CN114130687A - Product visual quality inspection method, system, computer equipment and storage medium - Google Patents
Product visual quality inspection method, system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114130687A CN114130687A CN202111231933.8A CN202111231933A CN114130687A CN 114130687 A CN114130687 A CN 114130687A CN 202111231933 A CN202111231933 A CN 202111231933A CN 114130687 A CN114130687 A CN 114130687A
- Authority
- CN
- China
- Prior art keywords
- product
- sorting
- sorted
- analyzed
- image
- 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
- 230000000007 visual effect Effects 0.000 title claims abstract description 110
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000007689 inspection Methods 0.000 title claims abstract description 40
- 238000003860 storage Methods 0.000 title claims abstract description 9
- 238000004458 analytical method Methods 0.000 claims abstract description 167
- 238000012545 processing Methods 0.000 claims abstract description 67
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012800 visualization Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 description 22
- 238000001514 detection method Methods 0.000 description 16
- 238000004422 calculation algorithm Methods 0.000 description 13
- 230000033764 rhythmic process Effects 0.000 description 6
- 230000001960 triggered effect Effects 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 4
- 238000005520 cutting process Methods 0.000 description 3
- 230000002950 deficient Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- 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
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- 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
- B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
-
- 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
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to a product visual quality inspection method, a product visual quality inspection system, computer equipment and a storage medium, which are used for accelerating the quality inspection efficiency of industrial products. A product visual quality inspection method, comprising: acquiring an image of a current product to be analyzed to obtain a product image, and generating a sorting request according to the product image; performing visual analysis processing on the product image to generate a corresponding product analysis result; judging whether a product analysis result of a previous product to be analyzed is obtained or not according to the sorting request, if so, enabling the previous product to be analyzed to become a product to be sorted, generating a sorting signal of the product to be sorted according to the obtained product analysis result of the previous product to be analyzed, storing the sorting signal of the product to be sorted into a sorting signal cache queue, and obtaining a sorting signal of the current product to be sorted from the sorting signal cache queue; and performing sorting processing on the current product to be sorted according to the obtained sorting signal of the current product to be sorted.
Description
Technical Field
The invention relates to the technical field of product quality detection, in particular to a product visual quality detection method, a product visual quality detection system, computer equipment and a storage medium.
Background
With the development of computer vision technology, many enterprises have started to automatically find the defects of industrial products and perform sorting by image detection methods, and the steps are generally taken as follows: firstly, photographing an industrial product; secondly, inputting the picture into a rear-end detection algorithm for detection; and after the detection result is obtained, sorting the industrial products according to the detection result, namely uniformly placing the industrial products with the detection result of GOOD into qualified products through sorting equipment (such as a manipulator or a gate), and uniformly placing the industrial products with the detection result of NG into defective products.
The industrial product is generally pulled on a conveyor or by a gripping device (for example, for the finished zipper, the zipper head is clamped by a gripper, pulled to a fixed position and then cut by a cutting machine, so as to separate a complete independent zipper, then the gripper moves to a cutting position again, clamps the zipper head again, pulls, and so on). In the process of pulling the industrial product, the camera is used for photographing firstly, when photographing is finished, the whole conveyor belt stops running or the pulling device stops pulling the industrial product, a visual algorithm is waited for completing product analysis and obtaining an analysis result (GOOD or NG), after the analysis result is obtained, a sorting signal is sent to perform sorting processing on the industrial product moving to a sorting position, then the next industrial product is continuously conveyed or pulled, and the steps are repeated, so that the coordination and consistency of the whole production rhythm are ensured.
For the quality detection device of the existing industrial product, the total time for completing the quality detection and sorting of the industrial product is determined by the three parts of the movement speed of the industrial product, the analysis time of a visual algorithm and the reset time of a sorting device or a pulling device. The longer the total time, the lower the production efficiency, whereas if the total time can be shortened, the production efficiency is improved. Moreover, the moving speed of the industrial product is determined by the mechanical performance of the production equipment, and the time of the visual analysis is determined by the complexity of the algorithm and the calculation hardware, so that the production efficiency of introducing the visual quality inspection is lower than the original production efficiency under the condition that the visual algorithm cannot complete the analysis in real time.
Disclosure of Invention
The present invention is directed to overcoming at least one of the above-mentioned disadvantages of the prior art, and providing a method, a system, a computer device and a storage medium for visual quality inspection of a product, which are used to increase the quality inspection efficiency of an industrial product to approach the production efficiency without introducing visual quality inspection capability.
The invention adopts the technical scheme that a product visual quality inspection method comprises the following steps:
acquiring an image of a current product to be analyzed to obtain a product image, and generating a sorting request according to the product image;
performing visual analysis processing on the product image to generate a corresponding product analysis result;
judging whether a product analysis result of a last product to be analyzed is obtained or not according to the sorting request, if so, enabling the last product to be analyzed to become a product to be sorted, generating a sorting signal of the product to be sorted according to the obtained product analysis result of the last product to be analyzed, storing the sorting signal of the product to be sorted into a sorting signal cache queue, and obtaining a sorting signal of the current product to be sorted from the sorting signal cache queue;
and performing sorting processing on the current product to be sorted according to the obtained sorting signal of the current product to be sorted.
The method comprises the steps of generating a component inspection request after a product to be analyzed finishes image acquisition, triggering the sorting processing of the current product to be sorted according to the sorting request, enabling the visual analysis process and the sorting processing process of the product to be analyzed to be carried out in parallel, enabling the visual analysis time to be coincident with the sorting processing time, and eliminating the time waiting for the visual analysis of the product.
Further, the determining whether to obtain a product analysis result of the previous product to be analyzed according to the sorting request further includes:
and if not, suspending the acquisition of the sorting signal of the current product to be sorted from the sorting signal cache queue until the product analysis result of the last product to be analyzed is acquired.
Whether the product analysis result of the last product to be analyzed is acquired or not is judged according to the sorting request, if not, the sorting signal of the current product to be sorted is temporarily stopped to be acquired from the sorting signal cache queue, the sorting processing of the current product to be sorted is temporarily stopped until the product analysis result of the last product to be analyzed is acquired, then the sorting processing of the product to be sorted is executed according to the acquired product analysis result of the last product to be analyzed, the sorting processing of only one product to be sorted can be executed in advance, and the normal operation of the overall production rhythm can be ensured.
Further, still include: and displaying the quantity information of the sorting signals in the sorting signal buffer queue in real time.
When a sorting signal is obtained from the sorting signal buffer queue, the number of the sorting signals in the sorting signal buffer queue is smaller than the number of products to be analyzed which have finished image acquisition and wait for sorting, and the number of the products to be analyzed is equal at the rest moments.
Further, the acquiring an image of a product obtained by acquiring an image of a product to be analyzed and generating a sorting request according to the product image includes: after image acquisition is carried out on a current product to be analyzed to obtain a plurality of product images, whether the acquisition of all the product images is finished is judged, and if yes, a sorting request is generated according to the plurality of product images;
the generating of the corresponding product analysis result after the visual analysis processing of the product image comprises: and respectively carrying out visual analysis processing on the plurality of product images to generate a plurality of corresponding analysis results, and integrating the plurality of analysis results to generate a product analysis result corresponding to the product to be analyzed.
In the process of collecting images of products to be analyzed, sometimes a plurality of product images need to be collected to complete the analysis of one product, whether the image collection of the current products to be analyzed is completed or not is judged before visual analysis, and a sorting request is generated to trigger sorting processing after the image collection of all the products is completed, so that the visual analysis process of one product to be analyzed corresponds to the sorting processing process of one product to be sorted, and the normal running of the whole production rhythm is ensured.
When a plurality of product images of a product are subjected to visual analysis, each product image is analyzed one by one, a plurality of corresponding analysis results are obtained and then integrated into a product analysis result of a product to be analyzed, a sorting signal is generated according to the product analysis result and stored into a sorting signal cache queue, the plurality of product images are adopted to perform complete and accurate visual analysis on the product to be analyzed, the accuracy of the analysis result is improved, and the plurality of analysis results are integrated into one product analysis result to improve the sorting efficiency and the accuracy.
Further, before image acquisition is performed on a current product to be analyzed to obtain a product image, the method further comprises the following steps:
according to the distance between image acquisition equipment for acquiring images of products to be analyzed currently and sorting equipment for sorting the products to be sorted currently and the length of each product to be sorted, sorting signals of one or more products to be sorted are stored in a sorting signal cache queue in advance;
or, according to the number of products to be sorted which can be accommodated between the image acquisition equipment for acquiring images of the products to be analyzed and the sorting equipment for sorting the products to be sorted, the sorting signals of one or more products to be sorted are stored in the sorting signal buffer queue in advance.
Another technical solution adopted by the present invention is a product visual quality inspection system, comprising:
the image acquisition module is used for acquiring images of a current product to be analyzed to obtain a product image and generating a sorting request according to the product image;
the visual analysis module is connected with the image acquisition module and is used for generating a corresponding product analysis result after the product image is subjected to visual analysis processing;
the sorting control module is respectively connected with the image acquisition module and the visual analysis module and is used for judging whether a product analysis result of a last product to be analyzed is acquired according to the sorting request, if so, the last product to be analyzed becomes a product to be sorted, a sorting signal of the product to be sorted is generated according to the acquired product analysis result of the last product to be analyzed, the sorting signal of the product to be sorted is stored in a sorting signal cache queue, and the sorting signal of the current product to be sorted is acquired from the sorting signal cache queue;
and the sorting processing module is connected with the sorting control module and is used for sorting the current product to be sorted according to the obtained sorting signal of the current product to be sorted.
The visual quality inspection method comprises the steps that an image acquisition module acquires images of products to be analyzed to generate a component inspection request, and a sorting control module performs sorting processing on the products to be sorted according to the sorting request, so that the visual analysis process of the products to be analyzed by a visual analysis module is performed in parallel with the processing processes of a sorting control module and a sorting processing module, the visual analysis time is overlapped with the sorting processing time, and the waiting time for visual analysis of the products is eliminated.
Further, the sorting control module is further configured to determine whether to acquire a product analysis result of a previous product to be analyzed according to the sorting request, and if not, suspend acquiring a sorting signal of a current product to be sorted from the sorting signal cache queue until acquiring a product analysis result of the previous product to be analyzed.
Further, the system also comprises a visualization module, wherein the visualization module is used for displaying the quantity information of the sorting signals in the sorting signal buffer queue in real time.
Another technical solution adopted by the present invention is a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the product visual quality inspection method when executing the computer program.
Another technical solution adopted by the present invention is a computer-readable storage medium storing a computer program, which when executed by a processor implements the steps of the product visual quality inspection method.
Compared with the prior art, the invention has the beneficial effects that: according to the product visual quality inspection method, the system, the computer equipment and the storage medium, after the product to be analyzed finishes image acquisition, the sorting processing process is triggered through the sorting request, so that the visual analysis process and the sorting processing process of the product to be analyzed are performed in parallel, the visual analysis time is coincided with the sorting processing time, and the time waiting for the product visual analysis is eliminated, the defect that in the prior art, after all images of a product are acquired, a sorting signal is acquired from a sorting signal cache queue after the visual analysis result of the product is obtained, so that the sorting processing is triggered by the sorting signal is overcome, the visual quality inspection efficiency in industrial products is improved, and the production efficiency which is the same as that of the product without the visual quality inspection analysis after the visual quality inspection analysis is introduced is achieved; the effective utilization rate of the equipment is improved, the equipment purchasing cost is reduced, under the condition of the same load, the production efficiency of the same equipment in unit time is improved more than before, and therefore the equipment demand and the equipment purchasing cost are reduced.
Drawings
FIG. 1 is a flow chart of a visual quality inspection method for a product according to the present invention.
Fig. 2 is a structural diagram of a product visual quality inspection system according to the present invention.
Detailed Description
The drawings are only for purposes of illustration and are not to be construed as limiting the invention.
For the quality of industrial products manufactured on a production line, more and more enterprises adopt an image visual analysis technology to carry out quality detection and sorting on the products, so that an end-to-end automatic production line from raw material processing and production to rear end quality detection is realized. In a product production line, a position for photographing and visually analyzing a product is often a certain distance away from a position for actually performing sorting, and a plurality of products may be separated from the position, so that in order to distinguish the products at different positions, the product at the position for image acquisition and visual analysis is named as a current product to be analyzed, the product at the position for currently performing sorting is named as a current product to be sorted, and the product which has completed image acquisition and visual analysis and waits for sorting is named as a product to be sorted.
Because the same product has different positions in the visual analysis and sorting processing, the visual analysis result of the product to be analyzed can be cached into a sorting signal after the product to be analyzed is subjected to the visual analysis, and the sorting signal is sent out and the sorting processing is carried out when the product to be analyzed moves to the sorting position to become the current product to be sorted.
Example 1
Referring to fig. 1, fig. 1 is a flowchart illustrating a visual quality inspection method for a product according to the present embodiment, the method including:
s101, carrying out image acquisition on a current product to be analyzed to obtain a product image, and generating a sorting request according to the product image;
s102, performing visual analysis processing on the product image to generate a corresponding product analysis result;
specifically, the acquiring an image of a product obtained by acquiring an image of a product to be analyzed and generating a sorting request according to the product image includes: after image acquisition is carried out on a current product to be analyzed to obtain a plurality of product images, whether the acquisition of all the product images is finished is judged, and if yes, a sorting request is generated according to the plurality of product images;
the generating of the corresponding product analysis result after the visual analysis processing of the product image comprises: and respectively carrying out visual analysis processing on the plurality of product images to generate a plurality of corresponding analysis results, and integrating the plurality of analysis results to generate a product analysis result corresponding to the product to be analyzed.
In an actual product production line, visual analysis of a product can be realized through one or more product images, but for a product which is long or has a large area, one picture cannot cover the whole product, and a plurality of pictures are required to be shot to cover a complete product, and the analysis of the plurality of pictures can improve the accuracy of a product analysis result and sorting, so that the embodiment can install a plurality of industrial cameras at the acquisition position of the product image so as to cover the shooting of the whole product, respectively execute the visual analysis of each product image according to the acquired product images after the acquisition of the plurality of product images of the current product to be analyzed, judge whether to finish the acquisition of all the product images after the acquisition of the plurality of product images of the current product to be analyzed, if judge that the acquisition of all the product images of the current product to be analyzed is finished, a sorting request corresponding to a current product to be analyzed is generated to trigger the operation of sorting processing.
In this embodiment, a visual analysis algorithm is specifically adopted to perform visual analysis processing on a product image to obtain a product analysis result, where the product analysis result is a GOOD or NG defective product, the visual analysis algorithm may adopt an existing deep learning algorithm model, and the deep learning algorithm model can accurately and efficiently complete detection and analysis of the product image.
When only one product image needs to be acquired for a current product to be analyzed, after the product image is acquired, performing visual analysis processing according to the product image to obtain a product analysis result corresponding to the current product to be analyzed, or when the product image is acquired in step S101, the visual analysis processing is performed on each product image to obtain an analysis result corresponding to one product image, and after the visual analysis is performed on a plurality of product images of the current product to be analyzed in sequence, a plurality of analysis results of the current product to be analyzed are obtained, and the plurality of analysis results are integrated into one product analysis result, so that a sorting signal only needs to be generated according to one product analysis result subsequently, sorting processing is executed, and sorting efficiency and accuracy are improved.
S103, judging whether a product analysis result of a previous product to be analyzed is obtained or not according to the sorting request, if so, enabling the previous product to be analyzed to become a product to be sorted, generating a sorting signal of the product to be sorted according to the obtained product analysis result of the previous product to be analyzed, storing the sorting signal of the product to be sorted to a sorting signal cache queue, and obtaining a sorting signal of a current product to be sorted from the sorting signal cache queue;
further, the determining whether to obtain a product analysis result of the previous product to be analyzed according to the sorting request further includes: and if not, suspending the acquisition of the sorting signal of the current product to be sorted from the sorting signal cache queue until the product analysis result of the last product to be analyzed is acquired.
And S104, performing sorting processing on the current product to be sorted according to the obtained sorting signal of the current product to be sorted.
The specific process of executing step S103 and step S104 according to the sorting request is as follows: after a current product to be analyzed is judged to finish the acquisition of a product image, a corresponding sorting request is generated, after the sorting request is obtained, whether the product analysis result of the previous product to be analyzed is obtained or not is judged firstly, if not, the sorting signal of the current product to be sorted is obtained from a sorting signal cache queue in a suspending mode, and the current product to be sorted is subjected to suspending sorting processing until the product analysis result of the previous product to be analyzed is obtained; and if so, the previous product to be analyzed becomes a product to be subjected to sorting, a sorting signal is generated according to the obtained product analysis result of the previous product to be analyzed, the sorting signal of the product to be subjected to sorting is stored in a sorting signal cache queue, the sorting signal of the current product to be subjected to sorting is obtained from the sorting signal cache queue, and sorting processing is carried out on the current product to be subjected to sorting according to the sorting signal of the current product to be subjected to sorting.
In this embodiment, after the product image acquisition is completed, a sorting request is generated to trigger the execution of step S103, when the sorting signal process of the current product to be sorted is acquired in step S103 and the sorting processing of the current product to be sorted is executed according to the sorting signal in step S104, the visual analysis process of the product image of the current product to be analyzed in step S102 is performed synchronously, which is a creation point of this embodiment.
It should be noted that, in this embodiment, the time point of the generation and triggering of the sorting request is that after all the product images of the current product to be analyzed are acquired, the current product to be sorted on the conveyor belt just moves to the position to be sorted, and at this time, the step S103 of acquiring the sorting signal of the current product to be sorted and the step S104 of executing the sorting process are triggered, which are consistent with the original production rhythm, but only eliminate the visual analysis time of the product to be analyzed.
It should be understood that after the sorting request is obtained, whether the product analysis result of the previous product to be analyzed is obtained or not is judged, if not, the visual analysis time of the previous product to be analyzed is longer, and at this time, the current product to be sorted is triggered to wait for the non-sorting processing, so that the sorting processing is triggered by only one product to be analyzed in advance, and the normal operation of the overall production rhythm is ensured.
Therefore, the present embodiment utilizes the sorting request, not only realizes the synchronous sorting process of the current products to be sorted when the visual analysis process is performed on the current products to be analyzed, eliminates the time for introducing the visual analysis into the production line, but also ensures the coordinated cooperation of the actions of each link of image acquisition, visual analysis and sorting, avoids the disorder of sorting, and ensures the ordered production rhythm.
Specifically, before acquiring an image of a product obtained by image acquisition of a product to be analyzed, the method further includes:
according to the distance between image acquisition equipment for acquiring images of products to be analyzed currently and sorting equipment for sorting the products to be sorted currently and the length of each product to be sorted, sorting signals of one or more products to be sorted are stored in a sorting signal cache queue in advance;
or, according to the number of products to be sorted which can be accommodated between the image acquisition equipment for acquiring images of the products to be analyzed and the sorting equipment for sorting the products to be sorted, the sorting signals of one or more products to be sorted are stored in the sorting signal buffer queue in advance.
Additionally, the present embodiment further includes: and displaying the quantity information of the sorting signals in the sorting signal buffer queue in real time. When a sorting signal is acquired from the sorting signal buffer queue, the number of the sorting signals in the sorting signal buffer queue should be smaller than the number of products to be analyzed which have finished image acquisition and wait for sorting, that is, the number of the products to be sorted, and the number of the products to be sorted at the rest of time should be equal.
Example 2
Referring to fig. 2, fig. 2 is a structural diagram of a product visual quality inspection system according to the present embodiment, the system mainly includes four software modules and a signal buffer queue, the four software modules can be connected to two hardware devices, which are an industrial camera and a sorting device, respectively, and the system includes:
the image acquisition module 201 is configured to acquire an image of a product to be analyzed, and generate a sorting request according to the product image;
the visual analysis module 202 is connected to the image acquisition module 201, and is configured to perform visual analysis on the product image to generate a corresponding product analysis result;
specifically, the acquiring an image of a product obtained by image-capturing a current product to be analyzed, and generating a sorting request according to the product image includes: after image acquisition is carried out on a current product to be analyzed to obtain a plurality of product images, whether the acquisition of all the product images is finished is judged, and if yes, a sorting request is generated according to the plurality of product images;
the generating of the corresponding product analysis result after the visual analysis processing of the product image comprises: and respectively carrying out visual analysis processing on the plurality of product images to generate a plurality of corresponding analysis results, and integrating the plurality of analysis results to generate a product analysis result corresponding to the product to be analyzed.
In this embodiment, the image obtaining module 201 is connected to one or more industrial cameras, and is configured to obtain a product image captured by the industrial cameras, and send the obtained product image to the visual analysis module 202, so that the visual analysis module 202 performs visual analysis processing on the product image; when a plurality of images are required to be shot for a product to cover a complete product, the image acquisition module 201 is further configured to determine whether to complete the acquisition of all product images of the product to be analyzed currently, and when it is determined that the acquisition of the product images is completed, a sorting request is generated and sent to the sorting control module 203, and the sorting control module 203 and the sorting processing module 204 are triggered to perform sorting on the product to be sorted currently.
In this embodiment, the visual analysis module 202 specifically uses a visual analysis algorithm to perform visual analysis processing on the product image to obtain a product analysis result, where the product analysis result is a GOOD or NG defective product, the visual analysis algorithm may use an existing deep learning algorithm model, and the deep learning algorithm model can implement accurate and efficient detection and analysis of the product image.
The visual analysis module 202 obtains the product images sent by the image obtaining module 201, and performs visual analysis processing on the product images to obtain product analysis results, when visual analysis processing needs to be performed on multiple product images of a product to be analyzed, the visual analysis module 202 sequentially obtains one product image, performs visual analysis processing on one product image to obtain an analysis result corresponding to one product image, performs visual analysis on multiple product images of the current product to be analyzed in sequence to obtain multiple analysis results of the current product to be analyzed, integrates the multiple analysis results into one product analysis result, and sends one product analysis result to the sorting control module 203, so that the sorting control module 203 performs subsequent processing after obtaining the product analysis results.
A sorting control module 203, which is respectively connected to the image acquisition module 201 and the visual analysis module 202, and is configured to determine whether a product analysis result of a previous product to be analyzed is acquired according to the sorting request, if so, the previous product to be analyzed becomes a product to be sorted, generate a sorting signal of the product to be sorted according to the acquired product analysis result of the previous product to be analyzed, store the sorting signal of the product to be sorted into a sorting signal cache queue, and acquire a sorting signal of a current product to be sorted from the sorting signal cache queue;
specifically, the sorting control module 203 is further configured to determine whether to obtain a product analysis result of a previous product to be analyzed according to the sorting request, and if not, suspend obtaining a sorting signal of a current product to be sorted from the sorting signal cache queue until obtaining a product analysis result of the previous product to be analyzed.
And the sorting processing module 204 is connected with the sorting control module 203 and is used for performing sorting processing on the current product to be sorted according to the obtained sorting signal of the current product to be sorted.
The sorting processing module 204 is connected to a sorting device in the production line, the sorting device can be set according to actual production, for example, a cutting machine, etc., and the working principle of the sorting control module 203 and the sorting processing module 204 is as follows: the image acquisition module 201 generates a corresponding sorting request after judging that a current product to be analyzed finishes the acquisition of a product image, and sends the sorting request to the sorting control module 203; after the sorting control module 203 acquires the sorting request, it determines whether to acquire a product analysis result of a previous product to be analyzed, if not, the sorting of the current product to be sorted is suspended until the product analysis result of the previous product to be analyzed is acquired, if so, a sorting signal is generated according to the acquired product analysis result of the previous product to be analyzed, the sorting signal of the product to be sorted is stored in a sorting signal cache queue, the sorting signal of the current product to be sorted is acquired from the sorting signal cache queue, and the sorting signal of the current product to be sorted is sent to the sorting processing module 204; the sorting processing module 204 controls the sorting device to perform sorting processing on the current product to be sorted according to the sorting signal of the current product to be sorted.
In this embodiment, after the image acquisition module 201 finishes the product image acquisition, a component inspection request is generated to trigger the execution of the sorting control module 203, and when the sorting control module 203 and the sorting processing module 204 control the sorting processing of the current product to be sorted, the visual analysis module 202 performs the visual analysis process on the product image of the current product to be analyzed synchronously, which is a creation point of this embodiment.
Additionally, the system also comprises a visualization module, wherein the visualization module is used for displaying the quantity information of the sorting signals in the sorting signal buffer queue in real time. When the sorting control module 203 sends a sorting signal to the sorting processing module 204, the number of the sorting signals in the sorting signal buffer queue should be less than the number of analysis products that have finished image acquisition and wait for sorting, that is, the number of the products to be sorted, and at the rest of the time, the numbers of the two should be equal.
In an embodiment of the present invention, there is further provided a computer device, which may be a terminal, and the computer device includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the product visual quality inspection method when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the product visual quality inspection method.
It should be understood that the above-mentioned embodiments of the present invention are only examples for clearly illustrating the technical solutions of the present invention, and are not intended to limit the specific embodiments of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention claims should be included in the protection scope of the present invention claims.
Claims (10)
1. A method for visual quality inspection of a product, comprising:
acquiring an image of a current product to be analyzed to obtain a product image, and generating a sorting request according to the product image;
performing visual analysis processing on the product image to generate a corresponding product analysis result;
judging whether a product analysis result of a last product to be analyzed is obtained or not according to the sorting request, if so, enabling the last product to be analyzed to become a product to be sorted, generating a sorting signal of the product to be sorted according to the obtained product analysis result of the last product to be analyzed, storing the sorting signal of the product to be sorted into a sorting signal cache queue, and obtaining a sorting signal of the current product to be sorted from the sorting signal cache queue;
and performing sorting processing on the current product to be sorted according to the obtained sorting signal of the current product to be sorted.
2. The visual quality inspection method of a product according to claim 1, wherein the determining whether to obtain the product analysis result of the previous product to be analyzed according to the sorting request further comprises:
and if not, suspending the acquisition of the sorting signal of the current product to be sorted from the sorting signal cache queue until the product analysis result of the last product to be analyzed is acquired.
3. The visual quality inspection method of a product according to claim 1, further comprising:
and displaying the quantity information of the sorting signals in the sorting signal buffer queue in real time.
4. The visual quality inspection method of a product according to claim 1, wherein the image acquisition of the product to be analyzed to obtain a product image, and the generation of the sorting request according to the product image comprises:
after image acquisition is carried out on a current product to be analyzed to obtain a plurality of product images, whether the acquisition of all the product images is finished is judged, and if yes, a sorting request is generated according to the plurality of product images;
the generating of the corresponding product analysis result after the visual analysis processing of the product image comprises:
and respectively carrying out visual analysis processing on the plurality of product images to generate a plurality of corresponding analysis results, and integrating the plurality of analysis results to generate a product analysis result corresponding to the product to be analyzed.
5. The visual quality inspection method of a product according to claim 1, wherein before the image of the product is acquired by image acquisition of the product to be analyzed, the method further comprises:
according to the distance between image acquisition equipment for acquiring images of products to be analyzed currently and sorting equipment for sorting the products to be sorted currently and the length of each product to be sorted, sorting signals of one or more products to be sorted are stored in a sorting signal cache queue in advance;
or, according to the number of products to be sorted which can be accommodated between the image acquisition equipment for acquiring images of the products to be analyzed and the sorting equipment for sorting the products to be sorted, the sorting signals of one or more products to be sorted are stored in the sorting signal buffer queue in advance.
6. A product visual quality inspection system, comprising:
the image acquisition module is used for acquiring images of a current product to be analyzed to obtain a product image and generating a sorting request according to the product image;
the visual analysis module is connected with the image acquisition module and is used for generating a corresponding product analysis result after the product image is subjected to visual analysis processing;
the sorting control module is respectively connected with the image acquisition module and the visual analysis module and is used for judging whether a product analysis result of a last product to be analyzed is acquired according to the sorting request, if so, the last product to be analyzed becomes a product to be sorted, a sorting signal of the product to be sorted is generated according to the acquired product analysis result of the last product to be analyzed, the sorting signal of the product to be sorted is stored in a sorting signal cache queue, and the sorting signal of the current product to be sorted is acquired from the sorting signal cache queue;
and the sorting processing module is connected with the sorting control module and is used for sorting the current product to be sorted according to the obtained sorting signal of the current product to be sorted.
7. The visual product quality inspection system of claim 6, wherein the sorting control module is further configured to determine whether to obtain a product analysis result of a previous product to be analyzed according to the sorting request, and if not, suspend obtaining a sorting signal of a current product to be sorted from the sorting signal cache queue until obtaining the product analysis result of the previous product to be analyzed.
8. The visual product quality inspection system of claim 6, further comprising a visualization module configured to display information on the number of inspection signals in the buffer queue of inspection signals in real time.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program performs the steps of the product visual quality inspection method of any one of claims 1-5.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the visual quality inspection method of a product according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111231933.8A CN114130687A (en) | 2021-10-22 | 2021-10-22 | Product visual quality inspection method, system, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111231933.8A CN114130687A (en) | 2021-10-22 | 2021-10-22 | Product visual quality inspection method, system, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114130687A true CN114130687A (en) | 2022-03-04 |
Family
ID=80394561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111231933.8A Pending CN114130687A (en) | 2021-10-22 | 2021-10-22 | Product visual quality inspection method, system, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114130687A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001134762A (en) * | 1999-11-08 | 2001-05-18 | Kyokuto Kaihatsu Kogyo Co Ltd | Selector for bottles |
| CN101403602A (en) * | 2008-11-17 | 2009-04-08 | 天津理工大学 | Embedded high-speed on-line machine vision detection method and device |
| CN204479490U (en) * | 2015-04-15 | 2015-07-15 | 夏朝 | A kind of laser marking On-line Product testing and analysis system |
| CN106824816A (en) * | 2016-12-20 | 2017-06-13 | 浙江工业大学 | A kind of PE based on machine vision bottles of detection and method for sorting |
| WO2018056417A1 (en) * | 2016-09-23 | 2018-03-29 | 株式会社アーステクニカ | Sorting device and sorting method |
| CN109277318A (en) * | 2018-06-29 | 2019-01-29 | 烟台大学 | A kind of fruit quality vision detection and classification device and detection stage division |
| CN210022894U (en) * | 2018-12-13 | 2020-02-07 | 东莞市乐琪光电科技有限公司 | Double SCARA battery defect detector |
| CN111266315A (en) * | 2020-02-20 | 2020-06-12 | 南京工程学院 | Ore material online sorting system and method based on visual analysis |
| CN111830039A (en) * | 2020-07-22 | 2020-10-27 | 南京认知物联网研究院有限公司 | Intelligent product quality detection method and device |
| CN213737330U (en) * | 2020-10-28 | 2021-07-20 | 迩言(上海)科技有限公司 | Multi-type defect sorting equipment for imperfect grains |
-
2021
- 2021-10-22 CN CN202111231933.8A patent/CN114130687A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001134762A (en) * | 1999-11-08 | 2001-05-18 | Kyokuto Kaihatsu Kogyo Co Ltd | Selector for bottles |
| CN101403602A (en) * | 2008-11-17 | 2009-04-08 | 天津理工大学 | Embedded high-speed on-line machine vision detection method and device |
| CN204479490U (en) * | 2015-04-15 | 2015-07-15 | 夏朝 | A kind of laser marking On-line Product testing and analysis system |
| WO2018056417A1 (en) * | 2016-09-23 | 2018-03-29 | 株式会社アーステクニカ | Sorting device and sorting method |
| CN106824816A (en) * | 2016-12-20 | 2017-06-13 | 浙江工业大学 | A kind of PE based on machine vision bottles of detection and method for sorting |
| CN109277318A (en) * | 2018-06-29 | 2019-01-29 | 烟台大学 | A kind of fruit quality vision detection and classification device and detection stage division |
| CN210022894U (en) * | 2018-12-13 | 2020-02-07 | 东莞市乐琪光电科技有限公司 | Double SCARA battery defect detector |
| CN111266315A (en) * | 2020-02-20 | 2020-06-12 | 南京工程学院 | Ore material online sorting system and method based on visual analysis |
| CN111830039A (en) * | 2020-07-22 | 2020-10-27 | 南京认知物联网研究院有限公司 | Intelligent product quality detection method and device |
| CN213737330U (en) * | 2020-10-28 | 2021-07-20 | 迩言(上海)科技有限公司 | Multi-type defect sorting equipment for imperfect grains |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN204479490U (en) | A kind of laser marking On-line Product testing and analysis system | |
| CN2828808Y (en) | Glass bottle body photographic tester | |
| CN110102511A (en) | A kind of vision detection system and method for product appearance | |
| CN108416866B (en) | Inspection task processing method and equipment | |
| CN102303017B (en) | Method for automatically detecting bending of injector steel needles by using machine vision system | |
| CN109145771A (en) | A kind of face snap method and device | |
| WO2022017197A1 (en) | Intelligent product quality inspection method and apparatus | |
| CN115331002A (en) | Method for realizing remote processing of heating power station fault based on AR glasses | |
| CN101807061A (en) | Vision detection control system and method for integrated circuit tendon-cut system | |
| CN103544524A (en) | Bar reviewing-counting method and device | |
| CN110793973A (en) | Leather surface defect detecting system | |
| CN112964732A (en) | Spinning cake defect visual detection system and method based on deep learning | |
| CN105844282A (en) | Method for detecting defects of fuel injection nozzle O-Ring through line scanning camera | |
| CN110246327A (en) | The detection method and device of remote controler, storage medium, processor | |
| CN114130687A (en) | Product visual quality inspection method, system, computer equipment and storage medium | |
| CN112080829B (en) | Binding yarn detection image system | |
| CN113793385A (en) | Method and device for positioning fish head and fish tail | |
| JP2014220657A (en) | Image measuring device and image measuring program | |
| CN112101060A (en) | Two-dimensional code positioning method based on translation invariance and small-area template matching | |
| EP4249187A1 (en) | Tool checking device, tool checking program, and tool checking method for robot arm | |
| CN115082795A (en) | Virtual image generation method, device, equipment, medium and product | |
| CN111842212A (en) | Automatic feeding structure, appearance detection device, mask appearance detection device and method | |
| CN208296781U (en) | A kind of mobile phone center flatness checking device | |
| CN114113119A (en) | Product visual quality inspection method, system, equipment and medium based on defect grade | |
| CN111402190B (en) | Image processing device and system for wire rod on-line detection |
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 |