CN102609921A - Image sharpening system and method based on laplace operator - Google Patents
Image sharpening system and method based on laplace operator Download PDFInfo
- Publication number
- CN102609921A CN102609921A CN2012100546789A CN201210054678A CN102609921A CN 102609921 A CN102609921 A CN 102609921A CN 2012100546789 A CN2012100546789 A CN 2012100546789A CN 201210054678 A CN201210054678 A CN 201210054678A CN 102609921 A CN102609921 A CN 102609921A
- Authority
- CN
- China
- Prior art keywords
- data
- frame
- template
- video image
- image data
- 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
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses an image sharpening system and method based on a laplace operator. The image sharpening system comprises a template generation module, a template parameter overlying module and an output value calculating module. The image sharpening method comprises the following steps: inputting Pixel_In by a data frame and introducing a third frame of video image data; forming a 3*3 neighborhood template with the previous two frames of video image data stored in FIFO (first input first output) 1 and FIFO2; overlying template parameters into video data by a multiplying unit; adding through the sum of three columns of template data to obtain the sum of 9 data in the 3*3 template, wherein the sum acts as the sharpened image marginal value by dividing a constant factor; and then adding the sharpened image marginal value and the corresponding original images to obtain clearer video images after margin reinforcement. The real-time sharpening treatment on the video image data can be carried out in the video collecting process.
Description
Technical field
The present invention relates to the technical field of video monitoring, is image sharpening system and image sharpening method based on Laplace operator that a kind of edge that utilizes Laplace operator to realize real time video image strengthens specifically.
Background technology
Image sharpening is exactly the profile of compensating images, strengthens the part of edge of image and Gray Level Jump, makes image become clear, and image sharpening is divided into the spatial domain processing and frequency field is handled two types.
The purpose that image sharpening is handled be for the details that makes edge of image, outline line and image become clear; The basic reason that thickens through level and smooth image is because image has received average or integral operation, therefore can carry out inverse operation (as differentiating) to it and just can make the clear of image change.
The energy of image mainly concentrates on its low frequency part, and image edge information mainly concentrates on its HFS.Consider that from frequency field image blurring essence is because playing high fdrequency component is attenuated, and therefore can make clear picture with Hi-pass filter.
Laplace operator is that a kind of the processing at image sharpening gathered very important algorithm.Laplace operator is and the irrelevant endpoint detections operator of an edge direction.Laplace operator is a kind of second-order differential operator.A continuous binary function, its Laplace's operation is defined as
For digital picture, Laplace operator can be reduced to
Formula (2) can use the filtering template to realize, template commonly used is following:
Use Laplce can be expressed as following formula to the basic skills of figure image intensifying:
Wherein, f (x, y) and g (x y) is image after input picture and the sharpening, and c is a constant 1.
Summary of the invention
The technical matters that the present invention will solve provides image sharpening system and the image sharpening method based on FPGA that a kind of edge that utilizes Laplace operator to realize real time video image strengthens.
The technical scheme that the present invention takes for the technical matters that exists in the solution known technology is:
Image sharpening system based on Laplace operator of the present invention comprises template generation module, template parameter laminating module and output valve computing module, and above-mentioned three modules are connected successively; The template generation module comprises two-way pushup storage FIFO1, FIFO2 and circuit-switched data frame input Pixel_In; Frame input Pixel_In is connected with FIFO2; And FIFO2 is connected with FIFO1; The front and back two continuous frames video data of being introduced by Frame input Pixel_In deposits FIFO1 and FIFO2 respectively in, and Pixel_In introduces the 3rd frame video data by the Frame input; Comprise Laplce's template, multiplier and totalizer in the template parameter laminating module; Store the Laplace operator factor in Laplce's template; Above-mentioned three road two field pictures link to each other respectively with Laplce's template through multiplier respectively, three products of gained again through the totalizer summation obtain a row template data and; The output valve computing module comprises totalizer, column data storer, frame data storer and divider; Three column data storeies are stored three row template datas respectively; Three frame data storeies are connected with FIFO2; The video data that the FIFO2 of storage correspondence successively receives; Through totalizer carry out streamline add with three row template datas and, gained and through divider divided by the constant factor again with the data that obtain by the frame data storer through totalizer add successively with, and the gained data are exported Pixel_Out as Frame.
Image sharpening method based on Laplace operator of the present invention may further comprise the steps:
A, introduce the first frame video image data, and deposit these frame video image data in FIFO2 by Frame input Pixel_In; Pixel_In introduces the second frame video image data by the Frame input; And deposit these frame video image data in FIFO2; Originally be stored in the first frame video image data conversion storage among the FIFO2 to FIFO1; The second frame video image data also transfer to the frame data storer Reg6 in the output valve calculation template simultaneously, introduce the 3rd frame video image data by Frame input Pixel_In again, constitute 3 * 3 neighborhood templates with the front cross frame vedio data of storing among FIFO1 and the FIFO2;
B, pairing three circuit-switched data of above-mentioned first to the 3rd frame video image data are carried out multiplication through multiplier and Laplce's template respectively and are calculated;
C, will add through totalizer through each self-corresponding product of three circuit-switched data that the B step obtains and, obtain the first row template data with, with the first row template data with deposit among the column data storer Reg3 in the output valve computing module;
D, introduce the 4th frame video image data by Frame input Pixel_In; The 3rd frame video image data storage is gone into FIFO2; And the second frame video image data of original storage and FIFO2 deposit FIFO1 in; Simultaneously with the frame data storer Reg6 in the 3rd frame video image data transmission to the output valve calculation template; And the second frame video image data transmission of the former Reg6 of being stored in is to the Reg5 that is linked in sequence with Reg6, second frame of storing among the 4th frame video image data and FIFO1 and the FIFO2 and the 3rd frame video image data formation 3 * 3 neighborhood templates;
E, pairing three circuit-switched data of second to the 4th frame video image data are carried out multiplication through multiplier and Laplce's template respectively and are calculated;
F, will pass through that each the self-corresponding product of three circuit-switched data that obtains after the E step adds through totalizer and; Obtain the secondary series template data with; With the secondary series template data with deposit among the column data storer Reg3 in the output valve computing module, simultaneously the first row template data with deposit in the interconnective Reg2 of Reg3 in;
G, introduce the 5th frame video image data by Frame input Pixel_In; The 4th frame video image data storage is gone into FIFO2; And the 3rd frame video image data of former storage and FIFO2 deposit FIFO1 in; Simultaneously with the frame data storer Reg6 in the 4th frame video image data transmission to the output valve calculation template; And the 3rd frame video image data transmission of the former Reg6 of being stored in is to the Reg5 that is linked in sequence with Reg6, and the second frame video image data transmission of the former Reg5 of being stored in is to the Reg4 that is linked in sequence with Reg5, the 3rd frame of storing among the 5th frame video image data and FIFO1 and the FIFO2 and the 4th frame video image data formation 3 * 3 neighborhood templates;
H, pairing three circuit-switched data of the 3rd to the 5th frame video image data are carried out multiplication through multiplier and Laplce's template respectively and are calculated;
I, will pass through that each the self-corresponding product of three circuit-switched data that obtains after the H step adds through totalizer and; Obtain the 3rd row template data with; With the 3rd row template data with deposit among the column data storer Reg3 in the output valve computing module; Simultaneously the secondary series template data with deposit in the interconnective Reg2 of Reg3 in, and the first row template data with deposit in the interconnective Reg1 of Reg2 in;
J, with three row template datas among Reg1, Reg2 and the Reg3 and add and; Obtain 3 * 3 templates 9 data with; With the result who obtains divided by the constant factor; As the image border after sharpening value, again the second frame video image data of storing among the image border value of above-mentioned gained and the Reg4 are added and, remember the image value after the sharpening;
K, continue to introduce vedio data, continue order according to step G to step J and carry out corresponding processing procedure by Frame input Pixel_In.
Advantage and good effect that the present invention has are:
The present invention is based on Laplace operator; Utilize three continuous frame video image data to set up 3 * 3 neighborhood template; Be added to template parameter in the video data through multiplier; Through to three row template datas with add with, draw 9 data in 3 * 3 templates with, with the gained data with divided by the image border value of constant factor after as sharpening; And then with the image border value after the sharpening add with corresponding original image and promptly draw the edge and strengthen after video image more clearly, in the video acquisition process, can carry out real-time sharpening and handle vedio data.
Description of drawings
Fig. 1 is the synoptic diagram of the image sharpening system based on Laplace operator of the present invention.
Embodiment
Followingly the present invention is carried out detailed explanation with reference to accompanying drawing and embodiment.
Fig. 1 is the synoptic diagram of the image sharpening system based on Laplace operator of the present invention.
As shown in Figure 1, the image sharpening system based on Laplace operator of the present invention comprises template generation module, template parameter laminating module and output valve computing module, and above-mentioned three modules are connected successively; The template generation module comprises two-way pushup storage FIFO1, FIFO2 and circuit-switched data frame input Pixel_In; Frame input Pixel_In is connected with FIFO2; And FIFO2 is connected with FIFO1; The front and back two continuous frames video data of being introduced by Frame input Pixel_In deposits FIFO1 and FIFO2 respectively in, and Pixel_In introduces the 3rd frame video data by the Frame input; Comprise Laplce's template Coefficient RAM, multiplier and totalizer in the template parameter laminating module; Store the Laplace operator factor in Laplce's template; Above-mentioned three road two field pictures link to each other respectively with Laplce's template through multiplier respectively, three products of gained again through the totalizer summation obtain a row template data and; The output valve computing module comprises totalizer, column data storer, frame data storer 1 and divider; Three column data storer Reg4, Reg5 and Reg6 store three row template datas respectively; Three frame data storeies are connected with FIFO2; The video data that the FIFO2 of storage correspondence successively receives; Through totalizer carry out streamline add with three row template datas and, gained and through divider add successively through totalizer with the data that obtain by frame data storer Reg3, Reg2 and Reg1 again divided by the constant factor and, and the gained data are exported Pixel_Out as Frame.
Image sharpening method based on Laplace operator of the present invention may further comprise the steps:
A, introduce the first frame video image data, and deposit these frame video image data in FIFO2 by Frame input Pixel_In; Pixel_In introduces the second frame video image data by the Frame input; And deposit these frame video image data in FIFO2; Originally be stored in the first frame video image data conversion storage among the FIFO2 to FIFO1; The second frame video image data also transfer to the frame data storer Reg6 in the output valve calculation template simultaneously, introduce the 3rd frame video image data by Frame input Pixel_In again, constitute 3 * 3 neighborhood templates with the front cross frame vedio data of storing among FIFO1 and the FIFO2;
B, pairing three circuit-switched data of above-mentioned first to the 3rd frame video image data are carried out multiplication through multiplier and Laplce's template respectively and are calculated;
C, will add through totalizer through each self-corresponding product of three circuit-switched data that the B step obtains and, obtain the first row template data with, with the first row template data with deposit among the column data storer Reg3 in the output valve computing module;
D, introduce the 4th frame video image data by Frame input Pixel_In; The 3rd frame video image data storage is gone into FIFO2; And the second frame video image data of original storage and FIFO2 deposit FIFO1 in; Simultaneously with the frame data storer Reg6 in the 3rd frame video image data transmission to the output valve calculation template; And the second frame video image data transmission of the former Reg6 of being stored in is to the Reg5 that is linked in sequence with Reg6, second frame of storing among the 4th frame video image data and FIFO1 and the FIFO2 and the 3rd frame video image data formation 3 * 3 neighborhood templates;
E, pairing three circuit-switched data of second to the 4th frame video image data are carried out multiplication through multiplier and Laplce's template respectively and are calculated;
F, will pass through that each the self-corresponding product of three circuit-switched data that obtains after the E step adds through totalizer and; Obtain the secondary series template data with; With the secondary series template data with deposit among the column data storer Reg3 in the output valve computing module, simultaneously the first row template data with deposit in the interconnective Reg2 of Reg3 in;
G, introduce the 5th frame video image data by Frame input Pixel_In; The 4th frame video image data storage is gone into FIFO2; And the 3rd frame video image data of former storage and FIFO2 deposit FIFO1 in; Simultaneously with the frame data storer Reg6 in the 4th frame video image data transmission to the output valve calculation template; And the 3rd frame video image data transmission of the former Reg6 of being stored in is to the Reg5 that is linked in sequence with Reg6, and the second frame video image data transmission of the former Reg5 of being stored in is to the Reg4 that is linked in sequence with Reg5, the 3rd frame of storing among the 5th frame video image data and FIFO1 and the FIFO2 and the 4th frame video image data formation 3 * 3 neighborhood templates;
H, pairing three circuit-switched data of the 3rd to the 5th frame video image data are carried out multiplication through multiplier and Laplce's template respectively and are calculated;
I, will pass through that each the self-corresponding product of three circuit-switched data that obtains after the H step adds through totalizer and; Obtain the 3rd row template data with; With the 3rd row template data with deposit among the column data storer Reg3 in the output valve computing module; Simultaneously the secondary series template data with deposit in the interconnective Reg2 of Reg3 in, and the first row template data with deposit in the interconnective Reg1 of Reg2 in;
J, with three row template datas among Reg1, Reg2 and the Reg3 and add and; Obtain 3 * 3 templates 9 data with; With the result who obtains divided by the constant factor; As the image border after sharpening value, again the second frame video image data of storing among the image border value of above-mentioned gained and the Reg4 are added and, remember the image value after the sharpening;
K, continue to introduce vedio data, continue order according to step G to step J and carry out corresponding processing procedure by Frame input Pixel_In.
The above only is preferred embodiment of the present invention, is not the present invention is done any pro forma restriction; Though the present invention is with preferred embodiment openly as above, yet, be not in order to limit the present invention; Anyly be familiar with the professional and technical personnel, in not breaking away from technical scheme scope of the present invention, can utilize the technology contents of announcement to make a little change or modification certainly; Become the equivalent embodiment of equivalent variations; In every case be the content that does not break away from technical scheme of the present invention, to any simple modification, equivalent variations and modification that above embodiment did, all belong in the scope of technical scheme of the present invention according to technical spirit of the present invention.
Claims (2)
1. image sharpening system based on Laplace operator, it is characterized in that: comprise template generation module, template parameter laminating module and output valve computing module, above-mentioned three modules are connected successively; The template generation module comprises two-way pushup storage FIFO1, FIFO2 and circuit-switched data frame input Pixel_In; Frame input Pixel_In is connected with FIFO2; And FIFO2 is connected with FIFO1; The front and back two continuous frames video data of being introduced by Frame input Pixel_In deposits FIFO1 and FIFO2 respectively in, and Pixel_In introduces the 3rd frame video data by the Frame input; Comprise Laplce's template, multiplier and totalizer in the template parameter laminating module; Store the Laplace operator factor in Laplce's template; Above-mentioned three road two field pictures link to each other respectively with Laplce's template through multiplier respectively, three products of gained again through the totalizer summation obtain a row template data and; The output valve computing module comprises totalizer, column data storer, frame data storer and divider; Three column data storeies are stored three row template datas respectively; Three frame data storeies are connected with FIFO2; The video data that the FIFO2 of storage correspondence successively receives; Through totalizer carry out streamline add with three row template datas and, gained and through divider divided by the constant factor again with the data that obtain by the frame data storer through totalizer add successively with, and the gained data are exported Pixel_Out as Frame.
2. image sharpening method based on the described image sharpening system based on Laplace operator of claim 1 may further comprise the steps:
A, introduce the first frame video image data, and deposit these frame video image data in FIFO2 by Frame input Pixel_In; Pixel_In introduces the second frame video image data by the Frame input; And deposit these frame video image data in FIFO2; Originally be stored in the first frame video image data conversion storage among the FIFO2 to FIFO1; The second frame video image data also transfer to the frame data storer Reg6 in the output valve calculation template simultaneously, introduce the 3rd frame video image data by Frame input Pixel_In again, constitute 3 * 3 neighborhood templates with the front cross frame vedio data of storing among FIFO1 and the FIFO2;
B, pairing three circuit-switched data of above-mentioned first to the 3rd frame video image data are carried out multiplication through multiplier and Laplce's template respectively and are calculated;
C, will add through totalizer through each self-corresponding product of three circuit-switched data that the B step obtains and, obtain the first row template data with, with the first row template data with deposit among the column data storer Reg3 in the output valve computing module;
D, introduce the 4th frame video image data by Frame input Pixel_In; The 3rd frame video image data storage is gone into FIFO2; And the second frame video image data of original storage and FIFO2 deposit FIFO1 in; Simultaneously with the frame data storer Reg6 in the 3rd frame video image data transmission to the output valve calculation template; And the second frame video image data transmission of the former Reg6 of being stored in is to the Reg5 that is linked in sequence with Reg6, second frame of storing among the 4th frame video image data and FIFO1 and the FIFO2 and the 3rd frame video image data formation 3 * 3 neighborhood templates;
E, pairing three circuit-switched data of second to the 4th frame video image data are carried out multiplication through multiplier and Laplce's template respectively and are calculated;
F, will pass through that each the self-corresponding product of three circuit-switched data that obtains after the E step adds through totalizer and; Obtain the secondary series template data with; With the secondary series template data with deposit among the column data storer Reg3 in the output valve computing module, simultaneously the first row template data with deposit in the interconnective Reg2 of Reg3 in;
G, introduce the 5th frame video image data by Frame input Pixel_In; The 4th frame video image data storage is gone into FIFO2; And the 3rd frame video image data of former storage and FIFO2 deposit FIFO1 in; Simultaneously with the frame data storer Reg6 in the 4th frame video image data transmission to the output valve calculation template; And the 3rd frame video image data transmission of the former Reg6 of being stored in is to the Reg5 that is linked in sequence with Reg6, and the second frame video image data transmission of the former Reg5 of being stored in is to the Reg4 that is linked in sequence with Reg5, the 3rd frame of storing among the 5th frame video image data and FIFO1 and the FIFO2 and the 4th frame video image data formation 3 * 3 neighborhood templates;
H, pairing three circuit-switched data of the 3rd to the 5th frame video image data are carried out multiplication through multiplier and Laplce's template respectively and are calculated;
I, will pass through that each the self-corresponding product of three circuit-switched data that obtains after the H step adds through totalizer and; Obtain the 3rd row template data with; With the 3rd row template data with deposit among the column data storer Reg3 in the output valve computing module; Simultaneously the secondary series template data with deposit in the interconnective Reg2 of Reg3 in, and the first row template data with deposit in the interconnective Reg1 of Reg2 in;
J, with three row template datas among Reg1, Reg2 and the Reg3 and add and; Obtain 3 * 3 templates 9 data with; With the result who obtains divided by the constant factor; As the image border after sharpening value, again the second frame video image data of storing among the image border value of above-mentioned gained and the Reg4 are added and, remember the image value after the sharpening;
K, continue to introduce vedio data, continue order according to step G to step J and carry out corresponding processing procedure by Frame input Pixel_In.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012100546789A CN102609921A (en) | 2012-03-05 | 2012-03-05 | Image sharpening system and method based on laplace operator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012100546789A CN102609921A (en) | 2012-03-05 | 2012-03-05 | Image sharpening system and method based on laplace operator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102609921A true CN102609921A (en) | 2012-07-25 |
Family
ID=46527267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012100546789A Pending CN102609921A (en) | 2012-03-05 | 2012-03-05 | Image sharpening system and method based on laplace operator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102609921A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103051844A (en) * | 2012-12-31 | 2013-04-17 | 青岛中星微电子有限公司 | Method and device for image backlight compensation |
| CN103716511A (en) * | 2014-01-22 | 2014-04-09 | 天津天地伟业数码科技有限公司 | Image sharpening system and method based on Prewitt operator |
| CN103716512A (en) * | 2014-01-22 | 2014-04-09 | 天津天地伟业数码科技有限公司 | Robinson operator-based image sharpening system and method |
| CN103714523A (en) * | 2014-01-22 | 2014-04-09 | 天津天地伟业数码科技有限公司 | Image sharpening system and image sharpening method on basis of Kirsch operators |
| CN104851081A (en) * | 2015-05-15 | 2015-08-19 | 南京信息工程大学 | GPU-based parallel Laplacian image sharpening method |
| CN105631854A (en) * | 2015-12-16 | 2016-06-01 | 天津天地伟业数码科技有限公司 | FPGA platform-based self-adaptive image definition evaluation algorithm |
| WO2017202244A1 (en) * | 2016-05-26 | 2017-11-30 | 深圳市中兴微电子技术有限公司 | Method and device for image enhancement and computer storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2626003Y (en) * | 2003-04-22 | 2004-07-14 | 海信集团有限公司 | Sobel and Laplace edge enhancement circuit for digital image of display |
-
2012
- 2012-03-05 CN CN2012100546789A patent/CN102609921A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2626003Y (en) * | 2003-04-22 | 2004-07-14 | 海信集团有限公司 | Sobel and Laplace edge enhancement circuit for digital image of display |
Non-Patent Citations (3)
| Title |
|---|
| JINCHENG WU ET AL.: "Design and Implementation of Video Image edge Detection System Based on FPGA", 《2010 3RD INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING(CPSP2010)》 * |
| 吴海波等: "基于拉普拉斯算子的彩色图像锐化处理", 《电脑开发与应用》 * |
| 毛伟民等: "拉普拉斯算子的FPGA实现方法", 《现代电子技术》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103051844A (en) * | 2012-12-31 | 2013-04-17 | 青岛中星微电子有限公司 | Method and device for image backlight compensation |
| CN103051844B (en) * | 2012-12-31 | 2016-05-18 | 青岛中星微电子有限公司 | A kind of method and device of image back light compensation |
| CN103716511A (en) * | 2014-01-22 | 2014-04-09 | 天津天地伟业数码科技有限公司 | Image sharpening system and method based on Prewitt operator |
| CN103716512A (en) * | 2014-01-22 | 2014-04-09 | 天津天地伟业数码科技有限公司 | Robinson operator-based image sharpening system and method |
| CN103714523A (en) * | 2014-01-22 | 2014-04-09 | 天津天地伟业数码科技有限公司 | Image sharpening system and image sharpening method on basis of Kirsch operators |
| CN104851081A (en) * | 2015-05-15 | 2015-08-19 | 南京信息工程大学 | GPU-based parallel Laplacian image sharpening method |
| CN105631854A (en) * | 2015-12-16 | 2016-06-01 | 天津天地伟业数码科技有限公司 | FPGA platform-based self-adaptive image definition evaluation algorithm |
| WO2017202244A1 (en) * | 2016-05-26 | 2017-11-30 | 深圳市中兴微电子技术有限公司 | Method and device for image enhancement and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102609921A (en) | Image sharpening system and method based on laplace operator | |
| CN102968769B (en) | Image consistency enhancing device | |
| CN110223242A (en) | A kind of video turbulent flow removing method based on time-space domain Residual Generation confrontation network | |
| CN106530237A (en) | Image enhancement method | |
| CN105096280A (en) | Method and device for processing image noise | |
| CN102289792A (en) | Method and system for enhancing low-illumination video image | |
| US8406559B2 (en) | Method and system for enhancing image sharpness based on local features of image | |
| CN105809643A (en) | Image enhancing method based on self-adaptive block channel stretching | |
| CN106875358A (en) | Image enchancing method and image intensifier device based on Bayer format | |
| CN103716511A (en) | Image sharpening system and method based on Prewitt operator | |
| CN103714523A (en) | Image sharpening system and image sharpening method on basis of Kirsch operators | |
| CN101894365A (en) | Adaptive variation remotely sensed image fusion method | |
| CN103313068A (en) | White balance corrected image processing method and device based on gray edge constraint gray world | |
| CN102609922A (en) | Image sharpening system and method based on FPGA (field programmable gate array) | |
| CN105447830B (en) | Dynamic video image clarity intensifying method and device | |
| CN103745443A (en) | Method and equipment for improving image quality | |
| CN102254305A (en) | Image restoring method based on three dictionary block matching | |
| CN103136530A (en) | Method for automatically recognizing target images in video images under complex industrial environment | |
| CN103455974A (en) | Image sketching style processing method | |
| CN104853059B (en) | Super-resolution image processing method and its device | |
| CN102768758A (en) | Improved color image unsharp masking (USM) method | |
| CN103716512A (en) | Robinson operator-based image sharpening system and method | |
| CN114612347B (en) | Multi-module cascade underwater image enhancement method | |
| CN117011130A (en) | Method, apparatus, device, medium and program product for image super resolution | |
| CN114022371B (en) | Defogging device and defogging method based on space and channel attention residual error network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120725 |