CN109658364A - Image processing method - Google Patents
Image processing method Download PDFInfo
- Publication number
- CN109658364A CN109658364A CN201811447040.5A CN201811447040A CN109658364A CN 109658364 A CN109658364 A CN 109658364A CN 201811447040 A CN201811447040 A CN 201811447040A CN 109658364 A CN109658364 A CN 109658364A
- Authority
- CN
- China
- Prior art keywords
- original
- block
- sub
- image
- blocks
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 28
- 238000006243 chemical reaction Methods 0.000 claims abstract description 53
- 238000013507 mapping Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 28
- 241001270131 Agaricus moelleri Species 0.000 claims 1
- 230000002708 enhancing effect Effects 0.000 description 8
- 238000000034 method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000000977 initiatory effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000276489 Merlangius merlangus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- 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
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- 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
- G06T2207/20172—Image enhancement details
- G06T2207/20208—High dynamic range [HDR] image processing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
The present invention provides a kind of image processing method.Image processing method of the invention obtains the full figure degree of concern weight mapping graph of original image, and original image is divided into multiple original blocks, histogram equalization processing is carried out to multiple original blocks respectively using full figure degree of concern weight mapping graph and preset grayscale conversion formula and forms multiple conversion blocks, splicing then is carried out to multiple conversion blocks and forms treated image, the contrast that image can be dynamically promoted according to human eye vision degree of concern, promotes the quality of image.
Description
Technical field
The present invention relates to field of display technology more particularly to a kind of image processing methods.
Background technique
Image enhancement technique is one kind of image processing techniques, it can significantly improve picture quality, so that picture material
More have a sense of hierarchy and subjective observation effect more meets people's demand.In actual life, often there are various problems in original image,
Such as: aperture is less than normal when taking pictures, and causes image partially dark；The contrast of scene is lower, and image emphasis is not protruded；It is exposed
Degree, causes image not normal, photo whiting etc..It can effectively be solved the above problems by image enhancement technique, promote display quality.
Existing image enhancement technique includes: saturation degree enhancing and contrast enhancing, is enhanced compared to saturation degree, contrast
It is higher to enhance the attention rate being subject to.Contrast enhancing is the gray-scale distribution by adjusting image, increases the distribution model of image gray-scale level
It encloses, to improve the contrast of image in whole or in part, improves visual effect.
In common contrast enhancement algorithms, image is handled with enhancing pair frequently with the mode of histogram equalization
Than degree, basic thought is the histogram of original image to be transformed to equally distributed form namely packed pixel number is less
Grayscale and extend the more grayscale of pixel number, the dynamic range of grey scale pixel value can be increased in this way, to reach enhancing figure
As the effect of overall contrast.
By the way of histogram equalization to image degree of comparing enhance handle when, generally include full figure form with
Block divides two kinds of forms of form.Full figure form, which refers to, directly integrally carries out histogram equalization to image, due to output pattern
It is influenced by original image, when there are (such as large stretch of clear zones, dark space, Sky Scene when a wide range of similar pixel in original image
Deng), biggish intensity value ranges can be occupied, image detail is caused to be unable to fully degree of comparing enhancing.And block divides form
Refer to and original input picture is subjected to block segmentation, and respectively carries out partial histogram equalization processing in each block, it can
The histogram equalization bring image detail for solving full figure form to a certain extent is unable to fully degree of comparing enhancing
Problem, but it can not carry out picture superposition according to human eye vision degree of concern, and the effect for enhancing contrast still extremely has
Limit.
Summary of the invention
The purpose of the present invention is to provide a kind of image processing methods, can be obviously improved the contrast of image, promote figure
The quality of picture.
To achieve the above object, the present invention provides a kind of image processing method, includes the following steps:
Step S1, original image is provided；The original image includes multiple pixels, and each pixel has corresponding original ash
Rank；
Step S2, the full figure degree of concern weight mapping graph of original image is obtained；The full figure degree of concern weight mapping
Figure includes that mapping point corresponding with multiple pixels, each mapping point have corresponding weighted value respectively；
Step S3, original image is divided into multiple original blocks；
Step S4, using full figure degree of concern weight mapping graph and preset grayscale conversion formula respectively to multiple regions of initiation
Block carries out histogram equalization processing and forms multiple conversion blocks；
Step S5, splicing is carried out to multiple conversion blocks and forms treated image.
In the step S4, calculated separately often using full figure degree of concern weight mapping graph and preset grayscale conversion formula
The corresponding conversion grayscale of the original gray-scale of each pixel in one original block simultaneously replaces original gray-scale using conversion grayscale
It changes, to form multiple conversion blocks.
The preset grayscale conversion formula are as follows:
Wherein, SkFor the conversion grayscale for the pixel that original gray-scale in original block is k, njIt is all original in original block
Grayscale is the value summed after the grayscale of the pixel of j is multiplied with corresponding weighted value respectively, and n is all pixels in original block
The value that grayscale is summed after being multiplied respectively with corresponding weighted value.
K is positive integer, and the value range of k is 0~L-1, wherein L is the available grayscale sum of original image.
Described image processing method further include step S5, to multiple conversion blocks carry out splicing formed treated figure
Picture.
In the step S5, splicing is carried out to multiple conversion blocks by way of linear interpolation.
Original image is divided into multiple original blocks of array arrangement in the step S3.
In the step S5, multiple conversion blocks are divided into four sub-blocks in the column arrangement of two rows two, thus multiple
The sub-block for converting block is arranged in array, and by way of linear interpolation multiple conversion blocks are carried out with the tool of splicing
Body mode are as follows: to the sub-block of the first row first row, sub-block, the sub-block of last line first row of the first row last column
And the sub-block of last line last column is without linear interpolation processing, to the first row, first row, last line, last
In addition to the sub-block of the first row first row, the sub-block of the first row last column, last line first row in the sub-block of one column
Sub-block and last line last column sub-block outside other sub-blocks carry out the processing of single linear interpolation, to sub-block
Other sub-blocks in array other than the first row, first row, last line, the sub-block of last column carry out in bilinearity
Insert processing.
The single linear interpolation processing is that horizontal single linear interpolation is handled.
The single linear interpolation processing is the vertical single linear interpolation processing of water.
In the step S2, the full figure degree of concern weight mapping graph of original image is obtained using GBVS algorithm.
Beneficial effects of the present invention: the full figure degree of concern weight that image processing method of the invention obtains original image is reflected
Figure is penetrated, and original image is divided into multiple original blocks, is turned using full figure degree of concern weight mapping graph and preset grayscale
It changes formula and multiple conversion blocks is formed to multiple original blocks progress histogram equalization processing respectively, then to multiple transition zones
Block carries out splicing and forms treated image, and the comparison of image can be dynamically promoted according to human eye vision degree of concern
Degree, promotes the quality of image.
Detailed description of the invention
For further understanding of the features and technical contents of the present invention, it please refers to below in connection with of the invention detailed
Illustrate and attached drawing, however, the drawings only provide reference and explanation, is not intended to limit the present invention.
In attached drawing,
Fig. 1 is the flow chart of image processing method of the invention；
Fig. 2 is the schematic diagram of the step S1 of image processing method of the invention；
Fig. 3 is the schematic diagram of the step S2 of image processing method of the invention；
Fig. 4 is the schematic diagram of the step S3 of image processing method of the invention；
Fig. 5 is the schematic diagram of the step S4 of image processing method of the invention；
Fig. 6 is the schematic diagram of the step S5 of image processing method of the invention.
Specific embodiment
Further to illustrate technological means and its effect adopted by the present invention, below in conjunction with preferred implementation of the invention
Example and its attached drawing are described in detail.
Referring to Fig. 1, the present invention provides a kind of image processing method, include the following steps:
Step S1, referring to Fig. 2, providing original image 10.The original image 10 includes multiple pixels, each pixel tool
There is corresponding original gray-scale.
Step S2, referring to Fig. 3, obtaining the full figure degree of concern weight mapping graph 20 of original image 10.The full figure closes
Note degree weight mapping graph 20 includes that mapping point corresponding with multiple pixels, each mapping point have corresponding weighted value respectively.
Specifically, in the step S2, using attention selection model (Graph-based Visual Saliency,
GBVS) algorithm obtains the full figure degree of concern weight mapping graph 20 of original image.
Step S3, referring to Fig. 4, original image 10 is divided into multiple original blocks 11.
Specifically, in the embodiment shown in fig. 4, in the step S3, original image 10 is divided into array arrangement
Multiple original blocks 11.Certain original image 10 is divided into original block 11 and other modes can also be used.
Step S4, referring to Fig. 5, being distinguished using full figure degree of concern weight mapping graph 20 and preset grayscale conversion formula
Histogram equalization processing is carried out to multiple original blocks 11 and forms multiple conversion blocks 31.
Specifically, in the step S4, full figure degree of concern weight mapping graph 20 and preset grayscale conversion formula are utilized
Calculate separately the corresponding conversion grayscale of original gray-scale of each pixel in each original block 11 and using conversion grayscale to original
Beginning grayscale is replaced, to form multiple conversion blocks 31.
Further, the preset grayscale conversion formula are as follows:
Wherein, SkFor the conversion grayscale for the pixel that original gray-scale in original block 11 is k, njTo own in original block 11
Original gray-scale is the value summed after the grayscale of the pixel of j is multiplied with corresponding weighted value respectively, and n is to own in original block 11
The value that the grayscale of pixel is summed after being multiplied respectively with corresponding weighted value.K is positive integer, and the value range of k is 0~L-1,
Wherein, L is the available grayscale sum of original image 10.
Step S5, referring to Fig. 6, carrying out splicing to multiple conversion blocks 31 forms treated image 30.
Specifically, in the step S5, stitching portion can be carried out to multiple conversion blocks 31 by way of linear interpolation
Reason.
Further, in the embodiment shown in fig. 6, in the step S5, multiple conversion blocks 31 are divided into two
Four sub-blocks 311 of the column arrangement of row two, so that the sub-block 311 of multiple conversion blocks 31 is arranged in array, by linear
The mode of interpolation carries out the concrete modes of splicings to multiple conversion blocks 31 are as follows: to the sub-block 311 of the first row first row,
The sub-district of last column of sub-block 311, the sub-block 311 of last line first row and the last line of last column of the first row
Block 311 without linear interpolation processing, in the first row, first row, last line, sub-block 311 of last column in addition to the
The sub-blocks 311 of last column of the sub-block 311 of a line first row, the first row, the sub-block 311 of last line first row and
Other sub-blocks 311 outside the sub-block 311 of last column of last line carry out the processing of single linear interpolation, to 311 gusts of sub-block
Other sub-blocks 311 in column other than the first row, first row, last line, the sub-block 311 of last column carry out two-wire
Property interpolation processing.
Further, the single linear interpolation processing is at the processing of horizontal single linear interpolation or vertical single linear interpolation
Reason.
It should be noted that first providing original image 10 in image processing method of the invention, then obtaining original image
10 full figure degree of concern weight mapping graph 20, full figure degree of concern weight mapping graph 20 include more with original image 10 respectively
The corresponding multiple mapping points of a pixel, each mapping point all have corresponding weighted value, are then divided into original image 10 more
A original block 11, using full figure degree of concern weight mapping graph 20 and preset grayscale conversion formula respectively to multiple regions of initiation
Block 11 carries out histogram equalization processing and forms multiple conversion blocks 31, specially utilizes full figure degree of concern weight mapping graph 20
And preset grayscale conversion formula calculates separately the corresponding conversion ash of original gray-scale of each pixel in each original block 11
Rank is simultaneously replaced original gray-scale using conversion grayscale, so that multiple conversion blocks 31 are formed, finally to multiple conversion blocks
31, which carry out splicings, forms treated image 30, and a wide range of similar pixel can effectively be avoided to occupy biggish gray value model
The poor problem of contrast reinforcing effect caused by enclosing, while each original can be dynamically promoted according to human eye vision degree of concern
The contrast of beginning block 11, so as to promote effect preferable for the contrast for the image 30 that finally obtains that treated, so that image has
There is higher quality.
In conclusion image processing method of the invention obtains the full figure degree of concern weight mapping graph of original image, and
Original image is divided into multiple original blocks, utilizes full figure degree of concern weight mapping graph and preset grayscale conversion formula point
It is other that multiple conversion blocks are formed to multiple original blocks progress histogram equalization processing, then multiple conversion blocks are spelled
It connects processing and forms treated image, the contrast of image can be dynamically promoted according to human eye vision degree of concern, promote figure
The quality of picture.
The above for those of ordinary skill in the art can according to the technique and scheme of the present invention and technology
Other various corresponding changes and modifications are made in design, and all these change and modification all should belong to the claims in the present invention
Protection scope.
Claims (10)
1. a kind of image processing method, which comprises the steps of:
Step S1, original image is provided；The original image includes multiple pixels, and each pixel has corresponding original gray-scale；
Step S2, the full figure degree of concern weight mapping graph of original image is obtained；The full figure degree of concern weight mapping graph packet
Mapping point corresponding with multiple pixels respectively is included, each mapping point has corresponding weighted value；
Step S3, original image is divided into multiple original blocks；
Step S4, using full figure degree of concern weight mapping graph and preset grayscale conversion formula respectively to multiple original blocks into
Column hisgram equalization processing forms multiple conversion blocks；
Step S5, splicing is carried out to multiple conversion blocks and forms treated image.
2. image processing method as described in claim 1, which is characterized in that in the step S4, utilize full figure degree of concern
The original gray-scale that weight mapping graph and preset grayscale conversion formula calculate separately each pixel in each original block is corresponding
Conversion grayscale and using conversion grayscale original gray-scale is replaced, to form multiple conversion blocks.
3. image processing method as claimed in claim 2, which is characterized in that the preset grayscale conversion formula are as follows:
Wherein, SkFor the conversion grayscale for the pixel that original gray-scale in original block is k, njFor original gray-scales all in original block
For the value that the grayscale of the pixel of j is summed with the multiplication of corresponding weighted value later respectively, n is the grayscale of all pixels in original block
The value summed after being multiplied respectively with corresponding weighted value.
4. image processing method as claimed in claim 3, which is characterized in that k is positive integer, and the value range of k is 0~L-
1, wherein L is the available grayscale sum of original image.
5. image processing method as described in claim 1, which is characterized in that in the step S5, pass through the side of linear interpolation
Formula carries out splicing to multiple conversion blocks.
6. image processing method as claimed in claim 5, which is characterized in that original image is divided into battle array in the step S3
Arrange multiple original blocks of arrangement.
7. image processing method as claimed in claim 6, which is characterized in that in the step S5, multiple conversion blocks are drawn
It is divided into four sub-blocks in the column arrangement of two rows two, so that the sub-block of multiple conversion blocks is arranged in array, by linear
The mode of interpolation carries out the concrete modes of splicings to multiple conversion blocks are as follows: to the sub-block of the first row first row, first
The sub-block of last column of sub-block, the sub-block of last line first row and the last line of last column of row is without line
Property interpolation processing, to the first row, first row, last line, last column sub-block in addition to the first row first row sub-district
The sub-block of last column of sub-block, the sub-block of last line first row and the last line of last column of block, the first row
Outer other sub-blocks carry out the processing of single linear interpolation, in sub- block array in addition to the first row, first row, last line, most
Other sub-blocks other than the sub-block of latter column carry out bilinear interpolation processing.
8. image processing method as claimed in claim 7, which is characterized in that the single linear interpolation processing is horizontal single linear
Interpolation processing.
9. image processing method as claimed in claim 7, which is characterized in that the single linear interpolation processing is vertical single linear
Interpolation processing.
10. image processing method as described in claim 1, which is characterized in that in the step S2, obtained using GBVS algorithm
The full figure degree of concern weight mapping graph of original image.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811447040.5A CN109658364A (en) | 2018-11-29 | 2018-11-29 | Image processing method |
| PCT/CN2019/070511 WO2020107651A1 (en) | 2018-11-29 | 2019-01-04 | Image processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811447040.5A CN109658364A (en) | 2018-11-29 | 2018-11-29 | Image processing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109658364A true CN109658364A (en) | 2019-04-19 |
Family
ID=66111096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811447040.5A Pending CN109658364A (en) | 2018-11-29 | 2018-11-29 | Image processing method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109658364A (en) |
| WO (1) | WO2020107651A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110188750A (en) * | 2019-05-16 | 2019-08-30 | 杭州电子科技大学 | A kind of natural scene picture character recognition method based on deep learning |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980282A (en) * | 2010-10-21 | 2011-02-23 | 电子科技大学 | Infrared image dynamic detail enhancement method |
| CN108242049A (en) * | 2016-12-26 | 2018-07-03 | 河北天地智慧医疗设备股份有限公司 | A kind of full size DR Imaging enhanced processing methods for GPU optimizations |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7894668B1 (en) * | 2006-09-28 | 2011-02-22 | Fonar Corporation | System and method for digital image intensity correction |
| CN102999903B (en) * | 2012-11-14 | 2014-12-24 | 南京理工大学 | Method for quantitatively evaluating illumination consistency of remote sensing images |
| CN104574326B (en) * | 2013-10-15 | 2017-07-18 | 无锡华润矽科微电子有限公司 | The method and apparatus that histogram equalization processing is carried out to image |
| CN104915939B (en) * | 2015-07-07 | 2018-06-22 | 杭州朗和科技有限公司 | A kind of image equilibration method and apparatus |
| JP2017076240A (en) * | 2015-10-14 | 2017-04-20 | キヤノン株式会社 | Image processing apparatus, image processing method, and program |
| CN105828057A (en) * | 2016-03-23 | 2016-08-03 | 武汉鸿瑞达信息技术有限公司 | High data rate (hdr) adaptive color mapping method for optimizing image recognition degree |
-
2018
- 2018-11-29 CN CN201811447040.5A patent/CN109658364A/en active Pending
-
2019
- 2019-01-04 WO PCT/CN2019/070511 patent/WO2020107651A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980282A (en) * | 2010-10-21 | 2011-02-23 | 电子科技大学 | Infrared image dynamic detail enhancement method |
| CN108242049A (en) * | 2016-12-26 | 2018-07-03 | 河北天地智慧医疗设备股份有限公司 | A kind of full size DR Imaging enhanced processing methods for GPU optimizations |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110188750A (en) * | 2019-05-16 | 2019-08-30 | 杭州电子科技大学 | A kind of natural scene picture character recognition method based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020107651A1 (en) | 2020-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104700376B (en) | Image histogram equalization Enhancement Method based on gamma correction and smothing filtering | |
| CN104268843B (en) | Image self-adapting enhancement method based on histogram modification | |
| CN107767349B (en) | A kind of method of Image Warping enhancing | |
| WO2018133609A1 (en) | Method for producing high dynamic range image from low dynamic range image | |
| CN106683080B (en) | A kind of retinal fundus images preprocess method | |
| CN106651818A (en) | Improved Histogram equalization low-illumination image enhancement algorithm | |
| CN101706953B (en) | Histogram equalization based image enhancement method and device | |
| CN105184754B (en) | Method for enhancing picture contrast | |
| CN108022223B (en) | Tone mapping method based on logarithm mapping function blocking processing fusion | |
| CN105046658B (en) | A kind of low-light (level) image processing method and device | |
| CN104301636B (en) | The synthetic method of low complex degree efficient high dynamic digital picture | |
| CN110298792B (en) | Low-illumination image enhancement and denoising method, system and computer equipment | |
| CN109003249A (en) | Enhance the method, apparatus and terminal of image detail | |
| CN110473152B (en) | Image enhancement method based on improved Retinex algorithm | |
| CN108280836B (en) | Image processing method and device | |
| CN102496152A (en) | Self-adaptive image contrast enhancement method based on histograms | |
| CN105513015B (en) | A kind of clearness processing method of Misty Image | |
| CN110706172A (en) | Low-illumination color image enhancement method based on adaptive chaotic particle swarm optimization | |
| CN104021531A (en) | Improved method for enhancing dark environment images on basis of single-scale Retinex | |
| CN115205160A (en) | No-reference low-illumination image enhancement method based on local scene perception | |
| CN109118437A (en) | A kind of method, storage medium that can handle muddy water image in real time | |
| CN106327437A (en) | Color text image correction method and system | |
| CN110175969A (en) | Image processing method and image processing apparatus | |
| CN109658364A (en) | Image processing method | |
| CN111369435B (en) | Color image depth up-sampling method and system based on self-adaptive stable model |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190419 |