CN114049317A - CCD equipment automatic inspection system and method based on artificial intelligence - Google Patents
CCD equipment automatic inspection system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN114049317A CN114049317A CN202111295008.1A CN202111295008A CN114049317A CN 114049317 A CN114049317 A CN 114049317A CN 202111295008 A CN202111295008 A CN 202111295008A CN 114049317 A CN114049317 A CN 114049317A
- Authority
- CN
- China
- Prior art keywords
- inspection
- acquisition information
- module
- information
- photo
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/95—Computational photography systems, e.g. light-field imaging systems
- H04N23/951—Computational photography systems, e.g. light-field imaging systems by using two or more images to influence resolution, frame rate or aspect ratio
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/12—Indexing scheme for image data processing or generation, in general involving antialiasing
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Abstract
The invention discloses an artificial intelligence based automatic CCD equipment inspection system and method, which comprises an acquisition module, a verification module and a verification module, wherein the acquisition module is used for acquiring image information of materials, and the image information comprises main acquisition information, additional recording acquisition information and travel acquisition information; the intelligent splicing module is used for randomly calling any two of the main acquisition information, the additional recording acquisition information and the travel acquisition information to be combined to form an inspection photo; the screening module is used for screening the inspection photos and sending the inspection photos or the supplementary inspection photos meeting the screening conditions to the recognition module; the identification module is used for identifying the inspection photos or the supplementary inspection photos and obtaining inspection results, can quickly identify the classification and the color of the materials through a preset instruction, and then greatly improves the photographing speed and the inspection speed of the industrial camera through setting different industrial cameras with photographing angles.
Description
Technical Field
The invention belongs to the field of automatic inspection, and particularly relates to a CCD equipment automatic inspection system and method based on artificial intelligence.
Background
The CCD camera can finish fast and multiple sampling of the high-speed target in a short time, when the high-speed target is projected at a normal speed, the change process of the recorded target is clearly and slowly presented to people, and the high-speed camera technology has the outstanding advantages of real-time target capture, fast image recording, instant playback, visual and clear image and the like.
However, the existing CCD camera still has the problems of blur and insufficient resolution when the shooting speed is too high, so we need to propose a new design solution to solve the above problems in the background art.
Disclosure of Invention
The invention aims to provide a CCD equipment automatic inspection system and method based on artificial intelligence, which are used for solving the problems of blurring and insufficient resolution when the shooting speed of the existing CCD camera is too high.
The purpose of the invention can be realized by the following technical scheme:
an artificial intelligence based automated inspection system for a CCD device, comprising: the acquisition module is used for acquiring image information of the material, wherein the image information comprises main acquisition information, additional recording acquisition information and travel acquisition information; the intelligent splicing module is used for randomly calling any two of the main acquisition information, the additional recording acquisition information and the travel acquisition information to be combined to form an inspection photo; the screening module is used for screening the inspection photos and sending the inspection photos or the supplementary inspection photos meeting the screening conditions to the recognition module; and the identification module is used for identifying the inspection photo or the supplementary inspection photo and obtaining an inspection result.
Further, the acquisition module comprises a main shooting unit, a bent shooting unit and a forward shooting unit; the system comprises a main shooting unit, a forward shooting unit and a control unit, wherein the main shooting unit is used for receiving main acquisition information of a main shooting camera, the forward shooting unit is used for receiving additional recording acquisition information of the forward shooting camera, and the forward shooting unit is used for receiving stroke acquisition information of the forward shooting camera; the main acquisition information at least comprises a top view of the material; the additional recording acquisition information at least comprises side view travel acquisition information of the material and at least comprises a front view of the material.
Furthermore, the acquisition module also comprises a scanning node, and the scanning node is used for scanning the shape characteristics of the material and generating a three-dimensional model of the material.
Further, the intelligent splicing module forms the inspection photo and comprises: acquiring any two information of main acquisition information, additional recording acquisition information and travel acquisition information under the same time node; acquiring a three-dimensional model of the material, and filling any two kinds of information of main acquisition information, additional recording acquisition information and travel acquisition information into a corresponding area of the three-dimensional model to form a simulation material; and outputting the simulation material into a test photo.
Further, the screening module is used for screening the test photos and comprises: acquiring an inspection photo, and inspecting the inspection photo according to preset inspection conditions; and if the checking is qualified, selecting the inspection photo and sending the inspection photo to the recognition module, otherwise, selecting the information which is not filled into the three-dimensional model from the main acquisition information, the additional recording acquisition information and the stroke acquisition information and filling the information into the area corresponding to the three-dimensional model to form an additional simulation material, and outputting the additional simulation material into the additional inspection photo and sending the additional simulation material to the recognition module.
Further, the preset instruction includes one or more of a color instruction and a shape instruction.
Furthermore, the resolution of the top view, the side view and the front view are the same, and the size of the top view, the side view and the front view is the same as that of the area corresponding to the three-dimensional model.
An automatic inspection method of CCD equipment based on artificial intelligence comprises the following steps:
the method comprises the steps that the material to be detected obtains image information through an acquisition module, wherein the image information comprises main acquisition information, additional recording acquisition information and travel acquisition information;
the intelligent splicing module combines any two of the main acquisition information, the additional recording acquisition information and the travel acquisition information to form an inspection photo;
the screening module screens the inspection photos, and sends the inspection photos or the supplementary inspection photos meeting the screening conditions to the recognition module for recognition and obtaining the inspection results.
Compared with the prior art, the invention has the beneficial effects that:
through setting up the industrial camera of different shooting angles, even realize that the problem of shooting is unclear appears in certain camera appearance problem or appearing under the condition of high-speed shooting, also can remedy with the industrial camera of different angles, greatly improve the speed of shooing and the inspection speed of industrial camera, secondly, through predetermineeing the realization that the instruction can be quick to the classification and the colour discernment of material, realize automatic inspection.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic block diagram of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more fully described below with reference to the accompanying drawings of the embodiments of the present invention, it is apparent that the described embodiments are a part of the embodiments of the present invention, rather than the whole embodiments, and all other embodiments obtained by one of ordinary skill in the art without inventive labor based on the embodiments of the present invention belong to the scope of protection of the present invention, and therefore, the detailed description of the embodiments of the present invention provided in the following drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention.
The automatic CCD equipment inspection system based on artificial intelligence provided by the embodiment is applied to scenes for carrying out automatic inspection on an acquisition device based on an industrial camera, and particularly used in scenes with high speed, high resolution and high recognition rate.
As shown in fig. 1, an artificial intelligence based CCD device automated inspection system includes:
the acquisition module is used for acquiring material image information transmitted by the color selector;
in some specific embodiments, the acquisition module comprises a main shooting unit, a downward shooting unit, a forward shooting unit and a scanning node, wherein the main shooting unit is used for receiving main acquisition information of a main shooting camera, the downward shooting unit is used for receiving supplement acquisition information of the downward shooting camera, and the forward shooting unit is used for receiving travel acquisition information of the forward shooting camera; the main acquisition information at least comprises a top view of the material; the additional recording acquisition information at least comprises side view travel acquisition information of the material and at least comprises a front view of the material; the scanning nodes are used for scanning the shape characteristics of the material and generating a three-dimensional model of the material.
For example, a camera for shooting a top view of a material is defined as a main shooting camera, a camera for shooting a side view of the material is defined as a top shooting camera, and a camera for shooting a main view of the material is defined as a front shooting camera, so that the corresponding material is a shooting target, an area before entering a shooting area is defined as a trip area, and an area after passing through the shooting area is defined as a supplementary recording area;
the area corresponding to the main camera is a shooting area, and the area corresponding to the front camera is a travel area; the area corresponding to the top shooting camera is an additional recording area;
when the material passes through the process area, the shooting area and the additional recording area through the transmission device, the corresponding main shooting camera, the forward shooting camera and the downward shooting camera can acquire images of the material, and of course, the images may also include other objects, which are not considered here.
Similarly, when the material passes through the process area, the shooting area and the additional recording area by the conveying device, the scanning node can scan the shape characteristics of the material to generate a three-dimensional model of the material, and specifically, the scanning node can be a scanner with a scanning function.
In some specific embodiments, the main shooting unit, the bent shooting unit and the front shooting unit control corresponding actuators to acquire main acquisition information, additional acquisition information and travel acquisition information at the same time; the actuators are the same type and are provided with the same industrial cameras, and when the industrial cameras are specifically executed, the same setting can ensure that the shooting effect, the shooting size and the shooting resolution are the same; the model of the industrial camera is flexibly selected according to specific implementation.
The scanning node is deployed at the starting end of the transmission device and also comprises an intelligent camera, the data collected by the scanning node comprises material video model data and material video screen data, and the scanning data comprises material scanning model data;
respectively establishing a video model and a scanning model by the scanning node based on the material video model data and the material scanning model data through built-in modeling software;
obtaining characteristic values of a video model and a scanning model through a neural network algorithm;
two situations can occur at this time;
in the first situation, if the characteristic value corresponding to the video model is different from the characteristic value corresponding to the scanning model, material view screen data is obtained, the material view screen data is analyzed through a video analysis neural algorithm trained in advance, and analysis characteristics are obtained;
selecting and analyzing the characteristics as characteristic values, wherein the characteristic values comprise the number of surfaces of the materials and the number of edges of the materials;
for example, when the cross section of the material is trapezoidal, the characteristic values corresponding to the material comprise 6 surfaces and 12 edges; when the material is spherical, the characteristic value corresponding to the material comprises 1 surface and 0 edge;
in some specific embodiments, if the first condition occurs, the transmission device reduces the transmission speed, specifically, according to the difference in calculation power of the video analysis neural algorithm operation equipment in the applied scene, the transmission device of the corresponding color selector reduces the transmission speed, so that on one hand, the acquisition resolution can be improved, on the other hand, time can be provided for the operation of the video analysis neural algorithm, and the problem that the material is conveyed away when the characteristics of the material are not identified is avoided;
in the second case, if the feature value corresponding to the video model is the same as the feature value corresponding to the scan model, the feature value corresponding to any one of the models is output, wherein the models include the video model and the scan model.
Before the characteristic values of the video model and the scanning model are obtained through the neural network algorithm, the neural network algorithm needs to be trained, specifically:
acquiring a plurality of sample video models, sample scanning models and sample pictures in advance, intelligently matching the sample video models, the sample scanning models and the sample pictures through a neural network algorithm, and obtaining characteristic values of the sample pictures;
the sample pictures are pictures with characteristic values, and the sample pictures are selected from material view screen data; the neural network algorithm is a convolution neural network operation circuit, and comprises: an external memory for storing an image to be processed; the external memory includes at least one of: double-rate synchronous dynamic random access memory and synchronous dynamic random access memory.
The internal memory includes a static memory array including a plurality of static memories each for storing different data.
And the direct access unit is connected with the external memory and used for reading the image to be processed and transmitting the read data to the control unit.
The control unit is connected with the direct access unit and used for storing data into the internal memory;
the internal memory is connected with the control unit and used for caching data;
the operation unit is connected with the internal memory and used for reading data from the internal memory and performing convolution pooling operation;
the operation unit comprises a convolution operation unit, a pooling operation unit, a buffer unit and a buffer control unit;
the convolution operation unit is used for carrying out convolution operation on the data and transmitting an obtained convolution result to the pooling operation unit;
the pooling operation unit is connected with the convolution operation unit and used for performing pooling operation on the convolution result and storing the obtained pooling result into the buffer unit;
and the buffer control unit is used for storing the pooling result into the internal memory through the buffer unit or into the external memory through the direct access unit.
More specifically, the number of the operation units is at least two, and when the operation units are connected in a cascade structure, the data of the nth layer is cached in the internal memory after the convolution pooling operation of the nth operation unit, and the data after the operation is taken out by the (n + 1) th operation unit and the convolution pooling operation of the (n + 1) th layer is performed, wherein n is a positive integer.
Under the condition that the operation units are connected in a parallel structure, the operation units respectively process partial images of the image to be processed, and the operation units adopt the same convolution kernel to carry out parallel convolution pooling operation.
Under the condition that the operation units are connected in a parallel structure, the operation units respectively extract different features of the image to be processed, and the operation units adopt different convolution kernels to perform parallel convolution pooling operation.
In the case where the number of the operation units is two, the two operation units extract contour information and detail information of the image to be processed, respectively.
In some specific embodiments, the intelligent splicing module is used for randomly calling any two of the main acquisition information, the additional recording acquisition information and the travel acquisition information to be combined to form an inspection photo;
specifically, any two information of main acquisition information, additional recording acquisition information and travel acquisition information under the same time node are acquired;
acquiring a three-dimensional model of the material, and filling any two kinds of information of main acquisition information, additional recording acquisition information and travel acquisition information into a corresponding area of the three-dimensional model to form a simulation material; and outputting the simulation material into a test photo.
In some embodiments, the screening module is configured to screen the inspection photos and send the inspection photos or the supplementary inspection photos that satisfy the screening condition to the recognition module;
specifically, acquiring a test photo, and checking the test photo according to a preset checking condition;
and if the checking is qualified, selecting the inspection photo and sending the inspection photo to the recognition module, otherwise, selecting the information which is not filled into the three-dimensional model from the main acquisition information, the additional recording acquisition information and the stroke acquisition information and filling the information into the area corresponding to the three-dimensional model to form an additional simulation material, and outputting the additional simulation material into the additional inspection photo and sending the additional simulation material to the recognition module.
In some embodiments, the screening conditions include photo resolution, photo size, location of photo calibration points, wherein any one of the occurrences is deemed to be an unsatisfactory screening condition;
(1) the photo resolution of the inspection photo generated after superposition is different from the resolutions of any two pictures in the selected top view, side view and main view;
(2) the photo size of the inspection photo generated after superposition is different from the photo sizes of any two pictures in the selected top view, the side view and the main view;
(3) the positions of the photo calibration points within the inspection photo generated after the coincidence do not coincide.
The calibration point of the picture in the picture is the lower right corner of the default output picture after the image is shot by the industrial camera and is 3mm away from the two corresponding edges of the lower right corner, and the calibration point is marked on one surface with the image;
if the pictures do not meet the screening condition after being supplemented, selecting the corresponding top view as a supplement inspection picture and forming precision alarm information;
in some embodiments, the identification module is configured to identify the inspection photograph or the supplementary inspection photograph and obtain an inspection result:
identifying the inspection photo or the supplementary inspection photo according to a preset instruction, wherein the preset instruction comprises one or more of a color instruction and a shape instruction;
the classification (the shape instruction is known to be a specific shape, such as a square) and the color recognition (the shape instruction is known to be a specific color, such as green) of the materials can be quickly realized through the preset instruction, and secondly, even if a certain camera has a problem or a problem that the shooting is unclear under the condition of high-speed shooting is realized through setting industrial cameras with different shooting angles, the problem can be remedied through the method, so that the shooting speed and the detection speed of the industrial cameras are greatly improved.
When the method is used specifically, the method comprises the following steps:
the method comprises the steps that the material to be detected obtains image information through an acquisition module, wherein the image information comprises main acquisition information, additional recording acquisition information and travel acquisition information;
the intelligent splicing module combines any two of the main acquisition information, the additional recording acquisition information and the travel acquisition information to form an inspection photo;
the screening module screens the inspection photos, and sends the inspection photos or the supplementary inspection photos meeting the screening conditions to the recognition module for recognition and obtaining the inspection results.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms such as second, etc. are used for names and do not indicate any particular order, and finally, it should be noted that the above embodiments are only for illustrating the technical method of the present invention and not limited, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical method of the present invention without departing from the spirit and scope of the technical method of the present invention.
Claims (8)
1. An automated inspection system for CCD equipment based on artificial intelligence, comprising:
the acquisition module is used for acquiring image information of the material, wherein the image information comprises main acquisition information, additional recording acquisition information and travel acquisition information;
the intelligent splicing module is used for randomly calling any two of the main acquisition information, the additional recording acquisition information and the travel acquisition information to be combined to form an inspection photo;
the screening module is used for screening the inspection photos and sending the inspection photos or the supplementary inspection photos meeting the screening conditions to the recognition module;
and the identification module is used for identifying the inspection photo or the supplementary inspection photo and obtaining an inspection result, wherein the inspection photo or the supplementary inspection photo is identified according to a preset instruction.
2. The artificial intelligence based CCD device automatic inspection system of claim 1, characterized in that the acquisition module comprises a main shooting unit, a down shooting unit and a forward shooting unit;
the system comprises a main shooting unit, a forward shooting unit and a control unit, wherein the main shooting unit is used for receiving main acquisition information of a main shooting camera, the forward shooting unit is used for receiving additional recording acquisition information of the forward shooting camera, and the forward shooting unit is used for receiving stroke acquisition information of the forward shooting camera;
the main acquisition information at least comprises a top view of the material;
the additional collection information at least comprises a side view of the material;
the travel acquisition information at least comprises a front view of the material.
3. The automated CCD device inspection system based on artificial intelligence of claim 2, wherein the collection module further comprises a scanning node for scanning the shape characteristics of the material and generating a three-dimensional model of the material.
4. The artificial intelligence based CCD device automated inspection system of claim 1, wherein the intelligent stitching module forming the inspection photo comprises:
acquiring any two information of main acquisition information, additional recording acquisition information and travel acquisition information under the same time node;
acquiring a three-dimensional model of the material, and filling any two kinds of information of main acquisition information, additional recording acquisition information and travel acquisition information into a corresponding area of the three-dimensional model to form a simulation material;
and outputting the simulation material into a test photo.
5. The artificial intelligence based CCD device automated inspection system of claim 4, wherein the screening module for screening inspection photographs comprises:
acquiring an inspection photo, and inspecting the inspection photo according to preset inspection conditions;
and if the checking is qualified, selecting the inspection photo and sending the inspection photo to the recognition module, otherwise, selecting the information which is not filled into the three-dimensional model from the main acquisition information, the additional recording acquisition information and the stroke acquisition information and filling the information into the area corresponding to the three-dimensional model to form an additional simulation material, and outputting the additional simulation material into the additional inspection photo and sending the additional simulation material to the recognition module.
6. The automated artificial intelligence based CCD device inspection system of claim 1, wherein the preset instructions include one or more of color instructions and shape instructions.
7. The automated inspection system of claim 2, wherein the top view, the side view and the front view have the same resolution and the dimensions of the top view, the side view and the front view are the same as the dimensions of the corresponding region of the three-dimensional model.
8. An automatic CCD equipment inspection method based on artificial intelligence is characterized by comprising the following steps:
the method comprises the steps that the material to be detected obtains image information through an acquisition module, wherein the image information comprises main acquisition information, additional recording acquisition information and travel acquisition information;
the intelligent splicing module combines any two of the main acquisition information, the additional recording acquisition information and the travel acquisition information to form an inspection photo;
the screening module screens the inspection photos, and sends the inspection photos or the supplementary inspection photos meeting the screening conditions to the recognition module for recognition and obtaining the inspection results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111295008.1A CN114049317A (en) | 2021-11-03 | 2021-11-03 | CCD equipment automatic inspection system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111295008.1A CN114049317A (en) | 2021-11-03 | 2021-11-03 | CCD equipment automatic inspection system and method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114049317A true CN114049317A (en) | 2022-02-15 |
Family
ID=80207079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111295008.1A Pending CN114049317A (en) | 2021-11-03 | 2021-11-03 | CCD equipment automatic inspection system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114049317A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114713462A (en) * | 2022-05-10 | 2022-07-08 | 深圳市智力昌智能设备有限公司 | Control system of point gum machine based on industry internet |
-
2021
- 2021-11-03 CN CN202111295008.1A patent/CN114049317A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114713462A (en) * | 2022-05-10 | 2022-07-08 | 深圳市智力昌智能设备有限公司 | Control system of point gum machine based on industry internet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110428366B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN108898567B (en) | Image noise reduction method, device and system | |
| Wu et al. | Deep high dynamic range imaging with large foreground motions | |
| CN109690620B (en) | Three-dimensional model generation device and three-dimensional model generation method | |
| DE602006000400T2 (en) | PICTORIALIZATION PROCESS AND SYSTEM | |
| CN108810418B (en) | Image processing method, image processing device, mobile terminal and computer readable storage medium | |
| CN110473185B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN108810413B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN113992861B (en) | Image processing method and image processing device | |
| CN110580428A (en) | image processing method, image processing device, computer-readable storage medium and electronic equipment | |
| CN109272060B (en) | Method and system for target detection based on improved darknet neural network | |
| CN110490196A (en) | Subject detection method and apparatus, electronic equipment, computer readable storage medium | |
| CN111986106A (en) | High dynamic image reconstruction method based on neural network | |
| CN107295252A (en) | Focusing area display methods, device and terminal device | |
| CN110365897B (en) | Image correction method and device, electronic equipment and computer readable storage medium | |
| CN114040116B (en) | Plastic mould good product monitoring feedback system | |
| CN114049317A (en) | CCD equipment automatic inspection system and method based on artificial intelligence | |
| WO2022193288A1 (en) | Image processing method and apparatus, and computer readable storage medium | |
| CN110392211A (en) | Image processing method and device, electronic equipment, computer readable storage medium | |
| CN111932462B (en) | Training method and device for image degradation model, electronic equipment and storage medium | |
| WO2020168515A1 (en) | Image processing method and apparatus, image capture processing system, and carrier | |
| CN109582811B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN115829890A (en) | Image fusion method, device, equipment, storage medium and product | |
| CN112036342A (en) | Document snapshot method, device and computer storage medium | |
| CN116580026B (en) | Automatic optical detection method, equipment and storage medium for appearance defects of precision parts |
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 |