CN114219863A - Seal detection method based on re-opening operation, storage medium and electronic device - Google Patents
Seal detection method based on re-opening operation, storage medium and electronic device Download PDFInfo
- Publication number
- CN114219863A CN114219863A CN202111540162.0A CN202111540162A CN114219863A CN 114219863 A CN114219863 A CN 114219863A CN 202111540162 A CN202111540162 A CN 202111540162A CN 114219863 A CN114219863 A CN 114219863A
- Authority
- CN
- China
- Prior art keywords
- image
- seal
- stamp
- detection method
- color
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000005260 corrosion Methods 0.000 claims abstract description 11
- 230000007797 corrosion Effects 0.000 claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000000873 masking effect Effects 0.000 claims description 7
- 230000006835 compression Effects 0.000 claims description 4
- 238000007906 compression Methods 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 238000007689 inspection Methods 0.000 abstract description 4
- 230000005540 biological transmission Effects 0.000 abstract description 2
- 238000005530 etching Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003628 erosive effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20068—Projection on vertical or horizontal image axis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention claims a seal detection method based on a rebuilding operation, which relates to the technical field of digital image processing and target detection, and comprises the steps of converting an RGB color space of a seal image into an HSV color space, and performing a red mask in the HSV color space to obtain a binary mask image; removing noise in the binary mask image by utilizing a reconstruction opening operation to obtain a de-noised seal image; filling holes by adopting a closed operation, carrying out corrosion operation on the de-noised seal image, and then expanding to obtain a hole filling image; and carrying out boundary projection on the hole filling image, and determining the maximum distance part as the position of the seal. The method can automatically detect the specific position coordinates of the seal in the picture, further compress the index map of the detected seal, adjust the color level, and solve the problems of high labor cost, low inspection efficiency and time consumption of network transmission. The method has better robustness and can better detect under various environments.
Description
Technical Field
The invention relates to the technical field of digital image processing and target detection, in particular to a seal detection method.
Background
In the paperless implementation process of government affairs, a large number of certificates, contracts, government documents and reports are involved, and the various electronic documents are necessary to be used in official seals. At present, the inspection and rechecking of official seals in data pictures adopt a manual inspection mode, which not only consumes a large amount of manpower, but also has lower efficiency and takes longer time for work.
Most of the prior art detect the seal image by a deep learning method, but the deep learning method needs a large amount of data to train a detection model, and the noise on the image is too simple to process or not processed at all. But the presence of noise can interfere with the results of the detection. In order to solve the interference of noise on a detection result, the invention provides a seal detection process based on a rebuilding operation, and aims to quickly detect the specific position of a seal in a picture.
As disclosed in publication No.: the chinese patent of invention CN104732227B, "a license plate fast positioning method based on definition and brightness evaluation", discloses a license plate fast positioning method based on definition and brightness evaluation, which comprises the following steps: performing a noise and sharpness based sharpness evaluation on the input image; if the definition is insufficient, carrying out gradient sharpening, and if the definition is too high, carrying out Gaussian blur processing; converting the RGB image into a gray image; evaluating the brightness of the gray scale image; if the brightness is abnormal, performing illumination normalization processing; extracting a vertical edge in the image through a Scharr operator; carrying out local adaptive threshold processing; filtering noise through morphological processing, and fusing vertical edges into a connected region; and carrying out region marking on the connected region, and screening according to the characteristics of the Chinese license plate to obtain a license plate region.
Disclosure of Invention
The invention provides a simple and efficient seal detection method based on the re-opening operation, aiming at the problems that the prior art seal image detection method needs a large amount of data to train a detection model, and the image noise is not enough to be processed.
The invention provides a seal detection method based on reconstruction opening operation, which comprises the steps of converting an RGB color space of a seal image into an HSV color space, and performing a red mask in the HSV color space to obtain a binary mask image; removing noise in the binary mask image by utilizing a reconstruction opening operation to obtain a de-noised seal image; filling holes by adopting a closed operation, carrying out corrosion operation on the de-noised seal image, and then expanding to obtain a hole filling image; and performing boundary projection on the hole filling image, determining the maximum space part as the position of the seal to obtain a detection image, performing index map compression on the detection image, and adjusting the color level to obtain the seal image.
Further, intersection of the image obtained by each expansion and the red seal masking image is obtained, and if the intersection obtaining result is not changed, the expansion is stopped. Reconstruction of models using morphology
According to the formula
And removing noise of the stamp image, wherein I represents the acquired stamp original image, and (I theta nB) represents that the stamp original image is etched for n times by taking B as a template.
The red mask is specifically: obtaining an image I of an HSV color spacehsvPixel point value I at (x, y) positionhsv(x, y) corresponding to a value of I on the H, S, V channelh(x,y)，Is(x,y)，Iv(x, y) according to the formula:
to IhsvThe pixel values of the red mask map at the coordinate point (x, y) are obtained, and the pixel values of all the points are synthesized to obtain a binary mask map
The removing noise by using the reconstruction opening operation specifically includes: binary image of red mask
Carrying out corrosion operation, and then carrying out corrosion on the binary image
Continuously expanding until the nth geodetic expansion result is equal to the (n-1) th geodetic expansion result, i.e. the expansion is performed
Wherein the content of the first and second substances,
the result of the nth geodetic expansion of the binary image F representing the geodetic expansion is shown.
According to the formula:
filling the outer edge of the image by adopting a closed operation to obtain a closed operation image matrix
Wherein, represents the closing operation,
indicating an expansion operation and theta indicates an erosion operation. According to the formula:
calculating the mask image of the (x, y) point to obtain the final mask image
Will be provided with
And performing matrix dot multiplication with the stamp original image I to obtain a final detection image. Performing boundary projection on the picture, and projecting the image in the directions of the x axis and the y axis respectively to form two images about the x axis and the y axisThe range with the largest span in the oscillogram is selected, namely the range of the image corresponding to the x axis and the y axis. Projecting the closed operation image to the x direction according to the formula:
determining the projection range of the X-direction according to the formula:
yrange＝(ymin,ymax) The range of the projection in the y-direction is obtained.
Further, the stamp index map compression method comprises the steps that a color table is attached to the index map, each position value of an image pixel is set to be between the number of colors, the position value represents the index value of the pixel in the color plate corresponding to the color, and the color of the corresponding image is found in the color plate according to the index value; the seal color level adjusting method comprises the steps of dividing a seal image into a plurality of sub-blocks, carrying out histogram equalization processing on the sub-blocks, and uniformly distributing the gray level of the image in all color dynamic ranges.
Further, the present invention also claims a computer-readable storage medium, on which a computer program is stored, which can be loaded and executed by a processor to perform the seal detection method according to any one of the above-mentioned embodiments of the present invention.
Further, the present invention also claims an electronic device, which includes: one or more processors; a memory; one or more application programs stored in the memory and configured to be loaded and executed by the one or more processors so as to perform the seal detection method of any of the above aspects of the present invention.
The seal detection method based on the rebuilding operation can quickly and accurately detect the seal in the picture and obtain the specific position, has simple and efficient operation and good robustness, and can quickly and effectively detect the seal under various environments.
Compared with the prior art, the seal detection method based on the re-opening operation has the following characteristics: the method can automatically detect the specific position coordinates of the seal in the picture, and solves the problems of high labor cost and low inspection efficiency. The method has better robustness and can better detect under various environments.
Drawings
In order to 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 introduced, and it is obvious that the drawings in the following description are some embodiments of the present invention.
FIG. 1 is a flow chart of the present invention based on a rebuild operation;
FIG. 2 is a diagram showing the seal detection obtained by the method of the present invention.
Detailed Description
In order to make the technical solution of the present invention better understood by those skilled in the art, the technical solution of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be obtained by a person of ordinary skill in the art without any creative effort based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart of the invention based on the restart operation, and the method for detecting a stamp based on the restart operation includes the following steps:
stamp picture red mask. Converting the RGB color space into HSV color space, and performing red masking in the HSV color space to obtain an initial red seal masking result;
noise is removed using a re-opening operation. And removing noise outside the seal by utilizing a reconstruction opening operation on the initial red seal masking image obtained from the red mask result to obtain a de-noised seal image.
The hole is filled with a closing operation. The outer edge of the seal is not a closed curve, the seal is closed, the de-noising seal image is corroded firstly, and then the corroded result is expanded to obtain a closed operation image.
And carrying out boundary projection on the closed operation image, and determining the maximum distance part as the position of the seal.
And converting the RGB color space of the picture into HSV color space, and selecting a red color range in the HSV color space. And (3) the selected red color range has noise, firstly, the image is corroded once or for multiple times, then, the corroded result is expanded for multiple times, the intersection of the image obtained by each expansion and the red seal masking image is obtained, and if the result is not changed, the expansion is stopped.
Further according to the formula
The reconstruction operation removes noise except the stamp image by using a morphological reconstruction model, wherein I represents the acquired stamp original image, and (I theta nB) represents that the stamp original image is corroded for n times by using B as a template,
for the morphological reconstruction model, it is indicated that the image expansion iterates repeatedly until a steady state is reached. Performing boundary projection on the picture is to perform affine transformation on the picture, and the height after transformation is a fixed pixel. And the step of projecting the boundary of the picture further comprises the step of projecting the image to the x-axis direction and the y-axis direction respectively to form two oscillograms related to the x-axis and the y-axis, and selecting the range with the maximum span larger than 0 in the oscillograms, namely the range of the image corresponding to the x-axis and the y-axis.
The following is a detailed description of the practice of the invention by way of specific examples.
Acquiring an original seal image I as an image of an RGB (Red-Green-Blue) color space, converting the RGB color space into an HSV (Hue, Saturation, Value) color space, and enabling the converted image I of the HSV color spacehsv. To IhsvPerforming red mask, setting the upper and lower limits of red in three channels of HSV space as
(the upper and lower limits of the red color in the HSV color subscale are shown in Table 1).
Table 1: colour sub-component table
Obtaining an image I of an HSV color spacehsvPixel point value I at (x, y) positionhsv(x, y) corresponding to a value of I on the H, S, V channelh(x,y)，Is(x,y)，Iv(x, y). According to the formula:
to IhsvPerforming a red mask results in a mask map in which,
representing the pixel value of the mask map at the (x, y) position. Thereby obtaining the result of the whole mask
It is obvious that
Is a binary map.
Noise is removed using a re-opening operation. In the re-opening operation, the formula is first called:
binary image of red mask
Performing n times of etching operations (the number of times of etching can be set according to experience) to obtain a binary image after etching
Wherein, theta represents corrosion operation, and B is a corrosion template. Then, the product is processedFor the binary image after corrosion
(as denoted F) is subjected to geodetic expansion. Calling a formula:
performing 1 geodetic expansion, wherein F represents a binary map of the geodetic expansion, b represents a template of the geodetic expansion,
denotes the inflation operation, and denotes the union. The n geodesic expansions are defined as:
to pair
Continuously expanding until
Until now.
The following is pseudo code:
do{
c is the final result of the rebuild operation, order
Obtaining a reconstructed on-manipulation image
The hole is filled with a closing operation. The outer edge of the stamp is not a closed curve and a closing operation is required to fill the outer edge. According to the formula:
wherein, represents the closing operation,
indicating an expansion operation and theta indicates an erosion operation. Obtaining a closed operation image matrix of the result after the closed operation
Carrying out boundary projection on the closed operation image, wherein the maximum distance part is the position of the seal, and projecting the closed operation image to the x direction according to the following formula:
the projection range in the x direction is determined. The extent x of the projection in the x-directionrangeExpressed as: x is the number ofrange＝(xmin,xmax)。
Similarly, according to the formula:
yrange＝(ymin,ymax) The range of the projection in the y-direction is available.
The final stamp image thus obtained is:
wherein x ismin:xmaxExpress get
Matrix from xminTo xmaxColumn, ymin:ymaxExpress get
Matrix from yminTo ymaxAnd (6) rows. The resulting final mask map
Is composed of
The sub-matrix of (2). Final mask image
And performing matrix dot multiplication with the seal original image I to obtain a final detection result image as follows:
the method can be adopted for compressing the stamp index map, the index map is attached with a color plate or a color table and corresponds to 256 colors, then each position value of an image pixel is between 0 and 255, a numerical value represents an index value of the color of the pixel corresponding to the color plate, and when the image is actually displayed, the color to be displayed can be found in the color plate by using the index, so that one pixel of the index map only needs 1 bit, and the storage space and the transmission bandwidth are greatly reduced compared with the original RGB image.
The method can be adopted for adjusting the color gradation of the seal, and compared with the whole seal picture, the condition of darkness appears in the detected local seal image area visually, and the method can adjust the color gradation of the image by a contrast limited self-adaptive histogram equalization method. Specifically, the stamp image is divided into a plurality of sub-blocks, histogram equalization processing is performed on the sub-blocks, and the gray level of the image is well distributed on all color dynamic ranges.
Fig. 2 is a stamp detection comparison diagram obtained by the method of the present invention, and it can be seen that the quality of the stamp image extracted by the method of the present invention is good, the consistency with the original image is good, and the definition is high.
The invention utilizes the series of processes to quickly and accurately detect the seal in the picture and give the specific position, has simple and efficient operation and good robustness, and can quickly and effectively detect the seal under various environments. The above-described embodiment is only one of the specific embodiments of the present invention, and general changes and substitutions by those skilled in the art within the technical scope of the present invention are included in the protection scope of the present invention.
Claims (10)
1. A seal detection method based on a re-opening operation is characterized by comprising the following steps: converting the RGB color space of the stamp image into HSV color space, and performing red masking in the HSV color space to obtain a binary mask image; removing noise in the binary mask image by utilizing a reconstruction opening operation to obtain a de-noised seal image; filling holes by adopting a closed operation, carrying out corrosion operation on the de-noised seal image, and then expanding to obtain a hole filling image; and performing boundary projection on the hole filling image, determining the maximum space part as the position of the seal to obtain a detection image, performing index map compression on the detection image, and adjusting the color level to obtain the seal image.
2. The stamp detection method according to claim 1, wherein the intersection of the hole filling image obtained by each expansion and the red stamp masking image is obtained, and the expansion is stopped if the intersection is not changed.
3. The stamp detection method according to claim 1, wherein the morphological reconstruction model is used
According to the formula
And removing noise of the stamp image, wherein F represents the acquired stamp original image, and (F theta nB) represents that the stamp original image is etched for n times by taking B as a template.
4. The stamp detection method according to claim 1, wherein said performing a red mask specifically is: obtaining an image I of an HSV color spacehsvPixel point value I at (x, y) positionhsv(x, y) corresponding to a value of I on the H, S, V channelh(x,y)，Is(x,y)，Iv(x, y) according to the formula:
to IhsvObtaining pixel values of the red mask image at the coordinate point (x, y), thereby obtaining a binary mask image
5. The stamp detection method according to claim 1, wherein the removing noise using the re-opening operation specifically comprises: binary image of red mask
Carrying out corrosion operation, and then carrying out corrosion on the binary image
Continuously expanding until the nth geodetic expansion result is equal to the (n-1) th geodetic expansion result, i.e. the expansion is performed
Wherein the content of the first and second substances,
the result of the nth geodetic expansion of the binary image F representing the geodetic expansion is shown.
6. The stamp detection method according to any one of claims 1-4, characterized in that according to the formula:
filling the outer edge of the image by adopting a closed operation to obtain a closed operation image matrix
Wherein, represents the closing operation,
represents an expansion operation, and Θ represents a corrosion operation; according to the formula:
calculating the mask image of the (x, y) point to obtain the final mask image
Will be provided with
And performing matrix dot multiplication with the stamp original image I to obtain a detection image.
7. The stamp detection method according to any one of claims 1 to 4, wherein the stamp index map compression method includes attaching a color table to the index map, setting each position value of a pixel of the image between the number of colors, the position value representing an index value of the corresponding color of the pixel on the color plate, and finding the color of the corresponding image in the color plate according to the index value; the seal color level adjusting method comprises the steps of dividing a seal image into a plurality of sub-blocks, carrying out histogram equalization processing on the sub-blocks, and uniformly distributing the gray level of the image in all color dynamic ranges.
8. The stamp detecting method according to any one of claims 1 to 4, wherein the closed operation image is projected in an x direction according to a formula:
determining the projection range of the X-direction of the X-ray image, and according to the formula:
yrange＝(ymin,ymax) The range of the projection in the y-direction is obtained.
9. A computer-readable storage medium, having stored thereon a computer program which can be loaded and run by a processor to perform the stamp detection method according to any one of claims 1 to 8.
10. An electronic device, comprising: one or more processors; a memory; one or more application programs stored in the memory and configured to be loaded and executed by the one or more processors so as to perform the seal detection method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111540162.0A CN114219863A (en) | 2021-12-16 | 2021-12-16 | Seal detection method based on re-opening operation, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111540162.0A CN114219863A (en) | 2021-12-16 | 2021-12-16 | Seal detection method based on re-opening operation, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114219863A true CN114219863A (en) | 2022-03-22 |
Family
ID=80702764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111540162.0A Pending CN114219863A (en) | 2021-12-16 | 2021-12-16 | Seal detection method based on re-opening operation, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114219863A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6728401B1 (en) * | 2000-08-17 | 2004-04-27 | Viewahead Technology | Red-eye removal using color image processing |
| CN106780438A (en) * | 2016-11-11 | 2017-05-31 | 广东电网有限责任公司清远供电局 | Defects of insulator detection method and system based on image procossing |
| CN110889374A (en) * | 2019-11-28 | 2020-03-17 | 中国建设银行股份有限公司 | Seal image processing method and device, computer and storage medium |
| CN112908451A (en) * | 2021-04-16 | 2021-06-04 | 千乘镜像(北京)科技有限公司 | Image processing method, apparatus and storage medium |
| CN113538498A (en) * | 2021-08-02 | 2021-10-22 | 傲雄在线(重庆)科技有限公司 | Seal image segmentation method based on local binarization, electronic device and readable storage medium |
-
2021
- 2021-12-16 CN CN202111540162.0A patent/CN114219863A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6728401B1 (en) * | 2000-08-17 | 2004-04-27 | Viewahead Technology | Red-eye removal using color image processing |
| CN106780438A (en) * | 2016-11-11 | 2017-05-31 | 广东电网有限责任公司清远供电局 | Defects of insulator detection method and system based on image procossing |
| CN110889374A (en) * | 2019-11-28 | 2020-03-17 | 中国建设银行股份有限公司 | Seal image processing method and device, computer and storage medium |
| CN112908451A (en) * | 2021-04-16 | 2021-06-04 | 千乘镜像(北京)科技有限公司 | Image processing method, apparatus and storage medium |
| CN113538498A (en) * | 2021-08-02 | 2021-10-22 | 傲雄在线(重庆)科技有限公司 | Seal image segmentation method based on local binarization, electronic device and readable storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 宋瑞祥: "基于机器视觉的步进梁出炉钢坯位置检测系统研究", 《中国优秀硕士学位论文全文数据库》 * |
| 赵永涛: "印鉴识别算法研究", 《中国优秀硕士学位论文全文数据库》 * |
| 雷玲等: "一种基于东北草场鼠洞的数字化检测方法", 《中国农业科技导报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111028213B (en) | Image defect detection method, device, electronic equipment and storage medium | |
| CN108805829B (en) | Image data processing method, device, equipment and computer readable storage medium | |
| US9042649B2 (en) | Color document image segmentation and binarization using automatic inpainting | |
| CN104063848A (en) | Enhancement method and device for low-illumination image | |
| WO2019041842A1 (en) | Image processing method and device, storage medium and computer device | |
| US20190266395A1 (en) | Method and device for segmenting lines in line chart | |
| CN104574328A (en) | Color image enhancement method based on histogram segmentation | |
| CN109919871A (en) | Fuzzy core estimation method based on image and fuzzy core mixed constraints | |
| CN110569774B (en) | Automatic line graph image digitalization method based on image processing and pattern recognition | |
| CN111489322A (en) | Method and device for adding sky filter to static picture | |
| CN114022383A (en) | Moire pattern removing method and device for character image and electronic equipment | |
| CN113538498B (en) | Seal image segmentation method based on local binarization, electronic device and readable storage medium | |
| JP2020197915A (en) | Image processing device, image processing method, and program | |
| JP2021189527A5 (en) | ||
| CN111462221A (en) | Method, device and equipment for extracting shadow area of object to be detected and storage medium | |
| CN112132774A (en) | Quality evaluation method of tone mapping image | |
| CN111325728A (en) | Product defect detection method, device, equipment and storage medium | |
| CN110889374A (en) | Seal image processing method and device, computer and storage medium | |
| CN114219863A (en) | Seal detection method based on re-opening operation, storage medium and electronic device | |
| Jaiswal et al. | A no-reference contrast assessment index based on foreground and background | |
| JP2010028429A (en) | Image processing apparatus, image processing method, and program | |
| CN116563133A (en) | Low-illumination color image enhancement method based on simulated exposure and multi-scale fusion | |
| CN113610940B (en) | Ocean vector file and image channel threshold based coastal area color homogenizing method | |
| CN113223098B (en) | Preprocessing optimization method for image color classification | |
| CN113763380B (en) | Vector gradient-based reference-free image definition evaluation method |
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 |