CN117197006A - Region filtering method, region filtering device, electronic equipment and computer readable storage medium - Google Patents
Region filtering method, region filtering device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN117197006A CN117197006A CN202311256341.0A CN202311256341A CN117197006A CN 117197006 A CN117197006 A CN 117197006A CN 202311256341 A CN202311256341 A CN 202311256341A CN 117197006 A CN117197006 A CN 117197006A
- Authority
- CN
- China
- Prior art keywords
- picture
- region
- convolution
- pixel point
- input picture
- 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.)
- Granted
Links
Landscapes
- Image Processing (AREA)
Abstract
The application provides a region filtering method, a device, electronic equipment and a computer readable storage medium, which are characterized in that firstly, binarization processing is carried out on an input picture, so that the gray value of a pixel point positioned in a target region of the input picture in the binarization picture is 1, the gray value of a pixel point positioned outside the target region is 0, then, convolution processing is carried out on the binarization picture, so that the gray value of each pixel point of the convolution picture represents the number of the pixel points adjacent to the pixel point and positioned in the target region, then, threshold segmentation is carried out on the convolution picture, so that each pixel point of the threshold region is provided with at least three pixel points adjacent to the pixel point and positioned in the target region, finally, the intersection of the threshold region and the target region of the input picture is calculated, and the pixel points which are not positioned in the intersection can be understood as isolated points or concave convex points at the edge of the target region, so that the points are removed, and the effective filtering of the edge of the target region is realized while the whole target region is not influenced.
Description
Technical Field
The application belongs to the technical field of machine vision detection, and particularly relates to a region filtering method, a device, electronic equipment and a computer readable storage medium.
Background
The development and application of machine vision drive the intelligent development of industrial production. The application of machine vision in the industrial field avoids many problems such as low accuracy, easy error, continuous work and fatigue, and is time-consuming and labor-consuming, which are encountered in the prior manual visual inspection. The application of machine vision solves these problems and improves the efficiency of inspection and quality of the product.
The core of the machine vision is the processing of digital pictures, and the quality of the picture processing plays a key role in the detection or positioning of the machine vision. Random noise interference can be encountered in the process of collecting or transmitting the picture, so that difficulties are brought to subsequent picture processing, such as picture positioning, segmentation, feature extraction and the like. Therefore, various filters such as dynamic average filtering, gaussian filtering, median filtering and the like are invented for solving noise interference of pictures.
In practical applications, these filters are only suppressing against noise pollution alone. However, if noise is at the edge of the target area, the conventional filter will affect the whole target area, and if only the isolated points or the concave-convex points of the edge zone of the target area are concerned, the conventional filter will not work well.
Disclosure of Invention
In view of the foregoing, the present application provides a region filtering method, apparatus, electronic device, and computer-readable storage medium.
The technical scheme adopted by the application is as follows:
as a first aspect of the present application, there is provided a region filtering method including:
performing binarization processing on an input picture to obtain a binarized picture with the same size as the input picture, wherein in the binarized picture, the gray value of a pixel point positioned in a target area of the input picture is 1, and the gray value of a pixel point positioned outside the target area is 0;
the binarization picture is subjected to convolution processing through the following convolution check, so that a convolution picture is obtained, and the gray value of each pixel point of the convolution picture represents the number of the pixel points adjacent to the pixel point and positioned in the target area:
threshold segmentation is carried out on the convolution picture to obtain a threshold region, wherein each pixel point of the threshold region is provided with at least three pixel points which are adjacent to the pixel point and are positioned in the target region;
and solving an intersection between the threshold region and a target region of the input picture, and removing pixel points which are not in the intersection in the target region.
As a second aspect of the present application, there is provided a zone filtration device comprising:
the device comprises a binarization processing module, a display module and a display module, wherein the binarization processing module is used for performing binarization processing on an input picture to obtain a binarized picture with the same size as the input picture, in the binarized picture, the gray value of a pixel point positioned in a target area of the input picture is 1, and the gray value of a pixel point positioned outside the target area is 0;
the convolution processing module is used for carrying out convolution processing on the binarized picture through the following convolution check to obtain a convolution picture, and the gray value of each pixel point of the convolution picture represents the number of the pixel points adjacent to the pixel point and positioned in the target area:
the threshold segmentation module is used for carrying out threshold segmentation on the convolution picture to obtain a threshold region, and each pixel point of the threshold region is provided with at least three pixel points adjacent to the pixel point and positioned in the target region;
and the noise filtering module is used for solving an intersection between the threshold area and a target area of the input picture and removing pixel points which are not in the intersection in the target area.
As a third aspect of the present application, there is provided an electronic device comprising a storage module comprising instructions loaded and executed by a processor, which instructions, when executed, cause the processor to perform a region filtering method of the first aspect described above.
As a fourth aspect of the present application, there is provided a computer-readable storage medium storing one or more programs which, when executed by a processor, implement a region filtering method of the first aspect described above.
According to the method, the input picture is subjected to binarization processing, the gray value of a pixel point in the target area of the input picture is 1, the gray value of a pixel point outside the target area is 0, then the binarization picture is subjected to convolution processing, the gray value of each pixel point of the convolution picture represents the number of the pixel points adjacent to the pixel point and positioned in the target area, then the convolution picture is subjected to threshold segmentation, each pixel point of the threshold area is provided with at least three pixel points adjacent to the pixel point and positioned in the target area, finally the intersection of the threshold area and the target area of the input picture is obtained, and the pixel points which are not in the intersection can be understood as isolated points or concave-convex points of the edge of the target area, so that the points are removed, and the effective filtering of the edge of the target area is realized while the whole target area is not influenced.
Drawings
The application is described in detail below with reference to the attached drawings and detailed description:
FIG. 1 is a flow chart of a region filtering method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a zone filtration device according to an embodiment of the present application;
fig. 3 is a schematic diagram of an electronic device according to an embodiment of the present application;
FIG. 4 is a schematic diagram of an input picture according to an embodiment of the present application;
FIG. 5 is a schematic diagram of an input image after merging and binarization processing according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a binarized picture according to an embodiment of the present application after convolution processing;
fig. 7 is a schematic diagram of a local detail of an input image after intersecting a threshold region according to an embodiment of the present application.
Detailed Description
Embodiments of the present application will be described below with reference to the drawings. The embodiments described in the present specification are not intended to be exhaustive or to represent the only embodiments of the present application. The following examples are presented for clarity of illustration of the application of the present patent and are not intended to limit the embodiments thereof. It will be apparent to those skilled in the art that various changes and modifications can be made in the embodiment described, and that all the obvious changes or modifications which come within the spirit and scope of the application are deemed to be within the scope of the application.
As shown in fig. 1, an embodiment of the present application provides a region filtering method, including:
s101, combining a plurality of target areas in an input picture to obtain a combined target area.
In this embodiment, the target area is a defect area region determined by visual detection in the input picture, and in an actual scene, the input picture often has a plurality of defect areas region, and one defect area region may have a plurality of connected areas, so that in order to facilitate the subsequent binarization processing, the plurality of defect areas region need to be combined in step S101. Of course, for a scene in which there is only one defective area in the input picture and the defective area has only one connected area, the defective area is the target area, and the merging is not required, i.e. step S101 may be omitted.
In this embodiment, a Halcon merge connected domain operator unit 1 (RegionErr, regionUnion) is used to merge multiple target regions, region err, in the input picture, where region union represents the merged target region.
S102, performing binarization processing on the input picture to obtain a binarized picture with the same size as the input picture, wherein in the binarized picture, the gray value of a pixel point positioned in a target area of the input picture is 1, and the gray value of a pixel point positioned outside the target area is 0.
In this embodiment, a binarization process is performed on an input picture by using a region-to-binarization operator region_to_bin (RegionUnion, binImage, FGray, BGray, W, L) of Halcon, where BinImage represents a binarized picture, a gray value fgray=1 of a pixel located inside a target region of the input picture, a gray value bgray=0 of a pixel located outside the target region, W and L represent the width and length of the picture, and the size of the pixel is consistent with that of the input picture.
S103, carrying out convolution processing on the binarized picture through the following convolution check to obtain a convolution picture, wherein the gray value of each pixel point of the convolution picture represents the number of the pixel points adjacent to the pixel point and positioned in the target area:
in this embodiment, a convolution operator convol_image (BinImage, imageConvol, filterMask, margin) of Halcon is used to perform convolution processing on the binarized picture, where ImageConvol represents the convolved picture, filterMask represents the convolution kernel, margin represents an edge processing mode, and there are general basic processing modes including 'mirrored', 'cyclic', 'continuous', 0, and a default value of 0, i.e., margin=0 is selected.
S104, performing threshold segmentation on the convolution picture to obtain a threshold region, wherein each pixel point of the threshold region is provided with at least three adjacent pixel points which are positioned in the target region.
In this embodiment, a threshold segmentation operator threshold (ImageConvol, regionResult, min, max) of Halcon is used to perform threshold segmentation on the convolution image ImageConvol, where region result represents a threshold region, which is a set of at least three pixels located in adjacent points of the target region, min and Max are respectively a lower limit and an upper limit of the gray value of the selected pixels, and the purpose of min=3, max=255, and Min is set to 3 is to screen out pixels having at least three adjacent points located in the target region.
S105, intersection is obtained between the threshold area and the target area of the input picture, and pixel points which are not in the intersection in the target area are removed.
In this embodiment, intersection operator intersection (RegionResult, regionErr, outRegion) of Halcon is used to intersect the threshold region result with the target region err of the input picture.
Fig. 4 shows an example of an input picture, in which a white outline region is a defective region, after merging and binarizing in steps 101 and 102, see fig. 5, and then convolving in step 103, see fig. 6, and fig. 7 shows a partial detail picture of the input picture after intersecting in step S105, in which black dots at edges represent pixel points not in the intersection.
As can be seen from the foregoing, according to the area filtering method provided by the embodiment, binarization processing is performed on an input image, so that the gray value of a pixel point located inside a target area of the input image in the binarized image is 1, the gray value of a pixel point located outside the target area is 0, then convolution processing is performed on the binarized image, so that the gray value of each pixel point of the convolved image represents the number of pixels adjacent to the pixel point and located inside the target area, then threshold segmentation is performed on the convolved image, so that each pixel point of the threshold area has at least three pixels adjacent to the pixel point and located inside the target area, finally, the intersection of the threshold area and the target area of the input image is obtained, and the pixel points which are not located in the intersection can be understood as isolated points or concave-convex points of the edge of the target area, so that the points are removed, and effective filtering of the edge of the target area is realized while the whole target area is not affected.
The area filtering apparatus of one or more embodiments of the present application will be described in detail below. Those skilled in the art will appreciate that these filtering means may be constructed using commercially available hardware components configured by the steps taught by the present solution. Fig. 2 shows a region filtering apparatus according to an embodiment of the present application, and as shown in fig. 2, the filtering apparatus includes a merging module 11, a binarization processing module 12, a convolution processing module 13, a threshold segmentation module 14, and a noise filtering module 15.
The merging module 11 is configured to merge multiple target areas in the input picture to obtain a merged target area.
In this embodiment, the target area is a defect area region determined by visual detection in the input picture, and in an actual scene, the input picture often has a plurality of defect areas region, and one defect area region may have a plurality of connected areas, so that in order to facilitate the subsequent binarization processing, the plurality of defect areas region need to be combined in step S101. Of course, for a scene in which there is only one defective area in the input picture and the defective area has only one connected area, the defective area is the target area, and the merging is not required, that is, the merging module 11 may be omitted.
In this embodiment, a Halcon merge connected domain operator unit 1 (RegionErr, regionUnion) is used to merge multiple target regions, region err, in the input picture, where region union represents the merged target region.
The binarization processing module 12 is configured to perform binarization processing on an input picture to obtain a binarized picture with the same size as the input picture, where in the binarized picture, a gray value of a pixel located inside a target area of the input picture is 1, and a gray value of a pixel located outside the target area is 0.
In this embodiment, a region-to-binarization operator of Halcon is used
The region_to_bin (RegionUnion, binImage, FGray, BGray, W, L) performs binarization processing on the input picture, wherein BinImage represents a binarized picture, gray values fgray=1 of pixels located inside a target region of the input picture, gray values bgray=0 of pixels located outside the target region, W and L represent the width and length of the picture, and the size of the input picture is consistent.
The convolution processing module 13 is configured to perform convolution processing on the binarized picture by performing convolution check to obtain a convolution picture, where a gray value of each pixel point of the convolution picture represents a number of pixel points adjacent to the pixel point and located inside the target area:
in this embodiment, a convolution operator convol_image (BinImage, imageConvol, filterMask, margin) of Halcon is used to perform convolution processing on the binarized picture, where ImageConvol represents the convolved picture, filterMask represents the convolution kernel, margin represents an edge processing mode, and there are general basic processing modes including 'mirrored', 'cyclic', 'continuous', 0, and a default value of 0, i.e., margin=0 is selected.
The threshold segmentation module 14 is configured to perform threshold segmentation on the convolution image to obtain a threshold region, where each pixel of the threshold region has at least three pixels adjacent to the pixel and located inside the target region.
In this embodiment, a threshold segmentation operator threshold (ImageConvol, regionResult, min, max) of Halcon is used to perform threshold segmentation on the convolution image ImageConvol, where region result represents a threshold region, which is a set of at least three pixels located in adjacent points of the target region, min and Max are respectively a lower limit and an upper limit of the gray value of the selected pixels, and the purpose of min=3, max=255, and Min is set to 3 is to screen out pixels having at least three adjacent points located in the target region.
The noise filtering module 15 is configured to intersect the threshold region with a target region of the input picture, and remove pixels in the target region that are not in the intersection.
In this embodiment, intersection operator intersection (RegionResult, regionErr, outRegion) of Halcon is used to intersect the threshold region result with the target region err of the input picture.
Fig. 4 shows an example of an input picture, in which a white outline region is a defective region, after merging and binarizing in steps 101 and 102, see fig. 5, and then convolving in step 103, see fig. 6, and fig. 7 shows a partial detail picture of the input picture after intersecting in step S105, in which black dots at edges represent pixel points not in the intersection.
In summary, the region filtering apparatus provided in the above embodiments may perform the region filtering method provided in each of the above embodiments.
Similar to the above concept, the structure of the area filtering apparatus shown in fig. 2 may be implemented as an electronic device, and fig. 3 is a schematic block diagram of the structure of the electronic device according to the embodiment of the present application.
The electronic device illustratively includes a memory module 21 and a processor 22, the memory module 21 including instructions loaded and executed by the processor 22, which when executed, cause the processor 22 to perform the steps according to various exemplary embodiments of the present application described in the above-described one area filtering methods section of this specification.
It should be appreciated that the processor 22 may be a central processing unit (CentralProcessingUnit, CPU), and that the processor 22 may also be other general purpose processors, digital signal processors (DigitalSignalProcessor, DSP), application specific integrated circuits (ApplicationSpecificIntegratedCircuit, ASIC), field programmable gate arrays (Field-ProgrammableGateArray, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Embodiments of the present application also provide a computer-readable storage medium storing one or more programs that, when executed by a processor, implement the steps described in the above section of a region filtering method according to various exemplary embodiments of the present application.
Those of ordinary skill in the art will appreciate that all or some of the steps, systems, functional modules/units in the apparatus, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between the functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer-readable storage media, which may include computer-readable storage media (or non-transitory media) and communication media (or transitory media).
The term computer-readable storage medium includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer-readable storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
By way of example, the computer readable storage medium may be an internal storage unit of the electronic device of the foregoing embodiments, such as a hard disk or a memory of the electronic device. The computer readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk provided on the electronic device, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash memory card (FlashCard), or the like.
The electronic device and the computer readable storage medium provided in the foregoing embodiments perform binarization processing on an input picture, so that a gray value of a pixel point located inside a target area of the input picture in the binarized picture is 1, and a gray value of a pixel point located outside the target area is 0, then perform convolution processing on the binarized picture, so that the gray value of each pixel point of the convolved picture represents the number of pixel points adjacent to the pixel point and located inside the target area, then perform threshold segmentation on the convolved picture, so that each pixel point of the threshold area has at least three pixel points adjacent to the pixel point and located inside the target area, finally calculate an intersection of the threshold area and the target area of the input picture, and the pixel points not located in the intersection can be understood as isolated points or concave-convex points at the edge of the target area, so that the points are removed, thereby realizing effective filtering on the edge of the target area while not affecting the whole target area.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A method of region filtering comprising:
performing binarization processing on an input picture to obtain a binarized picture with the same size as the input picture, wherein in the binarized picture, the gray value of a pixel point positioned in a target area of the input picture is 1, and the gray value of a pixel point positioned outside the target area is 0;
the binarization picture is subjected to convolution processing through the following convolution check, so that a convolution picture is obtained, and the gray value of each pixel point of the convolution picture represents the number of the pixel points adjacent to the pixel point and positioned in the target area:
threshold segmentation is carried out on the convolution picture to obtain a threshold region, wherein each pixel point of the threshold region is provided with at least three pixel points which are adjacent to the pixel point and are positioned in the target region;
and solving an intersection between the threshold region and a target region of the input picture, and removing pixel points which are not in the intersection in the target region.
2. The method of area filtering of claim 1, further comprising:
and combining the multiple target areas in the input picture before binarizing the input picture to obtain combined target areas.
3. The method according to claim 2, wherein the merging the plurality of detection areas in the input picture into one target area, further comprises:
and merging a plurality of detection areas in the input picture into a target area by adopting a merged connected area operator of Halcon.
4. The method according to claim 1, wherein the binarizing the input picture further comprises:
and carrying out binarization processing on the input picture by adopting a region-to-binarization operator of Halcon.
5. The area filtering method according to claim 1, wherein the convoluting the binarized picture is performed by convoluting:
and carrying out convolution processing on the binarized picture by adopting a convolution operator of Halcon.
6. The method according to claim 1, wherein said thresholding said convolved picture further comprises:
and carrying out threshold segmentation on the convolution picture by adopting a threshold segmentation operator of Halcon.
7. The method according to claim 1, wherein intersecting the threshold region with the target region of the input picture, further comprises:
and adopting a Halcon intersection operator to intersect the threshold region with the target region of the input picture.
8. A zone filtration device comprising:
the device comprises a binarization processing module, a display module and a display module, wherein the binarization processing module is used for performing binarization processing on an input picture to obtain a binarized picture with the same size as the input picture, in the binarized picture, the gray value of a pixel point positioned in a target area of the input picture is 1, and the gray value of a pixel point positioned outside the target area is 0;
the convolution processing module is used for carrying out convolution processing on the binarized picture through the following convolution check to obtain a convolution picture, and the gray value of each pixel point of the convolution picture represents the number of the pixel points adjacent to the pixel point and positioned in the target area:
the threshold segmentation module is used for carrying out threshold segmentation on the convolution picture to obtain a threshold region, and each pixel point of the threshold region is provided with at least three pixel points adjacent to the pixel point and positioned in the target region;
and the noise filtering module is used for solving an intersection between the threshold area and a target area of the input picture and removing pixel points which are not in the intersection in the target area.
9. An electronic device comprising a memory module including instructions loaded and executed by a processor, which when executed, cause the processor to perform a region filtering method according to any of claims 1-7.
10. A computer readable storage medium storing one or more programs, which when executed by a processor, implement a region filtering method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311256341.0A CN117197006B (en) | 2023-09-27 | 2023-09-27 | Region filtering method, region filtering device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311256341.0A CN117197006B (en) | 2023-09-27 | 2023-09-27 | Region filtering method, region filtering device, electronic equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117197006A true CN117197006A (en) | 2023-12-08 |
| CN117197006B CN117197006B (en) | 2024-05-10 |
Family
ID=88992323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311256341.0A Active CN117197006B (en) | 2023-09-27 | 2023-09-27 | Region filtering method, region filtering device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117197006B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019104767A1 (en) * | 2017-11-28 | 2019-06-06 | 河海大学常州校区 | Fabric defect detection method based on deep convolutional neural network and visual saliency |
| WO2019134298A1 (en) * | 2018-01-02 | 2019-07-11 | 武汉斗鱼网络科技有限公司 | Image processing method, appapatus, electronic device and storage medium |
| CN110766736A (en) * | 2019-10-29 | 2020-02-07 | 京东方科技集团股份有限公司 | Defect detection method, defect detection device, electronic equipment and storage medium |
| CN112330688A (en) * | 2020-11-02 | 2021-02-05 | 腾讯科技（深圳）有限公司 | Image processing method and device based on artificial intelligence and computer equipment |
| CN112464731A (en) * | 2020-11-03 | 2021-03-09 | 南京理工大学 | Traffic sign detection and identification method based on image processing |
| CN113724257A (en) * | 2021-11-01 | 2021-11-30 | 常州市宏发纵横新材料科技股份有限公司 | Carbon plate gray stain detection method, computer equipment and storage medium |
| CN114119554A (en) * | 2021-11-29 | 2022-03-01 | 哈尔滨工业大学 | A method and device for surface micro-defect detection based on convolutional neural network |
| CN114155241A (en) * | 2022-01-28 | 2022-03-08 | 浙江华睿科技股份有限公司 | Foreign matter detection method and device and electronic equipment |
| CN115082489A (en) * | 2022-08-23 | 2022-09-20 | 江苏永银化纤有限公司 | Colored silk evaluation method |
-
2023
- 2023-09-27 CN CN202311256341.0A patent/CN117197006B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019104767A1 (en) * | 2017-11-28 | 2019-06-06 | 河海大学常州校区 | Fabric defect detection method based on deep convolutional neural network and visual saliency |
| WO2019134298A1 (en) * | 2018-01-02 | 2019-07-11 | 武汉斗鱼网络科技有限公司 | Image processing method, appapatus, electronic device and storage medium |
| CN110766736A (en) * | 2019-10-29 | 2020-02-07 | 京东方科技集团股份有限公司 | Defect detection method, defect detection device, electronic equipment and storage medium |
| CN112330688A (en) * | 2020-11-02 | 2021-02-05 | 腾讯科技（深圳）有限公司 | Image processing method and device based on artificial intelligence and computer equipment |
| WO2022089236A1 (en) * | 2020-11-02 | 2022-05-05 | 腾讯科技（深圳）有限公司 | Image processing method apparatus based on artificial intelligence, and computer device and storage medium |
| CN112464731A (en) * | 2020-11-03 | 2021-03-09 | 南京理工大学 | Traffic sign detection and identification method based on image processing |
| CN113724257A (en) * | 2021-11-01 | 2021-11-30 | 常州市宏发纵横新材料科技股份有限公司 | Carbon plate gray stain detection method, computer equipment and storage medium |
| CN114119554A (en) * | 2021-11-29 | 2022-03-01 | 哈尔滨工业大学 | A method and device for surface micro-defect detection based on convolutional neural network |
| CN114155241A (en) * | 2022-01-28 | 2022-03-08 | 浙江华睿科技股份有限公司 | Foreign matter detection method and device and electronic equipment |
| CN115082489A (en) * | 2022-08-23 | 2022-09-20 | 江苏永银化纤有限公司 | Colored silk evaluation method |
Non-Patent Citations (5)
| Title |
|---|
| DONG WANG ET AL.: "The iterative convolution–thresholding method (ICTM) for image segmentation", 《PATTERN RECOGNITION》, vol. 130, 31 October 2022 (2022-10-31), pages 1 - 12 * |
| NIHAAL MEHTA ET AL.: "Repeatability of binarization thresholding methods for optical coherence tomography angiography image quantification", 《SCIENTIFIC REPORTS》, 21 September 2020 (2020-09-21), pages 1 - 11 * |
| 杨曦等: "一种利用图像角点和边缘信息的阈值分割方法", 《红外技术》, no. 02, 20 February 2008 (2008-02-20), pages 95 - 98 * |
| 程艳: "高密度柔性IC基板外观精密检测算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 01, 15 January 2023 (2023-01-15), pages 135 - 815 * |
| 郭忠峰等: "结合最小均方差滤波和目标灰度的边缘检测", 《机械工程与自动化》, no. 04, 15 August 2020 (2020-08-15), pages 18 - 20 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117197006B (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670500B (en) | Text region acquisition method and device, storage medium and terminal equipment | |
| CN111583157B (en) | Image processing method, system and computer readable storage medium | |
| CN110766736B (en) | Defect detection method, defect detection device, electronic equipment and storage medium | |
| US11379988B2 (en) | Method and apparatus for extracting edge of object in depth image and computer readable storage medium | |
| CN110136069B (en) | Text image correction method and device and electronic equipment | |
| US20190206043A1 (en) | Method and system for detection of in-panel mura based on hough transform and gaussian fitting | |
| CN110782424B (en) | Image fusion method and device, electronic equipment and computer readable storage medium | |
| CN113034447B (en) | Edge defect detection method and device | |
| CN105096330A (en) | Image processing method capable of automatically recognizing pure-color borders, system and a photographing terminal | |
| CN111696064A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
| CN109934781B (en) | Image processing method, image processing device, terminal equipment and computer readable storage medium | |
| CN108074238B (en) | Hough transform and Gaussian fitting-based in-plane mura detection method and detection system | |
| CN115861622A (en) | Image comparison method, device, equipment and storage medium | |
| CN117197006B (en) | Region filtering method, region filtering device, electronic equipment and computer readable storage medium | |
| CN118379317B (en) | Glass fiber cloth edge identification method, equipment and storage medium | |
| CN111126248A (en) | Method and device for identifying shielded vehicle | |
| CN113378847B (en) | Character segmentation method, system, computer device and storage medium | |
| CN114596210A (en) | Noise estimation method, device, terminal equipment and computer readable storage medium | |
| CN111508017B (en) | Method and system for positioning mark center with weak contrast | |
| CN116309583B (en) | Method and system for detecting display screen dent defect | |
| CN118351059A (en) | Circuit board detection method, device, computer equipment and storage medium | |
| CN115862044A (en) | Method, apparatus, and medium for extracting target document part from image | |
| CN112528741B (en) | State identification method and device for transformer substation pressure plate | |
| CN115830049A (en) | Corner point detection method and device | |
| CN112652004A (en) | Image processing method, device, equipment and medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |