource waste such as electric quantity and the like caused by the fact that the equipment is started for a long time can be avoided according to the fact that the certain image capturing equipment is correspondingly started when the glass to be detected arrives at the position of the image capturing equipment.
In one embodiment, one image capturing device may be responsible for capturing images of more than one portion, for example, a certain image capturing device may rotate by an angle, so that two portions of the glass product to be detected may be continuously captured to the greatest extent, and therefore, the image capturing frequency of the image capturing device needs to be determined according to the moving speed of the glass product, so as to ensure that the image capturing device can complete capturing.
Referring to fig. 7, fig. 7 is a schematic flow chart of a glass defect detection method according to an embodiment of the application. The glass defect detection method can be applied to a server and used for detecting and classifying the defects of the glass by controlling the glass defect detection equipment in a centralized manner, so that the efficiency of glass defect detection is improved.
As shown in fig. 7, the glass defect detection method specifically includes steps S401 to S402.
S401, the terminal equipment obtains a defect index of the glass to be detected according to a preset weight coefficient, the defect position, the defect type and the defect size;
s402, the terminal equipment obtains the defect grade based on a preset defect grade comparison table and the defect index.
In one embodiment, a defect value corresponding to a defect position of the glass to be detected can be obtained according to a defect position comparison table and a defect position of the glass to be detected, a defect value corresponding to a defect type can be obtained according to a defect type comparison table, and a defect value corresponding to a defect size can be obtained according to a defect size comparison table, for example, if the defect value corresponding to the defect position is set to decrease in sequence according to the distance between the defect position and the center of the glass, the defect position of the glass is assumed to be at the center of the glass, the defect type is a scratch, and the defect value corresponding to the defect position, the defect type and the defect size can be 90, 70 and 80 respectively.
In one embodiment, the defect index of the glass to be detected may be obtained by giving corresponding weights to the defect position, the defect type and the defect size according to the importance degree, for example, the weights corresponding to the defect position, the defect type and the defect size are respectively 0.5, 0.2 and 0.3, and the defect index of the glass in the above embodiment is 90×0.5+70×0.2+80×0.3=83.
In one embodiment, according to a preset defect level comparison table, a defect level corresponding to a defect index is obtained as a defect level of the glass to be currently detected, for example, when the defect index is in the range of 0 to 30, the defect level is 1, when the defect index is in the range of 30 to 50, the defect level is 2, when the defect index is in the range of 50 to 70, the defect level is 3, when the defect index is in the range of 70 to 90, the defect level is 4, when the defect index is in the range of 90 to 100, the defect level is 5, and it is possible to set the defect level to be 3 or more as a defective product, and therefore, the defect level of the glass product with the defect index of 83 is 4.
Referring to fig. 8, fig. 8 is a schematic block diagram of a glass defect detecting apparatus for performing the glass defect detecting method according to an embodiment of the present application. The glass defect detection device can be configured on a server.
As shown in fig. 8, the glass defect detecting apparatus 500 includes:
the image to be processed obtaining module 501 is configured to transmit glass to be detected to an image acquisition module by using the glass transmission module, where the image acquisition module acquires an image to be processed of the glass to be detected;
the recognition result obtaining module 502 is configured to process the image to be processed based on the image processing algorithm by using the image processing module to obtain a preprocessed image, and recognize the preprocessed image based on the glass defect recognition algorithm to obtain a recognition result;
a defect level determining module 503, configured to, when the identification result indicates that the glass to be detected has a defect, obtain a defect position, a defect type, and a defect size based on the identification result, and determine a defect level of the glass to be detected based on the defect position, the defect type, and the defect size;
and the glass classification module 504 is used for conveying the glass to be detected to a storage position corresponding to the defect grade by the glass conveying module.
In one embodiment, the image obtaining module to be processed 501 includes:
the glass conveying unit is used for conveying the glass to be detected to the image acquisition module according to a preset speed by the glass conveying module;
the light control unit is used for starting light according to an illumination mode when the glass to be detected reaches the image acquisition module;
the image acquisition unit is used for acquiring the image of the glass to be detected based on the preset speed, and the image acquisition module is used for controlling the image pickup device to acquire the image of the glass to be detected.
In one embodiment, the image obtaining module to be processed 501 further includes:
the illumination mode obtaining unit is used for obtaining the glass shape, the glass type and the preset speed of the glass to be detected by the terminal equipment, and generating the illumination mode of the light module based on the shape and the glass type of the glass to be detected.
In one embodiment, the image obtaining unit to be processed includes:
an image acquisition instruction obtaining subunit, configured to obtain, by using the terminal device, image acquisition time and image acquisition frequency of the image capturing device based on a transmission distance and the preset speed;
the image acquisition sub-unit is used for controlling the image pickup device to acquire the image to be processed based on the image acquisition time and the image acquisition frequency.
In one embodiment, the glass defect detection apparatus 500 further includes a glass defect identification algorithm determination module, the glass defect identification algorithm determination module including:
the recognition accuracy obtaining unit is used for training the pre-training algorithm based on the defect glass and the defect condition of the defect glass to obtain the recognition accuracy of the pre-training algorithm for recognizing the defect;
and the algorithm determining unit is used for determining the pre-training algorithm as the glass defect recognition algorithm when the recognition accuracy is larger than a preset accuracy threshold.
In one embodiment, the identification result obtaining module 502 further includes:
the identification result sending unit is used for receiving and storing the identification result sent by the image processing module by the terminal equipment, analyzing the identification result, and obtaining the defect position, the defect type and the defect size of the glass to be detected for the user to check.
In one embodiment, the defect level determination module 503 includes:
a defect index obtaining unit, configured to obtain a defect index of the glass to be detected according to a preset weight coefficient, the defect position, the defect type and the defect size by using the terminal device;
the defect grade obtaining unit is used for obtaining the defect grade based on a preset defect grade comparison table and the defect index by the terminal equipment.
It should be noted that, for convenience and brevity of description, the specific working process of the apparatus and each module described above may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
The apparatus described above may be implemented in the form of a computer program which is executable on a computer device as shown in fig. 9.
Referring to fig. 9, fig. 9 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device may be a server.
With reference to FIG. 9, the computer device includes a processor, memory, and a network interface connected by a system bus, where the memory may include a non-volatile storage medium and an internal memory.
The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause a processor to perform any of a number of glass defect detection methods.
The processor is used to provide computing and control capabilities to support the operation of the entire computer device.
The internal memory provides an environment for the execution of a computer program in a non-volatile storage medium that, when executed by a processor, causes the processor to perform any of a number of glass defect detection methods.
The network interface is used for network communication such as transmitting assigned tasks and the like. It will be appreciated by persons skilled in the art that the architecture shown in fig. 9 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
It should be appreciated that the processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein in one embodiment the processor is configured to run a computer program stored in the memory to implement the steps of:
the glass transmission module transmits glass to be detected to the image acquisition module, and the image acquisition module acquires an image to be processed of the glass to be detected;
the image processing module processes the image to be processed based on the image processing algorithm to obtain a preprocessed image, and recognizes the preprocessed image based on the glass defect recognition algorithm to obtain a recognition result;
when the identification result shows that the glass to be detected has defects, the terminal equipment acquires defect positions, defect types and defect sizes based on the identification result, and determines defect grades of the glass to be detected based on the defect positions, the defect types and the defect sizes;
and the glass conveying module conveys the glass to be detected to a storage position corresponding to the defect grade.
In one embodiment, the processor is configured to, when implementing the glass transfer module to transfer glass to be detected to an image acquisition module, acquire a to-be-processed image of the glass to be detected, implement:
the glass conveying module conveys the glass to be detected to the image acquisition module according to a preset speed;
when the glass to be detected reaches the image acquisition module, the light module starts light according to an illumination mode;
based on the preset speed, the image acquisition module controls the image pickup device to acquire the image of the glass to be detected, and the image to be processed is obtained.
In one embodiment, when the glass to be detected reaches the image acquisition module, the processor is further configured to, before implementing that the light module turns on light according to an illumination mode:
the terminal equipment obtains the glass shape, the glass type and the preset speed of the glass to be detected, and generates an illumination mode of the light module based on the shape and the glass type of the glass to be detected.
In one embodiment, the processor is configured to, when implementing that the image acquisition module controls the image capturing device to acquire the image of the glass to be detected based on the preset speed, obtain the image to be processed, implement:
the terminal equipment obtains the image acquisition time and the image acquisition frequency of the camera equipment based on the transmission distance and the preset speed;
the image acquisition module controls the image pickup device to acquire the image to be processed based on the image acquisition time and the image acquisition frequency.
In one embodiment, before implementing the glass defect recognition algorithm, the processor is further configured to, before implementing the recognition on the preprocessed image to obtain a recognition result:
training the pre-training algorithm based on the defect glass and the defect condition of the defect glass to obtain the recognition accuracy of the pre-training algorithm for recognizing the defect;
and when the identification accuracy is greater than a preset accuracy threshold, determining the pre-training algorithm as the glass defect identification algorithm.
In one embodiment, when the identification result indicates that the glass to be detected has a defect, the processor is configured to, when the terminal device obtains a defect position, a defect type and a defect size based on the identification result, implement:
the terminal equipment receives and stores the identification result sent by the image processing module, analyzes the identification result, and obtains the defect position, the defect type and the defect size of the glass to be detected for the user to check.
In one embodiment, when the processor obtains the defect position, the defect type and the defect size based on the identification result, and determines the defect level of the glass to be detected based on the defect position, the defect type and the defect size, the processor is configured to implement:
the terminal equipment obtains a defect index of the glass to be detected according to a preset weight coefficient, the defect position, the defect type and the defect size;
and the terminal equipment obtains the defect grade based on a preset defect grade comparison table and the defect index.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, the computer program comprises program instructions, and the processor executes the program instructions to realize any glass defect detection method provided by the embodiment of the application.
The computer readable storage medium may be an internal storage unit of the computer device according to the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, which are provided on the computer device.
While the application has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims (10)

1. The utility model provides a glass defect detection method which characterized in that, glass defect detection method is applied to glass defect detection system, glass defect detection system includes terminal equipment and at least one defect detection equipment, defect detection equipment includes image acquisition module, image processing module, light module and glass transfer module, terminal equipment and defect detection side equipment all carry on preset operating system, terminal equipment is used for controlling at least one defect detection equipment, image processing module stores preset glass defect identification algorithm and preset image processing algorithm, glass defect detection method includes:
the glass transmission module transmits glass to be detected to the image acquisition module, and the image acquisition module acquires an image to be processed of the glass to be detected;
the image processing module processes the image to be processed based on the image processing algorithm to obtain a preprocessed image, and recognizes the preprocessed image based on the glass defect recognition algorithm to obtain a recognition result;
when the identification result shows that the glass to be detected has defects, the terminal equipment acquires defect positions, defect types and defect sizes based on the identification result, and determines defect grades of the glass to be detected based on the defect positions, the defect types and the defect sizes;
and the glass conveying module conveys the glass to be detected to a storage position corresponding to the defect grade.
2. The glass defect detection method of claim 1, wherein the glass transfer module transfers glass to be detected to an image acquisition module that acquires a to-be-processed image of the glass to be detected, comprising:
the glass conveying module conveys the glass to be detected to the image acquisition module according to a preset speed;
when the glass to be detected reaches the image acquisition module, the light module starts light according to an illumination mode;
based on the preset speed, the image acquisition module controls the image pickup device to acquire the image of the glass to be detected, and the image to be processed is obtained.
3. The method for detecting glass defects according to claim 2, wherein when the glass to be detected reaches the image acquisition module, the light module further comprises, before turning on the light according to the illumination mode:
the terminal equipment obtains the glass shape, the glass type and the preset speed of the glass to be detected, and generates an illumination mode of the light module based on the shape and the glass type of the glass to be detected.
4. The glass defect detection method according to claim 2, wherein the image acquisition module controls an image capturing device to acquire an image of the glass to be detected based on the preset speed, and the image to be processed is obtained, comprising:
the terminal equipment obtains the image acquisition time and the image acquisition frequency of the camera equipment based on the transmission distance and the preset speed;
the image acquisition module controls the image pickup device to acquire the image to be processed based on the image acquisition time and the image acquisition frequency.
5. The method for detecting glass defects according to claim 1, wherein the step of recognizing the preprocessed image based on the glass defect recognition algorithm, before obtaining the recognition result, further comprises:
training the pre-training algorithm based on the defect glass and the defect condition of the defect glass to obtain the recognition accuracy of the pre-training algorithm for recognizing the defect;
and when the identification accuracy is greater than a preset accuracy threshold, determining the pre-training algorithm as the glass defect identification algorithm.
6. The method for detecting glass defects according to claim 1, wherein when the identification result is that the glass to be detected has defects, the terminal device obtains a defect position, a defect type and a defect size based on the identification result, and the method comprises:
the terminal equipment receives and stores the identification result sent by the image processing module, analyzes the identification result, and obtains the defect position, the defect type and the defect size of the glass to be detected for the user to check.
7. The method according to any one of claims 1 to 6, wherein determining a defect level of the glass to be inspected based on the defect location, the defect type, and the defect size comprises:
the terminal equipment obtains a defect index of the glass to be detected according to a preset weight coefficient, the defect position, the defect type and the defect size;
and the terminal equipment obtains the defect grade based on a preset defect grade comparison table and the defect index.
8. A glass defect detection apparatus, comprising:
the glass transmission module is used for transmitting the glass to be detected to the image acquisition module, and the image acquisition module acquires the image to be processed of the glass to be detected;
the recognition result obtaining module is used for processing the image to be processed based on the image processing algorithm to obtain a preprocessed image, and recognizing the preprocessed image based on the glass defect recognition algorithm to obtain a recognition result;
the terminal equipment is used for acquiring a defect position, a defect type and a defect size based on the identification result when the identification result shows that the glass to be detected has defects, and determining the defect grade of the glass to be detected based on the defect position, the defect type and the defect size;
and the glass classification module is used for conveying the glass to be detected to a storage position corresponding to the defect grade by the glass conveying module.
9. A computer device, the computer device comprising a memory and a processor;
the memory is used for storing a computer program;
the processor for executing the computer program and for implementing the glass defect detection method according to any one of claims 1 to 7 when the computer program is executed.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to implement the glass defect detection method according to any one of claims 1 to 7.
CN202310405172.6A 2023-04-12 2023-04-12 Glass defect detection method, device, computer equipment and storage medium Pending CN116630233A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310405172.6A CN116630233A (en) 2023-04-12 2023-04-12 Glass defect detection method, device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310405172.6A CN116630233A (en) 2023-04-12 2023-04-12 Glass defect detection method, device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116630233A true CN116630233A (en) 2023-08-22

Family

ID=87635476

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310405172.6A Pending CN116630233A (en) 2023-04-12 2023-04-12 Glass defect detection method, device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116630233A (en)

Similar Documents

Publication Publication Date Title
CN107944504B (en) Board recognition and machine learning method and device for board recognition and electronic equipment
KR20210010541A (en) Battery detection method and device (BATTERY DETECTION METHOD AND DEVICE)
CN110659660A (en) Automatic optical detection classification device using deep learning system and training device thereof
WO2020007118A1 (en) Display screen peripheral circuit detection method and device, electronic equipment and storage medium
KR102378186B1 (en) Artificial intelligence vision inspection system for wiring harness
CN110276257B (en) Face recognition method, device, system, server and readable storage medium
KR102168724B1 (en) Method And Apparatus for Discriminating Normal and Abnormal by using Vision Inspection
US11203494B2 (en) System and method for sorting moving objects
CN111310826B (en) Method and device for detecting labeling abnormality of sample set and electronic equipment
CN115184359A (en) Surface defect detection system and method capable of automatically adjusting parameters
CN104118609A (en) Labeling quality detecting method and device
CN112711603B (en) Cloud-based workpiece detection method and system and computer-readable storage medium
CN111879781A (en) Test paper quality detection system based on machine vision
CN112712504B (en) Cloud-based workpiece detection method and system and computer-readable storage medium
CN104132945A (en) On-line surface quality visual inspection device for bar based on optical fiber conduction
CN111681220B (en) Method, device, system and storage medium for constructing defect detection model
CN111681215A (en) Convolutional neural network model training method, and workpiece defect detection method and device
CN207222383U (en) Plank sorting system
CN110751055B (en) Intelligent manufacturing system
CN113902740A (en) Construction method of image blurring degree evaluation model
JP6303219B1 (en) Image processing system and image processing method
CN116630233A (en) Glass defect detection method, device, computer equipment and storage medium
JP2019095984A (en) Image processing system
TW202209173A (en) Method for defect detection, method for defect classification and system thereof
CN102866165A (en) Surface defect detecting device of hardware

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