CN104537632A - Infrared image histogram enhancing method based on edge extraction - Google Patents
Infrared image histogram enhancing method based on edge extraction Download PDFInfo
- Publication number
- CN104537632A CN104537632A CN201410834788.6A CN201410834788A CN104537632A CN 104537632 A CN104537632 A CN 104537632A CN 201410834788 A CN201410834788 A CN 201410834788A CN 104537632 A CN104537632 A CN 104537632A
- Authority
- CN
- China
- Prior art keywords
- image
- histogram
- edge
- fringe region
- infrared image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The invention discloses an infrared image histogram enhancing method based on edge extraction. The infrared image histogram enhancing method includes the following steps of extracting the edge area of an original infrared image to obtain an edge area image, counting gray values, not equal to zero, in the edge area image to obtain a histogram and an accumulation histogram of the edge area, and enhancing the unprocessed infrared image according to the histogram and the accumulation histogram of the edge area. The enhancing method is high in enhancing contrast ratio, clear in image and good in visual effect.
Description
Technical field
The present invention relates to a kind of Infrared Image Enhancement Algorithm, specifically, the present invention relates to a kind of method of the infrared histogram enhancement algorithm based on edge extracting.
Background technology
Infrared imaging system antijamming capability is strong, and hidden performance is good, and air penetration capacity is strong, can adapt to multiple special occasions.But due to infrared eye self-characteristic, as the characteristic such as highly sensitive, dynamic range is large, and the various noise in complex work environment, cause infrared image to present high background, low-contrast feature.Be embodied in imaging scene and only account for a very little part in the dynamic range of whole infrared imaging system, picture contrast is poor, smudgy.Therefore need to carry out image enhaucament to original infrared image, thus improve the contrast of infrared image, improve the visual effect of image.
At present, the infrared image enhancing method of main flow has histogram enhancement and gray scale stretching Enhancement Method.But it is all carry out image enhancement processing according to the grey-level statistics in entire image that this two class strengthens algorithm, and have ignored the characteristic of image originally in spatial domain.But, for infrared image itself, the background with close gray scale occupies again very large a part of ratio wherein, and detailed information and Weak target only account for very little a part of ratio, be easy to cause in the process of image enhaucament, image detail is submerged in background, makes to become large to the identification difficulty of Small object.
Summary of the invention
The object of the present invention is to provide a kind of Enhancement Method of infrared image, the region, image border that method is extracted by edge detection operator, and according to the histogram of these fringe regions, image enhaucament is carried out to infrared image.Picture contrast after process of the present invention is high, and details is clear, and quality is good.
Technical scheme of the present invention is as follows:
A kind of infrared image histogram enhancement method based on edge extracting.Comprise the following steps: (1) extracts the fringe region of original infrared image F, to obtain fringe region image F
edge; (2) fringe region image F is added up
edgein non-vanishing gray-scale value, to obtain histogram p and the accumulative histogram c thereof of described fringe region image;
(3) with the histogram p of described fringe region image and accumulative histogram c, described original infrared image F is strengthened, the infrared image F' after being enhanced.
Described step (1), extracts the fringe region of untreated original infrared image F, to obtain fringe region image F
edge, specifically comprise following sub-step: the edge being detected described infrared image F by edge detection operator, be then set to 1 according to the gray-scale value of edge pixel, principle that the gray-scale value of non-edge pixels is set to 0 generates bianry image T
edge; Travel through described bianry image T
edgeon all pixels, for the pixel on each coordinate, if there is the pixel that gray-scale value is 1, then described fringe region image F in the pixel in the pixel on this coordinate or its neighborhood
edgegrey scale pixel value in upper same coordinate is set to the gray-scale value at described infrared image F same coordinate place, otherwise described fringe region image F
edgegrey scale pixel value on this coordinate upper is set to 0, travels through complete bianry image T
edgefringe region image F is obtained after performing above-mentioned corresponding process
edge.
Described step (2), statistics meter fringe region image F
edgein non-vanishing gray-scale value, with the step of the histogram p and accumulative histogram c thereof that obtain described fringe region, specifically comprise following process: travel through described fringe region image F
edge, the number of times that statistics gray-scale value k occurs in described fringe region image, to obtain the histogram p of described fringe region image, this histogrammic each represent with p (k), k=0,1 ..., M, M are the maximum gray scale of original infrared image F; The histogram of accumulative fringe region image is to obtain described accumulative histogram c, and each of this accumulative histogram represents with c (k), and sets c (0)=0, and computing formula is:
Described step (3), with the histogram p of fringe region image and accumulative histogram c, described original infrared image F is strengthened, the step of the infrared image F' after being enhanced, comprise following sub-step: arranged in order by k value coordinate corresponding for all nonzero terms in the histogram p of described fringe region image and build sequence v, concrete grammar is: from k=1 to k=M, travel through the every of the histogram p of described fringe region image, k value corresponding to the item of all p of meeting (k) ≠ 0 is rearranged sequence v according to order from small to large, the every of sequence v represents with v (i), i=1, 2, 3, ..., N, N is the quantity of nonzero term in the histogram p of described fringe region image, and expand sequence v and obtain sequence v', this sequence v' is every with v'(j) represent, concrete extended mode is:
The gray-scale value k of each pixel on original infrared image F is calculated, calculate and strengthen result, gray-scale value w (k) of same position place pixel on image after being enhanced, circular is: for the gray-scale value k of each pixel on original image, search in sequence v', determine which two adjacency is the size of k to be in v' between, concrete lookup method is for being ergodic sequence v', T is found to make as j=T, v'(j)≤k < v'(j+1) set up, mark T
1=v'(T), T
2=v'(T+1), and calculate the result after final Enhancement Method enhancing according to following computing formula:
wherein w (k) is for strengthening result,
represent and round downwards.
Enhancement Method of the present invention is by the histogram in statistics infrared image edge region, improve the ratio that the regions such as texture, edge, Small object occupy in statistics with histogram, make grain details strengthen successful, clear picture after strengthening, contrast is high, good visual effect.
Accompanying drawing explanation
Fig. 1 is the infrared image histogram enhancement method flow diagram that the present invention is based on edge extracting.
Fig. 2 is the refinement process flow diagram of step of the present invention (1).
Fig. 3 is the refinement process flow diagram of step of the present invention (3).
Fig. 4 illustrates the image without Enhancement Method process of the present invention.
Fig. 5 illustrates the fringe region image after step of the present invention (1) process.
Fig. 6 illustrates and processes through step of the present invention (2) the fringe region histogram obtained.
Fig. 7 illustrates the image after Enhancement Method process of the present invention.
Embodiment
Below in conjunction with drawings and Examples, the present invention is further described.As shown in Figure 1, the infrared histogram enhancement algorithm that the present invention is based on edge extracting comprises the following steps:
(1) fringe region of original infrared image F is extracted, to obtain fringe region image F
edgestep, specifically comprise following sub-step:
By edge detection operator, as Canny operator, detect the edge of described infrared image F, be then set to 1 according to the gray-scale value of edge pixel, principle that the gray-scale value of non-edge pixels is set to 0 generates bianry image T
edge;
Travel through described bianry image T
edgeon all pixels, for the pixel on each coordinate, if there is the pixel that gray-scale value is 1, then described fringe region image F in the pixel in the pixel on this coordinate or its neighborhood
edgegrey scale pixel value in upper same coordinate is set to the gray-scale value at described infrared image F same coordinate place, otherwise described fringe region image F
edgegrey scale pixel value on this coordinate upper is set to 0, travels through complete bianry image T
edgefringe region image F is obtained after performing above-mentioned corresponding process
edge;
(2) fringe region image F is added up
edgein non-vanishing gray-scale value, with the step of the histogram p and accumulative histogram c thereof that obtain described fringe region, specifically comprise following sub-step:
Travel through described fringe region image F
edge, the number of times that statistics gray-scale value k occurs in described fringe region image, to obtain the histogram p of described fringe region image, this histogrammic each represent with p (k), k=0,1 ..., M, M are the maximum gray scale of original infrared image F; The histogram of accumulative fringe region image is to obtain described accumulative histogram c, and each of this accumulative histogram represents with c (k), and sets c (0)=0, and computing formula is:
(3) strengthen described original infrared image F with the histogram p of described fringe region image and accumulative histogram c, the step of the infrared image F' after being enhanced, comprises following sub-step:
K value coordinate corresponding for all nonzero terms in the histogram p of described fringe region image is arranged in order and builds sequence v, concrete grammar is: from k=1 to k=M, travel through the every of the histogram p of described fringe region image, k value corresponding to the item of all p of meeting (k) ≠ 0 is rearranged sequence v according to order from small to large, the every of sequence v represents with v (i), i=1, 2, 3, ..., N, N is the quantity of nonzero term in the histogram p of described fringe region image, and expand sequence v and obtain sequence v', this sequence v' is every with v'(j) represent, concrete extended mode is:
The gray-scale value k of each pixel on original infrared image F is calculated, calculate and strengthen result, gray-scale value w (k) of same position place pixel on image after being enhanced, circular is: for the gray-scale value k of each pixel on original image, search in sequence v', determine which two adjacency is the size of k to be in v' between, the concrete lookup method of tool is for being ergodic sequence v', T is found to make as j=T, v'(j)≤k < v'(j+1) set up, mark T
1=v'(T), T
2=v'(T+1), and calculate the result after final Enhancement Method enhancing according to following computing formula:
wherein w (k) is for strengthening result,
represent and round downwards.
As shown in Figure 4, its be sweep type infrared system export, resolution sizes be 1024 × 1280, based on demarcate nonuniformity correction after infrared image.This infrared image is without image enhancement processing, and can see, picture contrast is poor, and image detail is difficult to differentiate.
The infrared fringe region image that Fig. 5 obtains after being through step of the present invention (1) process, in step (1), rim detection is that the Canny edge detection operator being 0.005 by threshold parameter value carries out processing.Fig. 6 is its histogram that edge area image carries out statistics with histogram and obtains.
Fig. 7 is through the infrared image that Enhancement Method process of the present invention obtains, and can see, the contrast of image is high, and details is clear, and quality is good.
Claims (4)
1., based on an infrared image histogram enhancement method for edge extracting, it is characterized in that, comprise the following steps:
(1) fringe region of original infrared image F is extracted, to obtain fringe region image F
edge;
(2) fringe region image F is added up
edgein non-vanishing gray-scale value, to obtain histogram p and the accumulative histogram c thereof of described fringe region image;
(3) with the histogram p of described fringe region image and accumulative histogram c, described original infrared image F is strengthened, the infrared image F' after being enhanced.
2. the infrared image histogram enhancement method based on edge extracting according to claim 1, is characterized in that, described step (1), extracts the fringe region of original infrared image F, to obtain fringe region image F
edgestep, specifically comprise following process:
Detected the edge of described original infrared image F by edge detection operator, be then set to 1 according to the gray-scale value of edge pixel, principle that the gray-scale value of non-edge pixels is set to 0 generates bianry image T
edge;
Travel through described bianry image T
edgeon all pixels, for the pixel on each coordinate, if there is the pixel that gray-scale value is 1, then described fringe region image F in the pixel in the pixel on this coordinate or its neighborhood
edgegrey scale pixel value in upper same coordinate is set to the gray-scale value at described infrared image F same coordinate place, otherwise described fringe region image F
edgegrey scale pixel value on this coordinate upper is set to 0, travels through complete bianry image T
edgefringe region image F is obtained after performing above-mentioned corresponding process
edge.
3. the infrared image histogram enhancement method based on edge extracting according to claim 2, is characterized in that, described step (2), statistics fringe region image F
edgein non-vanishing gray-scale value, with the step of the histogram p and accumulative histogram c thereof that obtain described fringe region, specifically comprise following process:
Travel through described fringe region image F
edge, statistics gray-scale value k is at described fringe region image F
edgethe number of times of middle appearance, to obtain the histogram p of described fringe region image, this histogrammic each represent with p (k), k=0,1 ..., M, M are the maximum gray scale of original infrared image F; The histogram of accumulative fringe region image is to obtain described accumulative histogram c, and each of this accumulative histogram represents with c (k), and sets c (0)=0, and computing formula is:
4. the infrared image histogram enhancement method based on edge extracting according to claim 3, it is characterized in that, described step (3), with the histogram p of described fringe region image and accumulative histogram c, described original infrared image F is strengthened, the step of the infrared image F' after being enhanced, comprises following process:
By described fringe region image F
edgehistogram p in k value coordinate corresponding to all nonzero terms arrange in order and build sequence v, concrete grammar is: from k=1 to k=M, travel through the every of the histogram p of described fringe region image, k value corresponding to the item of all p of meeting (k) ≠ 0 is rearranged sequence v according to order from small to large, the every of sequence v represents with v (i), i=1,2,3, ..., N, N are the quantity of nonzero term in the histogram p of described fringe region image, and expand sequence v and obtain sequence v', this sequence v' is every with v'(j) represent, concrete extended mode is:
The gray-scale value k of each pixel on original infrared image F is calculated, calculate and strengthen result, gray-scale value w (k) of same position place pixel on image after being enhanced, circular is: for the gray-scale value k of each pixel on original image, search in sequence v', determine which two adjacency is the size of k to be in v' between, concrete lookup method is ergodic sequence v', T is found to make as j=T, v'(j)≤k < v'(j+1) set up, mark T
1=v'(T), T
2=v'(T+1), and calculate the result after final Enhancement Method enhancing according to following computing formula:
wherein w (k) is for strengthening result,
represent and round downwards.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410834788.6A CN104537632B (en) | 2014-12-26 | 2014-12-26 | Infrared image histogram enhancement method based on edge extracting |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410834788.6A CN104537632B (en) | 2014-12-26 | 2014-12-26 | Infrared image histogram enhancement method based on edge extracting |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104537632A true CN104537632A (en) | 2015-04-22 |
CN104537632B CN104537632B (en) | 2017-07-11 |
Family
ID=52853151
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410834788.6A Active CN104537632B (en) | 2014-12-26 | 2014-12-26 | Infrared image histogram enhancement method based on edge extracting |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104537632B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106127713A (en) * | 2016-06-30 | 2016-11-16 | 山东中安科创光电科技有限公司 | Small and weak gas leakage target strengthens and Fast implementation |
CN106204617A (en) * | 2016-07-21 | 2016-12-07 | 大连海事大学 | Adapting to image binarization method based on residual image rectangular histogram cyclic shift |
WO2017185445A1 (en) * | 2016-04-26 | 2017-11-02 | 成都市晶林科技有限公司 | Image detail enhancement and noise suppression method applied to infrared thermal imager |
CN112634273A (en) * | 2021-03-10 | 2021-04-09 | 四川大学 | Brain metastasis segmentation system based on deep neural network and construction method thereof |
CN116681696A (en) * | 2023-07-27 | 2023-09-01 | 东莞雅达高精密塑胶模具有限公司 | Mold quality monitoring method for automatic production equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101101669A (en) * | 2007-07-13 | 2008-01-09 | 天津大学 | Image reinforcement method for self-adaptive regulation according to edge and brightness |
CN101211459A (en) * | 2007-12-21 | 2008-07-02 | 上海广电集成电路有限公司 | Boundary point processed histogram balancing method |
CN101957986A (en) * | 2010-10-11 | 2011-01-26 | 华中科技大学 | Method for realizing infrared image enhancement by controlling long and short integrals |
CN102521813A (en) * | 2011-11-21 | 2012-06-27 | 华中科技大学 | Infrared image adaptive enhancement method based on dual-platform histogram |
-
2014
- 2014-12-26 CN CN201410834788.6A patent/CN104537632B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101101669A (en) * | 2007-07-13 | 2008-01-09 | 天津大学 | Image reinforcement method for self-adaptive regulation according to edge and brightness |
CN101211459A (en) * | 2007-12-21 | 2008-07-02 | 上海广电集成电路有限公司 | Boundary point processed histogram balancing method |
CN101957986A (en) * | 2010-10-11 | 2011-01-26 | 华中科技大学 | Method for realizing infrared image enhancement by controlling long and short integrals |
CN102521813A (en) * | 2011-11-21 | 2012-06-27 | 华中科技大学 | Infrared image adaptive enhancement method based on dual-platform histogram |
Non-Patent Citations (4)
Title |
---|
H.D. CHENG ,X.J. SHI: "A simple and effective histogram equalization approach to image enhancement", 《DIGITAL SIGNAL PROCESSING》 * |
冷璐 等: "结合边缘细节局部自适应增强的直方图均衡化", 《微电子学与计算机》 * |
张志忠 等: "一种基于组合方法的红外图像增强方法", 《红外技术》 * |
赵文达 等: "基于梯度直方图变换增强红外图像的细节", 《光学精密工程》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017185445A1 (en) * | 2016-04-26 | 2017-11-02 | 成都市晶林科技有限公司 | Image detail enhancement and noise suppression method applied to infrared thermal imager |
CN106127713A (en) * | 2016-06-30 | 2016-11-16 | 山东中安科创光电科技有限公司 | Small and weak gas leakage target strengthens and Fast implementation |
CN106127713B (en) * | 2016-06-30 | 2019-02-26 | 山东中安科创光电科技有限公司 | Small and weak gas leakage target enhancing and Fast implementation |
CN106204617A (en) * | 2016-07-21 | 2016-12-07 | 大连海事大学 | Adapting to image binarization method based on residual image rectangular histogram cyclic shift |
CN106204617B (en) * | 2016-07-21 | 2018-10-02 | 大连海事大学 | Adapting to image binarization method based on residual image histogram cyclic shift |
CN112634273A (en) * | 2021-03-10 | 2021-04-09 | 四川大学 | Brain metastasis segmentation system based on deep neural network and construction method thereof |
CN116681696A (en) * | 2023-07-27 | 2023-09-01 | 东莞雅达高精密塑胶模具有限公司 | Mold quality monitoring method for automatic production equipment |
CN116681696B (en) * | 2023-07-27 | 2023-10-20 | 东莞雅达高精密塑胶模具有限公司 | Mold quality monitoring method for automatic production equipment |
Also Published As
Publication number | Publication date |
---|---|
CN104537632B (en) | 2017-07-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103077521B (en) | A kind of area-of-interest exacting method for video monitoring | |
US9946941B2 (en) | Lane detection | |
CN110717489B (en) | Method, device and storage medium for identifying text region of OSD (on Screen display) | |
US9384556B2 (en) | Image processor configured for efficient estimation and elimination of foreground information in images | |
CN102156996B (en) | Image edge detection method | |
Dutta et al. | A color edge detection algorithm in RGB color space | |
WO2017012581A1 (en) | Method and system for decoding qr code based on weighted average grey method | |
CN104537632A (en) | Infrared image histogram enhancing method based on edge extraction | |
CN104966285B (en) | A kind of detection method of salient region | |
KR20150117646A (en) | Method and apparatus for image enhancement and edge verification using at least one additional image | |
CN106204617B (en) | Adapting to image binarization method based on residual image histogram cyclic shift | |
US20160180181A1 (en) | Obstacle detecting apparatus and obstacle detecting method | |
CN105513035A (en) | Method and system for detecting human body hidden item in passive millimeter wave image | |
CN104574366A (en) | Extraction method of visual saliency area based on monocular depth map | |
CN104504652A (en) | Image denoising method capable of quickly and effectively retaining edge and directional characteristics | |
WO2016029555A1 (en) | Image interpolation method and device | |
CN104268853A (en) | Infrared image and visible image registering method | |
CN107392095A (en) | A kind of small IR targets detection algorithm based on mask image | |
CN105023265A (en) | Checkerboard angular point automatic detection method under fish-eye lens | |
CN109255792B (en) | Video image segmentation method and device, terminal equipment and storage medium | |
US8396297B2 (en) | Supervised edge detection using fractal signatures | |
US20120320433A1 (en) | Image processing method, image processing device and scanner | |
CN110414385A (en) | A kind of method for detecting lane lines and system based on homography conversion and characteristic window | |
CN104463814A (en) | Image enhancement method based on local texture directionality | |
CN106327464A (en) | Edge detection method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |