CN115965811A - Assembly quality detection method and device and storage medium - Google Patents
Assembly quality detection method and device and storage medium Download PDFInfo
- Publication number
- CN115965811A CN115965811A CN202211582674.8A CN202211582674A CN115965811A CN 115965811 A CN115965811 A CN 115965811A CN 202211582674 A CN202211582674 A CN 202211582674A CN 115965811 A CN115965811 A CN 115965811A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- good product
- characteristic
- assembly
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to an assembly quality detection method, device and method, comprising the following steps: collecting a good product image, carrying out and processing on the good product image, and marking the characteristics in the good product image to obtain a profile model of the good product and a document containing marking information to form a feature image set of the good product; acquiring an initial image of an assembly part to be detected, and preprocessing the image to be detected to obtain an image of the assembly part to be detected; the image of the assembly part to be detected and the characteristic image of the good product at the same position are compared and analyzed, whether the quality of the assembly part to be detected is qualified or not is judged, a detection result is obtained, the image of the assembly part to be detected and the characteristic image of the good product image are collected and compared, whether quality problems such as misloading and neglected loading occur or not in the assembly process is fed back, labor intensity is reduced, and working efficiency is improved.
Description
Technical Field
The invention relates to the technical field of industrial assembly quality detection, in particular to a detection method and a detection system for portable digital industrial assembly quality detection, and is particularly suitable for assembly quality detection of related products in space equipment.
Background
In the field of product assembly related to aerospace equipment, the quality of a product is always put at a high position, and one small screw is related to the success or failure of the product. With the continuous development of the technology, particularly the development of high and new technology taking the aerospace technology as the core, the aerospace equipment is developed in the directions of automation, intellectualization and no humanization, and the industrial assembly quality in the assembly process of products related to the aerospace equipment is particularly important. At present, in the final assembly process of related products, an operator needs to use a camera to photograph the assembly process according to the requirement of image recording so as to record the state of the products.
In the prior art, the adopted photographing mode is that before photographing, personnel need to write the information of the photographed part on a photographing card, then hold the photographing card with one hand and hold a camera with the other hand, and photograph the card and the photographed part together so as to record the product quality information of the assembled part. The photographing mode is manually operated, time and labor are consumed, photograph records are scattered and are not easy to manage, and when a plurality of photographing points are provided, the defect is more prominent.
Therefore, an assembly quality detection method, system and device which can improve image quality, reduce labor intensity, improve work efficiency, realize informatization of images, realize customized management, provide effective guarantee for product quality tracing, are convenient and fast, and are flexible in operation are needed, and detection efficiency is improved.
Disclosure of Invention
In order to solve one of the above technical problems, the invention provides an assembly quality detection method, an assembly quality detection device and a storage medium, which can improve image quality, reduce labor intensity, improve working efficiency, realize informatization of images, realize customized management, provide effective guarantee for product quality tracing, and are convenient, fast and flexible in operation.
In order to achieve the above purpose, the technical solution of the embodiment of the present invention is implemented as follows:
an assembly quality detection method comprising: collecting a good product image, preprocessing the good product image, marking the characteristics in the good product image to obtain a profile model of the good product and a document containing marking information, and forming a feature image set of the good product; acquiring an initial image of an assembly part to be detected, and preprocessing the image to be detected to obtain an image of the assembly part to be detected; comparing the image of the assembly part to be detected with the characteristic image of the good product in the characteristic image set, and screening out the characteristic image of the good product at the same position as the assembly part to be detected; comparing and analyzing the image of the assembly part to be detected and the characteristic image of a good product at the same position to obtain difference information between the image of the assembly part to be detected and the characteristic image of the good product; performing image analysis on difference information between the image of the assembly part to be detected and the characteristic image of a good product, and judging whether the quality of the assembly part to be detected is qualified or not to obtain a detection result; and the system outputs an image comparison detection result in real time, and if the comparison result is unqualified, the target area in the detection image is marked by a red square frame and NG information prompt is displayed.
Further, when collecting the characteristic image of the good product, selecting a corresponding area position in the established characteristic image for marking to form a document containing marking information; performing convolution operation on the original images of good products by adopting a preset step length common convolution layer and an average pooling layer, and superposing convolution results to obtain a plurality of characteristic layers of the good products, wherein the characteristic layers are associated with calibrated parameter values; convolution filters with different scales and numbers are sequentially adopted to carry out convolution operation on each feature layer so as to extract different first feature points from each feature layer, and after the first feature points with the same size are combined through dot product operation, the first feature points are associated with corresponding parameter values to obtain a good product profile model.
Further, matching calculation is carried out on the images to be detected after pretreatment of the template image sets of good products, and similarity measurement values are solved; and taking the maximum value of the similarity metric values, obtaining the images which are most matched in the good template image set and corresponding position information, and screening out the feature images of the good products at the same positions as the assembly parts to be detected.
Further, matching calculation is carried out on the images to be detected after pretreatment of the template image set of good products, and a similarity metric value is solved; and taking the maximum value of the similarity metric values, obtaining the images which are most matched in the good template image set and corresponding position information, and screening out the feature images of the good products at the same positions as the assembly parts to be detected.
Further, the pre-processing of the good images and the images to be detected comprises the steps of noise reduction processing of the images, conversion into set size and normalization processing.
In another aspect of the present invention, there is provided a computer-readable storage medium, including: the computer readable storage medium has stored therein at least one instruction or at least one program which is loaded and executed by a processor to implement the steps of the method as described above.
In another aspect of the present invention, there is provided an assembly quality detecting apparatus comprising
The device comprises at least one acquisition end movably arranged with a bracket, a display end and an input end which are detachably arranged on the bracket, and a control end electrically connected with a camera, the display end and the input end;
the acquisition end is provided with electronic equipment which can capture images and convert the images into digital signals;
the display end is an electronic device provided with an application capable of displaying images;
the input end is an electronic device or a special terminal which can input instructions;
the control terminal comprises a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor.
Furthermore, the device also comprises an adjusting rod arranged between the collecting end and the support, one end of the adjusting rod is fixed with the collecting end, and the other end of the adjusting rod is telescopic and connected with the support.
Furthermore, the adjusting rod is a telescopic rod, and the adjusting pipe is a universal hose.
Furthermore, the portable box is further included for accommodating the folded bracket, the display end and the input end which are detached from the bracket and the camera.
The assembling quality detection device provided by the embodiment greatly improves the flexibility and maneuverability of operation through the foldable triangular support, expands the data capture range of the acquisition end through the adjusting rod arranged between the acquisition end and the support, can realize the data acquisition coverage of a full range and no blind area by matching with the adjusting pipe arranged between the acquisition end and the adjusting rod, is simple and flexible in whole operation, safe and reliable, and realizes the consistency of multi-batch acquired images of batch products through a mechanical positioning function.
Drawings
FIG. 1 is a schematic diagram of an embodiment of an acquisition device according to an assembly quality detection method;
FIG. 2 is a schematic flow chart diagram of one embodiment of an assembly quality detection method;
FIG. 3 is a schematic flow chart diagram of another embodiment of an assembly quality detection method;
FIG. 4 is a schematic flow chart diagram of another embodiment of an assembly quality detection method;
fig. 5 is a schematic flow chart of another embodiment of an assembly quality detection method.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that, if the embodiment of the present invention relates to directional indications, such as up, down, left, right, front, and back 823082308230, the directional indications are only used to explain the relative position relationship between the components, the motion situation, and the like in a specific posture, and if the specific posture is changed, the directional indications are correspondingly changed. In addition, if there is a description of "first, second", "S1, S2", "step one, step two", etc. in the embodiments of the present invention, such description is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of indicated technical features or indicating the execution order of the methods, etc., and those skilled in the art will understand that all that is within the technical idea of the invention and does not depart from the gist of the invention shall fall within the protection scope of the invention.
As shown in fig. 1, according to a schematic structural diagram of a collecting apparatus according to an assembly quality detecting method shown in some exemplary embodiments, as shown in fig. 1, the collecting apparatus includes at least one collecting terminal 10 movably disposed with a support 20, a display terminal 30 and an input terminal 40 detachably disposed on the support 20, and a control terminal electrically connected with a camera 10, the display terminal 30 and the input terminal 40.
The acquisition terminal 10 is an electronic device installed to convert image capture into digital signals.
The display terminal 30 is an electronic device installed with an application that can present images.
The input terminal 40 is an electronic device or a dedicated terminal that can input instructions.
The device comprises a control end processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor.
The electronic device referred to herein may be a smart home appliance, a smart phone, a tablet computer, a wearable device, an e-book reader, a camera, a laptop portable computer, a desktop computer, and the like. The intelligent household appliances can be refrigerators, air conditioners, televisions, microwave ovens, weighing scales, electric cookers, water dispensers and the like, and the wearable devices can be intelligent bracelets, intelligent tie clips, intelligent key rings, intelligent watches, intelligent rings and the like.
Therefore, after the acquired images are transmitted to the controller by the acquisition terminal 10 and are compared and analyzed, the result is displayed by the display terminal 30, and the input of the related instruction can be performed by the input terminal 40 for corresponding control. Preferably, the support frame 20 is a collapsible triangular support frame to improve the flexibility and maneuverability of the operation.
In the preferred embodiment of the present application, as shown in fig. 1, in order to expand the data capture range of the acquisition end 10, the data capture device further includes an adjusting rod 50 disposed between the acquisition end 10 and the bracket 20, one end of the adjusting rod 50 is fixed to the acquisition end 10, and the other end of the adjusting rod is telescopically connected to the bracket 20. Furthermore, in order to realize the data acquisition coverage of the acquisition end 10 in the full range and without blind areas, the device further comprises an adjusting pipe 60 arranged between the acquisition end 10 and the adjusting rod 50, wherein one end of the adjusting pipe 60 is connected with the telescopic end of the adjusting rod 50, and the other end arranged opposite to the adjusting pipe is connected with the acquisition end 10 in an angle-adjustable manner into a whole and is arranged in a co-motion manner. In some embodiments of the present application, the adjusting rod 50 is a telescopic rod, and the adjusting tube 60 is a universal hose.
Optionally, a portable case for receiving the folded stand 20, the display terminal 30 and the input terminal 40 detached from the stand 20, and the camera 10 is further included.
In conclusion, the assembly quality detection device in the embodiment of the disclosure greatly improves the flexibility and maneuverability of operation through the foldable triangular bracket, expands the data capture range of the acquisition end through the adjusting rod arranged between the acquisition end and the bracket, and can realize full-range data acquisition coverage without blind areas by matching with the adjusting pipe arranged between the acquisition end and the adjusting rod, and the whole operation is simple, flexible, safe and reliable. The mechanical positioning function realizes the consistency of the multi-batch collected images of batch products.
Fig. 2 is a flowchart illustrating an assembly quality inspection method according to an exemplary embodiment, which is applied to the assembly quality inspection apparatus shown in fig. 1, as shown in fig. 2, and includes the following steps.
In step S10, collecting a good product image, preprocessing the good product image, labeling features in the good product image to obtain a profile model of the good product and a document containing labeling information, and forming a feature image set of the good product;
in step S20, an initial image of the assembly part to be detected is obtained, and the image to be detected is preprocessed to obtain an image of the assembly part to be detected;
in step S30, comparing the image of the assembly part to be detected with the characteristic images of good products in the characteristic image set, and selecting the characteristic images of good products at the same positions as the assembly part to be detected;
in step S40, comparing and analyzing the image of the assembly part to be detected and the feature image of a good product at the same position to obtain difference information between the image of the assembly part to be detected and the feature image of a good product;
in step S50, performing image analysis on the difference information between the image of the assembly part to be detected and the characteristic image of a good product, and determining whether the quality of the assembly part to be detected is qualified or not to obtain a detection result;
in step S60, the system outputs the image comparison detection result in real time, and if the comparison result is not qualified, the target area in the detection image is marked with a red square and an NG information prompt is displayed.
Further, the good image and the image to be detected are preprocessed, including the noise reduction processing, the conversion into the set size and the normalization processing of the images; the good product image and the image to be detected comprise RGB information and depth image information; and the marking is to perform frame selection on positions in the good images and the images to be detected to obtain rectangular frames and documents, wherein the documents comprise the coordinates, the sizes and the types of the rectangular frames.
In summary, the assembly quality detection method in the embodiment of the disclosure compares the collected image of the to-be-detected portion with the characteristics of the non-defective image, and feeds back whether quality problems such as misloading and neglected loading occur in the assembly process, so that the labor intensity is reduced, the working efficiency is improved, the informatization of the image is realized, and an effective guarantee is provided for product quality tracing.
Example 2:
in addition to embodiment 1, as shown in fig. 3, in step S10, the method further includes the following steps:
in step S110, when collecting a feature image of a good product, selecting a corresponding region position from the established feature image for labeling, and forming a document containing labeling information;
in step S120, a predetermined step size ordinary convolution layer and an average pooling layer are used to perform convolution operation on the good-quality original image and superimpose the convolution results to obtain a plurality of characteristic layers of the good-quality image, and the characteristic layers are associated with the calibrated parameter values;
in step S130, convolution operations are sequentially performed on each feature layer by using convolution filters of different scales and numbers to extract different first feature points from each feature layer, and the first feature maps of the same size are combined by dot product operations and then associated with corresponding parameter values to obtain a good-quality contour model.
In summary, in the assembly quality detection method in the embodiment of the present disclosure, the area position is selected from the good-quality feature image and is labeled, and the convolution operation is performed on the predetermined step size common convolution layer and the average pooling layer and the convolution result is superimposed, so as to obtain the corresponding feature layer, and the feature layer is associated with the position information. The image matching method based on the feature extraction has the advantages of small calculated amount and high efficiency.
Example 3:
in another preferred embodiment based on example 1, as shown in fig. 4, step S10 further includes the following steps:
in step S140, when collecting a feature image of a good product, selecting a corresponding region position from the established feature image for labeling to form a document containing labeling information;
in step S150, a corresponding feature score threshold and a matching score threshold are set for the selected region, and the calibrated parameters are associated with each other;
in step S160, image training modeling is performed on the region of the selected good product feature image, the feature score threshold, the matching score threshold, and the label information, and the obvious feature points in the image are extracted to obtain an image set of the good product contour model.
Preferably, the selected area features are one or more combinations of image gray scale and/or image edge shape.
In summary, the characteristic template image set of the good product is obtained by setting the corresponding characteristic score threshold and matching score threshold for the selected area, calculating the image gray distribution, and/or the image edge shape. The image information can be saved as much as possible, and errors generated during image segmentation and feature extraction are avoided, so that the registration result is inaccurate.
In addition, models modeled with respect to image training, such as LeNet-5, googleNet, resNet-50, etc., should be easily conceived by those skilled in the art, and thus are not described in detail herein.
Example 4:
in addition to embodiment 1, as shown in fig. 5, in step S30, the method further includes the following steps:
in step S310, matching calculation is carried out on the images to be detected after pretreatment of the template image sets of good products, and similarity measurement values are solved;
in step S320, the maximum value of the similarity metric is obtained, the best matching image and the corresponding position information in the good product template image set are obtained, and the feature image of the good product at the same position as the assembly part to be detected is selected.
In addition, the morphological region detection algorithm in the present application is well known to those skilled in the art and will not be described herein.
The assembly quality detection method provided by the embodiment of the application at least has the following characteristics:
according to the assembly quality detection method provided by the embodiment of the application, the similarity contrast analysis detection is carried out on the collected images and the template library images based on the image feature comparison algorithm of machine vision, and then whether quality problems such as misloading and neglected loading occur in the assembly process or not is fed back, so that the labor intensity can be obviously reduced, the working efficiency is improved, and meanwhile, the stability is also ensured.
The above-mentioned features of the embodiments may be arbitrarily combined only in the embodiments of the present invention, and for the sake of brevity, all possible combinations of the features in the above-mentioned embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent should be subject to the appended claims.
Claims (10)
1. An assembly quality detection method, comprising:
collecting a good product image, preprocessing the good product image, marking the characteristics in the good product image to obtain a profile model of the good product and a document containing marking information, and forming a feature image set of the good product;
acquiring an initial image of an assembly part to be detected, and preprocessing the image to be detected to obtain an image of the assembly part to be detected;
comparing the image of the assembly part to be detected with the characteristic image of the good product in the characteristic image set, and screening out the characteristic image of the good product at the same position as the assembly part to be detected;
comparing and analyzing the image of the assembly part to be detected and the characteristic image of a good product at the same position to obtain difference information between the image of the assembly part to be detected and the characteristic image of the good product;
carrying out image analysis on difference information between the image of the assembly part to be detected and the characteristic image of a good product, and judging whether the quality of the assembly part to be detected is qualified or not to obtain a detection result;
and the system outputs an image comparison detection result in real time, and if the comparison result is unqualified, the target area in the detection image is marked by a red square frame and an NG information prompt is displayed.
2. The assembly quality inspection method according to claim 1, further comprising:
when the characteristic images of good products are collected, selecting corresponding area positions from the established characteristic images for marking to form a document containing marking information;
performing convolution operation on the original images of good products by adopting a preset step length common convolution layer and an average pooling layer, and superposing convolution results to obtain a plurality of characteristic layers of the good products, wherein the characteristic layers are associated with calibrated parameter values;
convolution filters with different scales and numbers are sequentially adopted to carry out convolution operation on each feature layer so as to extract different first feature points from each feature layer, and after the first feature points with the same size are combined through dot product operation, the first feature points are associated with corresponding parameter values to obtain a good product profile model.
3. The assembly quality inspection method according to claim 1, further comprising:
when the characteristic images of good products are collected, selecting corresponding area positions from the established characteristic images for marking to form a document containing marking information;
setting corresponding feature score threshold values and matching score threshold values for the selected areas, and associating calibrated parameters of the feature score threshold values and the matching score threshold values;
and carrying out image training modeling on the selected region of the good product characteristic image, the characteristic score threshold, the matching score threshold and the labeling information, and extracting obvious characteristic points in the image to obtain an image set of a good product contour model.
4. The assembly quality inspection method according to claim 1, further comprising:
performing matching calculation on the images to be detected after pretreatment of the template image set of good products, and solving a similarity metric value;
and taking the maximum value of the similar metric values, obtaining the best matched image and corresponding position information in the good template image set, and screening out the feature image of the good product at the same position as the assembly part to be detected.
5. The assembly quality inspection method according to claim 1, wherein the pre-processing of the good-quality image and the image to be inspected includes noise reduction, conversion to a set size, and normalization of the images.
6. An assembly device quality detection apparatus, comprising:
the device comprises at least one acquisition end (10) movably arranged with a support (20), a display end (30) and an input end (40) which are detachably arranged on the support (20), and a control end electrically connected with a camera (10), the display end (30) and the input end (40);
the acquisition end (10) is provided with electronic equipment which can capture images and convert the images into digital signals;
the display end (30) is an electronic device provided with an application capable of displaying images;
the input end (40) is an electronic device or a special terminal which can input instructions;
the control terminal comprises a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor.
7. The assembly quality detection device according to claim 6, further comprising an adjusting rod (50) arranged between the collecting end (10) and the support (20), wherein one end of the adjusting rod (50) is fixed with the collecting end (10), and the other end of the adjusting rod, which is arranged oppositely, is telescopically connected with the support (20).
8. The assembly quality detecting apparatus according to claim 7, further comprising: the adjusting pipe (60) is arranged between the collecting end (10) and the adjusting rod (50), one end of the adjusting pipe (60) is connected with the telescopic end of the adjusting rod (50), and the other end of the adjusting pipe (60) which is arranged oppositely is connected with the collecting end (10) in an angle-adjustable mode into a whole and moves together.
9. The assembly quality detecting device according to claim 7 or 8, wherein the adjusting rod (50) is a telescopic rod, and the adjusting pipe (60) is a universal hose.
10. A computer-readable storage medium, in which at least one instruction or at least one program is stored, which is loaded and executed by a processor to implement the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211582674.8A CN115965811A (en) | 2022-12-09 | 2022-12-09 | Assembly quality detection method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211582674.8A CN115965811A (en) | 2022-12-09 | 2022-12-09 | Assembly quality detection method and device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115965811A true CN115965811A (en) | 2023-04-14 |
Family
ID=87359362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211582674.8A Pending CN115965811A (en) | 2022-12-09 | 2022-12-09 | Assembly quality detection method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115965811A (en) |
-
2022
- 2022-12-09 CN CN202211582674.8A patent/CN115965811A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2680765C1 (en) | Automated determination and cutting of non-singular contour of a picture on an image | |
| CN109410192B (en) | Fabric defect detection method and device based on multi-texture grading fusion | |
| CN107621932B (en) | Local amplification method and device for display image | |
| CN109241844B (en) | Attitude estimation method, device and equipment for three-dimensional object and storage medium | |
| CN104240180B (en) | A kind of method and device for realizing image adjust automatically | |
| CN104053984A (en) | Image examination method and image examination apparatus | |
| JP2007114843A (en) | Quality deciding device | |
| CN108052909B (en) | Thin fiber cap plaque automatic detection method and device based on cardiovascular OCT image | |
| CN110910445B (en) | Object size detection method, device, detection equipment and storage medium | |
| CN108229289B (en) | Target retrieval method and device and electronic equipment | |
| JP7214432B2 (en) | Image processing method, image processing program, recording medium, image processing apparatus, production system, article manufacturing method | |
| JP2016119090A (en) | System and method for determining clutter in acquired image | |
| CN108776965B (en) | Method, device and equipment for measuring straight line in image and storage medium | |
| CN114119695A (en) | Image annotation method and device and electronic equipment | |
| CN112613425B (en) | Target identification system for small sample underwater image | |
| CN104748862A (en) | Analyzing device and analyzing method | |
| JP4788475B2 (en) | Image processing apparatus and image processing method | |
| CN117314863A (en) | Defect output method, device, equipment and storage medium | |
| CN117058106A (en) | Method for measuring flatness and surface defects of flexible glass based on random forest | |
| CN115965811A (en) | Assembly quality detection method and device and storage medium | |
| CN115908988A (en) | Defect detection model generation method, device, equipment and storage medium | |
| CN104655636B (en) | Thermal image analysis device, thermal image configuration device, thermal image analysis method and thermal image configuration method | |
| CN108734175A (en) | A kind of extracting method of characteristics of image, device and electronic equipment | |
| CN113838015A (en) | Electric appliance product appearance defect detection method based on network cooperation | |
| CN111368823B (en) | Pointer type instrument reading identification method and device |
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 |