CN107833189A - The Underwater Target Detection image enchancing method of the limited self-adapting histogram equilibrium of contrast - Google Patents
The Underwater Target Detection image enchancing method of the limited self-adapting histogram equilibrium of contrast Download PDFInfo
- Publication number
- CN107833189A CN107833189A CN201711038835.6A CN201711038835A CN107833189A CN 107833189 A CN107833189 A CN 107833189A CN 201711038835 A CN201711038835 A CN 201711038835A CN 107833189 A CN107833189 A CN 107833189A
- Authority
- CN
- China
- Prior art keywords
- image
- contrast
- enhanced
- target detection
- rgb
- 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 26
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000003044 adaptive effect Effects 0.000 claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000006243 chemical reaction Methods 0.000 claims abstract description 10
- 230000009466 transformation Effects 0.000 claims abstract description 5
- 238000011158 quantitative evaluation Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000002708 enhancing effect Effects 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G06T5/70—
-
- 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 by the use of histogram techniques
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30184—Infrastructure
Abstract
The invention discloses a kind of Underwater Target Detection image enchancing method for contrasting limited self-adapting histogram equilibrium, its step includes：Calculate 4 direction Sobel edge detectors of gray level image corresponding to original color image, gradient image, and adaptive gain function；By original color image by rgb space through nonlinear transformation to HSI spaces；Brightness vector Comparison study in HSI spatial images is limited self-adapting histogram equilibrium algorithm and carries out enhancing processing；The conversion of enhanced HSI spatial images is back to rgb space；To R in enhanced RGB image, G, B component carries out the broad sense bounded multiplicative computing based on adaptive gain function respectively, obtains the enhancing image based on original image gradient information；Image is shown after being strengthened；Quantitative assessment is carried out to enhancing image.The present invention can make full use of the texture of original image to realize image enhancement processing so that the visual quality of images after processing improves, gradient information enriches.
Description
Technical Field
The invention belongs to the field of image information processing, and particularly relates to an underwater target detection image enhancement method based on contrast-limited self-adaptive histogram equalization.
Background
The underwater target detection image has special conditions of non-uniform brightness, low signal-to-noise ratio, low contrast and the like, and common underwater target detection image enhancement algorithms mainly comprise two categories of modifying illumination of the underwater image and inhibiting image contrast to reserve image edges, but inevitably reduce the visual quality of the detection image. The traditional image enhancement algorithm based on contrast enhancement has great limitations, such as histogram equalization, which performs global enhancement on an image, but enlarges noise or introduces new noise. Although the defect that global histogram equalization is difficult to adapt to local gray distribution is overcome, the local histogram equalization, namely an Adaptive Histogram Equalization (AHE), has an obvious artificial blocking effect after equalization. Therefore, contrast Limited Adaptive Histogram Equalization (CLAHE) has a clear advantage. Due to the influence of the optical characteristics of water and various particles, plankton and water body flow in water, the underwater detection image enhancement effect of the research result of direct translation and transfer contrast limited adaptive histogram equalization is still insufficient. The method combines rich gradient information of the original image with a contrast-limited adaptive histogram equalization algorithm, so that the details of the enhanced image are richer and clearer, and the contrast and the information entropy of the whole image can be effectively improved.
Disclosure of Invention
The technical problem to be solved by the invention is to research an underwater target detection image enhancement method with contrast limited self-adaptive histogram equalization in the face of objective actual requirements of accurate positioning and accurate description of underwater target detection images under the environment with non-uniform brightness, low signal-to-noise ratio and low contrast, realize denoising and enhancing processing of the underwater target detection images and improve the visual quality of the underwater target detection images.
The invention is realized by adopting the following scheme:
the underwater target detection image enhancement method based on contrast limited adaptive histogram equalization comprises the following steps:
the method comprises the following steps: acquiring an original color image of underwater target detection;
step two: calculating a 4-direction Sobel edge detector, a gradient image and an adaptive gain function of a gray level image corresponding to the original color image;
step three: carrying out nonlinear transformation on an original color image from an RGB space to an HSI space;
step four: applying a contrast limited adaptive histogram equalization algorithm to the brightness vector in the HSI space image for enhancement processing;
step five: converting the enhanced HSI space image back to an RGB space;
step six: respectively carrying out generalized bounded multiplication operation based on an adaptive gain function on R, G and B components in the enhanced RGB image to obtain an enhanced image based on original image gradient information;
step seven: converting the R, G and B components of the enhanced image from the range of [0,1] to the range of [0,255] and displaying the enhanced image;
step eight: and carrying out quantitative evaluation on the enhanced image from the aspects of mean value, contrast, information entropy, color scale and the like.
Further, in the second step, the first step,
calculating a Gray level image Gray (I) corresponding to the original color image I; selecting a Sobel operator with noise robustness to acquire an edge gradient image by utilizing the characteristic that human eyes are sensitive to high-frequency information such as edges; filtering in the conventional Sobel operator, i.e. 0 ° And 90 ° On the basis of the direction, filtering in two opposite angle directions, namely 45-degree and 135-degree directions is added;
the Sobel edge detector mask in four directions is defined as:
assuming that Z (i, j) is defined as a 3 × 3 image neighborhood of pixel point (i, j), Z (i, j) can be expressed as:
wherein z (i, j) is defined as the gray value of the pixel point (i, j);
the gradient vector of the pixel point (i, j) in the 4 directions can be defined as:
G k (i,j)＝∑∑z(i+m-1,j+n-1)×S k (m,n),k＝1,2,3,4
the gradient image of pixel point (i, j) may be defined as:
the gradient image is normalized to:
wherein, delta 1 And delta 2 A slight amount of disturbance to ensure g n (i,j)∈(0,1)；
The adaptive gain function λ (i, j) at pixel point (i, j) is expressed as:
wherein a and b are adjustable positive variables for averaging the adaptive gain function λ (i, j)
Further, in the third step, the first step,
the original color image is nonlinearly transformed from RGB space to HSI space, and the transformation formula is as follows:
wherein, the first and the second end of the pipe are connected with each other,
before conversion, the values of R, G, B are normalized to [0,1]; then after conversion, the S, I component is in the [0,1] range and H is in the [0,360] range.
Further, in the fourth step,
and (3) applying a contrast limited adaptive histogram equalization algorithm to the brightness vector I in the HSI space image for enhancement processing, and keeping the color information (H, S) unchanged.
Further, in the fifth step,
converting the enhanced HSI space image back to the RGB space, and setting the converted RGB space image as R ' G ' B ', wherein the conversion formula is as follows:
(a) RG zone (0 ≦ H <120 °):
(b) GB area (120 ≦ H <240 °):
H＝H-120°
(c) BR zone (240 ≦ H <360 °):
H＝H-240°
further, in the sixth step,
respectively carrying out generalized bounded multiplication operation based on a self-adaptive gain function on R ', G' and B 'components in the enhanced RGB image to obtain an enhanced image R' G 'B' based on original image gradient information; the generalized bounded multiply operation is represented as:
further, in the seventh step,
converting the R, G and B components of the enhanced image from the [0,1] range to the [0,255] range, and displaying the enhanced image;
the final output image can be represented as:
wherein the content of the first and second substances,
further, in the step eight, the step,
for enhanced image RGB out Quantitative evaluation is carried out from the aspects of mean value, contrast, information entropy, color scale and the like, and the related quantitative evaluation index function is expressed as follows:
mean value:wherein, mu R 、μ G And mu B Are respectively RGB out The mean of the three channel color components;
contrast ratio:wherein P (i, j; d, θ) k ) Is a gray level co-occurrence matrix; theta k Is the angle between the pixels, theta k ＝(k-1)×45°，k＝1,2,3,4；
Information entropy:
color scale:wherein α = R-G, β = (R + G)/2-B; mu.s α And mu β Are the mean values of alpha and beta, σ, respectively α And σ β Standard deviations of alpha and beta, respectively.
Description of the problems associated with image enhancement for contrast-limited adaptive histogram equalization algorithms:
(1) There are two parameters in the contrast-limited adaptive histogram equalization algorithm: a clip Coefficient (CL) and a block size (BZ). As the shear coefficient increases, the image brightness increases and the image smoothness increases; as the image block size increases, the image dynamic range increases. But the image quality enhancement effect depends mainly on the clipping factor, not the image block size. In the practical application process, the two parameters need to be set reasonably.
(2) Parameters a and b in the adaptive gain function λ (i, j) can be appropriately adjusted according to the need of contrast enhancement, so as to obtain enhanced images with different contrasts.
(3) When quantitatively evaluating an enhanced image, only a high contrast ratio cannot be required, and the contrast ratio, information entropy, and color information should be comprehensively considered.
The invention achieves the following benefits:
the method can perform denoising enhancement processing of contrast-limited adaptive histogram equalization on the image by only utilizing the self information of the single underwater target detection image with non-uniform brightness, low signal-to-noise ratio and low contrast. Firstly, carrying out contrast limited self-adaptive histogram equalization enhancement processing through an HSI space image, then carrying out self-adaptive gain by utilizing the rich gradient information of the image, and finally evaluating a dark channel prior enhanced image from comprehensive quantitative evaluation indexes such as a mean value, contrast, information entropy and color scale. The 4-direction Sobel edge detector used in the invention can fully utilize the self-abundant gradient information of the image to realize image enhancement processing, so that the processed image has improved visual quality and abundant texture information.
Drawings
FIG. 1 is a control flow diagram of the underwater target detection image enhancement method of the present invention versus constrained adaptive histogram equalization.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
Referring to fig. 1, the invention is an underwater target detection image enhancement method with a contrast-limited adaptive histogram equalization, the overall flow chart is shown in fig. 1, and the specific implementation steps are as follows:
the first step is as follows: and acquiring an original color image I of the underwater target.
The second step is that: and calculating a Gray level image Gray (I) corresponding to the original color image I. And selecting a Sobel operator with certain noise robustness to acquire an edge gradient image by utilizing the characteristic that human eyes are sensitive to high-frequency information such as edges. On the basis of traditional Sobel operator filtering (0-degree direction and 90-degree direction), filtering in two diagonal directions (45-degree direction and 135-degree direction) is added, and the noise smoothing capacity is enhanced.
The Sobel edge detector mask in four directions is defined as:
assuming that Z (i, j) is defined as a 3 × 3 image neighborhood of pixel point (i, j), Z (i, j) can be expressed as:
wherein z (i, j) is defined as the gray value of the pixel point (i, j).
The gradient vector of the pixel point (i, j) in the 4 directions can be defined as:
G k (i,j)＝∑∑z(i+m-1,j+n-1)×S k (m,n),k＝1,2,3,4
the gradient image of pixel point (i, j) may be defined as:
the gradient image is normalized to:
wherein, delta 1 And delta 2 A slight amount of disturbance to ensure g n (i,j)∈(0,1)。
To obtain an image rich in gradient information, the adaptive gain function λ (i, j) at pixel point (i, j) can be expressed as:
wherein a and b are adjustable positive variables to ensure the mean of the adaptive gain function λ (i, j)
The third step: the original color image is nonlinearly transformed from RGB space to HSI space, and the transformation formula is as follows:
wherein, the first and the second end of the pipe are connected with each other,
before conversion, the values of R, G, B should be normalized to [0,1]. Then after conversion, the S, I component is in the [0,1] range and H is in the [0,360] range.
The fourth step: and applying a contrast limited adaptive histogram equalization algorithm to the brightness vector (I) in the HSI space image for enhancement processing, and keeping the color information (H, S) unchanged.
Let the enhanced luminance vector be denoted as I ', the enhanced HSI spatial image is denoted as HSI'.
The fifth step: converting the enhanced HSI space image back to the RGB space, and setting the converted RGB space image as R ' G ' B ', wherein the conversion formula is as follows:
(a) RG zone (0. Ltoreq. H <120 ℃ C.):
(b) GB area (120 ≦ H <240 °):
H＝H-120°
(c) BR zone (240 ≦ H <360 °):
H＝H-240°
and a sixth step: and respectively carrying out generalized bounded multiplication operation based on an adaptive gain function on the R ', G' and B 'components in the enhanced RGB image to obtain an enhanced image R' G 'B' based on the original image gradient information. The generalized bounded multiply operation can be expressed as:
the seventh step: and converting the R, G and B components of the enhanced image from the [0,1] range to the [0,255] range, and displaying the enhanced image.
The final output image can be represented as:
wherein the content of the first and second substances,
step eight: for enhanced image RGB out Quantitative evaluation is carried out from the aspects of mean value, contrast, information entropy, color scale and the like, and the related quantitative evaluation index function is expressed as follows:
mean value:wherein, mu R 、μ G And mu B Are respectively RGB out Mean of three channel color components.
Contrast ratio:wherein P (i, j; d, theta) k ) Is a gray level co-occurrence matrix; theta k Is the angle between the pixels, theta k ＝(k-1)×45°，k＝1,2,3,4。
Information entropy:
color scale:wherein α = R-G, β = (R + G)/2-B; mu.s α And mu β Mean values of alpha and beta, σ, respectively α And σ β Standard deviations of alpha and beta, respectively.
Description of the problem with contrast-limited adaptive histogram equalization algorithm image enhancement:
(1) There are two parameters in the contrast-limited adaptive histogram equalization algorithm: a clipping Coefficient (CL) and an image block size (BZ). As the shear coefficient increases, the image brightness increases and the image smoothness increases; as the image block size increases, the image dynamic range increases. But the image quality enhancement effect depends mainly on the cropping coefficient rather than the image block size. In the practical application process, the two parameters need to be set reasonably.
(2) Parameters a and b in the adaptive gain function λ (i, j) can be appropriately adjusted according to the need of contrast enhancement, so as to obtain enhanced images with different contrasts.
(3) When quantitatively evaluating an enhanced image, only a high contrast ratio cannot be required, and the contrast ratio, the information entropy, and the color information should be comprehensively considered.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (8)
1. The underwater target detection image enhancement method based on contrast limited adaptive histogram equalization comprises the following steps:
the method comprises the following steps: acquiring an original color image of underwater target detection;
step two: calculating a 4-direction Sobel edge detector, a gradient image and an adaptive gain function of a gray level image corresponding to the original color image;
step three: the original color image is nonlinearly transformed from an RGB space to an HSI space;
step four: applying a contrast limited adaptive histogram equalization algorithm to the brightness vector in the HSI space image for enhancement processing;
step five: converting the enhanced HSI space image back to an RGB space;
step six: respectively carrying out generalized bounded multiplication operation based on an adaptive gain function on R, G and B components in the enhanced RGB image to obtain an enhanced image based on original image gradient information;
step seven: converting the R, G and B components of the enhanced image from the range of [0,1] to the range of [0,255] and displaying the enhanced image;
step eight: and carrying out quantitative evaluation on the enhanced image from the aspects of mean value, contrast, information entropy, color scale and the like.
2. The method of contrast limited adaptive histogram equalized underwater target detection image enhancement according to claim 1, characterized by: in the second step, the first step is that,
calculating a Gray level image Gray (I) corresponding to the original color image I; selecting a Sobel operator with noise robustness to acquire an edge gradient image by utilizing the characteristic that human eyes are sensitive to high-frequency information such as edges; on the basis of traditional Sobel operator filtering, namely filtering in the directions of 0 degrees and 90 degrees, two opposite angle directions are added, namely filtering in the directions of 45 degrees and 135 degrees;
the Sobel edge detector mask in four directions is defined as:
assuming that Z (i, j) is defined as a 3 × 3 image neighborhood of pixel point (i, j), Z (i, j) can be expressed as:
wherein z (i, j) is defined as the gray value of the pixel point (i, j);
the gradient vector of the pixel point (i, j) in the 4 directions can be defined as:
G k (i,j)＝∑∑z(i+m-1,j+n-1)×S k (m,n),k＝1,2,3,4
the gradient image of the pixel point (i, j) may be defined as:
the gradient image is normalized to:
wherein, delta 1 And delta 2 A slight disturbance amount to ensure g n (i,j)∈(0,1)；
The adaptive gain function λ (i, j) at pixel point (i, j) is expressed as:
wherein a and b are adjustable positive variables for averaging the adaptive gain function λ (i, j)
3. The contrast-limited adaptive histogram equalized underwater object detection image enhancement method according to claim 1, characterized in that: in the third step, the step (c),
the original color image is nonlinearly transformed from an RGB space to an HSI space, and the transformation formula is as follows:
wherein, the first and the second end of the pipe are connected with each other,
before conversion, the values of R, G, B are normalized to [0,1]; then after conversion, the S, I component is in the [0,1] range and H is in the [0,360] range.
4. The contrast-limited adaptive histogram equalized underwater object detection image enhancement method according to claim 1, characterized in that: the fourth step is that the number of the first step,
and (3) applying a contrast limited adaptive histogram equalization algorithm to the brightness vector I in the HSI space image for enhancement processing, and keeping the color information (H, S) unchanged.
5. The method of contrast limited adaptive histogram equalized underwater target detection image enhancement according to claim 1, characterized by: in the step five, the step of the method is that,
converting the enhanced HSI space image back to an RGB space, and setting the converted RGB space image as R ' G ' B ', wherein the conversion formula is as follows:
(a) RG zone (0. Ltoreq. H <120 ℃ C.):
(b) GB area (120 ° ≦ H <240 °):
H＝H-120°
(c) BR zone (240 ≦ H <360 °):
H＝H-240°
6. the method of contrast limited adaptive histogram equalized underwater target detection image enhancement according to claim 1, characterized by: in the step six, the step (B),
respectively carrying out generalized bounded multiplication operation based on an adaptive gain function on R ', G' and B 'components in the enhanced RGB image to obtain an enhanced image R' G 'B' based on original image gradient information; the generalized bounded multiply operation is represented as:
7. the method of contrast limited adaptive histogram equalized underwater target detection image enhancement according to claim 1, characterized by: in the seventh step, the number of the first step,
converting the R, G and B components of the enhanced image from the range of [0,1] to the range of [0,255] and displaying the enhanced image;
the final output image can be represented as:
wherein the content of the first and second substances,
8. the method of contrast limited adaptive histogram equalized underwater target detection image enhancement according to claim 1, characterized by: in the step eight, the step (c),
for enhanced image RGB out Quantitative evaluation is carried out from the aspects of mean value, contrast, information entropy, color scale and the like, and the related quantitative evaluation index function is expressed as follows:
mean value:wherein, mu R 、μ G And mu B Are respectively RGB out A mean of three channel color components;
contrast ratio:wherein P (i, j; d, θ) k ) Is a gray level co-occurrence matrix; theta k Is the angle between the pixels, theta k ＝(k-1)×45°，k＝1,2,3,4；
Information entropy:
color scale:wherein α = R-G, β = (R + G)/2-B; mu.s α And mu β Are the mean values of alpha and beta, σ, respectively α And σ β Standard deviations of alpha and beta, respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711038835.6A CN107833189A (en) | 2017-10-30 | 2017-10-30 | The Underwater Target Detection image enchancing method of the limited self-adapting histogram equilibrium of contrast |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711038835.6A CN107833189A (en) | 2017-10-30 | 2017-10-30 | The Underwater Target Detection image enchancing method of the limited self-adapting histogram equilibrium of contrast |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107833189A true CN107833189A (en) | 2018-03-23 |
Family
ID=61651071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711038835.6A Pending CN107833189A (en) | 2017-10-30 | 2017-10-30 | The Underwater Target Detection image enchancing method of the limited self-adapting histogram equilibrium of contrast |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107833189A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932706A (en) * | 2018-08-14 | 2018-12-04 | 长沙全度影像科技有限公司 | A kind of contrast and saturation degree Enhancement Method of color image |
| CN109658343A (en) * | 2018-11-05 | 2019-04-19 | 天津大学 | The underwater picture Enhancement Method of color combining conversion and adpative exposure |
| CN110009581A (en) * | 2019-03-18 | 2019-07-12 | 深圳市华星光电技术有限公司 | Image processing method, device and storage medium |
| CN110675332A (en) * | 2019-08-20 | 2020-01-10 | 广东技术师范大学 | Method for enhancing quality of metal corrosion image |
| CN112598607A (en) * | 2021-01-06 | 2021-04-02 | 安徽大学 | Endoscope image blood vessel enhancement algorithm based on improved weighted CLAHE |
| CN112950565A (en) * | 2021-02-25 | 2021-06-11 | 山东英信计算机技术有限公司 | Method and device for detecting and positioning water leakage of data center and data center |
| CN114445300A (en) * | 2022-01-29 | 2022-05-06 | 赵恒� | Nonlinear underwater image gain algorithm for hyperbolic tangent deformation function transformation |
| CN114612340A (en) * | 2022-03-25 | 2022-06-10 | 郑骐骥 | Image data denoising method and system based on step-by-step contrast enhancement |
| CN116309203A (en) * | 2023-05-19 | 2023-06-23 | 中国人民解放军国防科技大学 | Unmanned platform motion estimation method and device with polarization vision self-adaptation enhancement |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101527786A (en) * | 2009-03-31 | 2009-09-09 | 西安交通大学 | Method for strengthening definition of sight important zone in network video |
| CN103440635A (en) * | 2013-09-17 | 2013-12-11 | 厦门美图网科技有限公司 | Learning-based contrast limited adaptive histogram equalization method |
| CN103632339A (en) * | 2012-08-21 | 2014-03-12 | 张晓光 | Single image defogging method based on variation Retinex and apparatus |
| CN106056559A (en) * | 2016-06-30 | 2016-10-26 | 河海大学常州校区 | Dark-channel-prior-method-based non-uniform-light-field underwater target detection image enhancement method |
| CN107220950A (en) * | 2017-05-31 | 2017-09-29 | 常州工学院 | A kind of Underwater Target Detection image enchancing method of adaptive dark channel prior |
-
2017
- 2017-10-30 CN CN201711038835.6A patent/CN107833189A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101527786A (en) * | 2009-03-31 | 2009-09-09 | 西安交通大学 | Method for strengthening definition of sight important zone in network video |
| CN103632339A (en) * | 2012-08-21 | 2014-03-12 | 张晓光 | Single image defogging method based on variation Retinex and apparatus |
| CN103440635A (en) * | 2013-09-17 | 2013-12-11 | 厦门美图网科技有限公司 | Learning-based contrast limited adaptive histogram equalization method |
| CN106056559A (en) * | 2016-06-30 | 2016-10-26 | 河海大学常州校区 | Dark-channel-prior-method-based non-uniform-light-field underwater target detection image enhancement method |
| CN107220950A (en) * | 2017-05-31 | 2017-09-29 | 常州工学院 | A kind of Underwater Target Detection image enchancing method of adaptive dark channel prior |
Non-Patent Citations (4)
| Title |
|---|
| ZHIYUAN XU 等: "Fog Removal from Color Images using Contrast Limited Adaptive Histogram Equalization", 《2009 2ND INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING》 * |
| 张亚飞 等: "基于HSI和局部同态滤波的彩色图像增强算法", 《计算机应用与软件》 * |
| 毕国玲 等: "基于照射_反射模型和有界运算的多谱段图像增强", 《物理学报》 * |
| 闫钧宣 等: "HIS空间亮度信息的多尺度Retinex图像增强研究", 《计算机工程与应用》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932706A (en) * | 2018-08-14 | 2018-12-04 | 长沙全度影像科技有限公司 | A kind of contrast and saturation degree Enhancement Method of color image |
| CN109658343A (en) * | 2018-11-05 | 2019-04-19 | 天津大学 | The underwater picture Enhancement Method of color combining conversion and adpative exposure |
| CN109658343B (en) * | 2018-11-05 | 2023-06-16 | 天津大学 | Underwater image enhancement method combining color conversion and adaptive exposure |
| CN110009581A (en) * | 2019-03-18 | 2019-07-12 | 深圳市华星光电技术有限公司 | Image processing method, device and storage medium |
| CN110009581B (en) * | 2019-03-18 | 2021-02-02 | 深圳市华星光电技术有限公司 | Image processing method, device and storage medium |
| CN110675332A (en) * | 2019-08-20 | 2020-01-10 | 广东技术师范大学 | Method for enhancing quality of metal corrosion image |
| CN112598607B (en) * | 2021-01-06 | 2022-11-18 | 安徽大学 | Endoscope image blood vessel enhancement algorithm based on improved weighted CLAHE |
| CN112598607A (en) * | 2021-01-06 | 2021-04-02 | 安徽大学 | Endoscope image blood vessel enhancement algorithm based on improved weighted CLAHE |
| CN112950565A (en) * | 2021-02-25 | 2021-06-11 | 山东英信计算机技术有限公司 | Method and device for detecting and positioning water leakage of data center and data center |
| CN114445300A (en) * | 2022-01-29 | 2022-05-06 | 赵恒� | Nonlinear underwater image gain algorithm for hyperbolic tangent deformation function transformation |
| CN114612340A (en) * | 2022-03-25 | 2022-06-10 | 郑骐骥 | Image data denoising method and system based on step-by-step contrast enhancement |
| CN116309203A (en) * | 2023-05-19 | 2023-06-23 | 中国人民解放军国防科技大学 | Unmanned platform motion estimation method and device with polarization vision self-adaptation enhancement |
| CN116309203B (en) * | 2023-05-19 | 2023-08-01 | 中国人民解放军国防科技大学 | Unmanned platform motion estimation method and device with polarization vision self-adaptation enhancement |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107833189A (en) | The Underwater Target Detection image enchancing method of the limited self-adapting histogram equilibrium of contrast | |
| Ma et al. | Contrast limited adaptive histogram equalization-based fusion in YIQ and HSI color spaces for underwater image enhancement | |
| Pan et al. | Haze removal for a single remote sensing image based on deformed haze imaging model | |
| Wang et al. | Biologically inspired image enhancement based on Retinex | |
| Zhang et al. | Color correction and adaptive contrast enhancement for underwater image enhancement | |
| CN104156921B (en) | Self-adaptive low-illuminance or non-uniform-brightness image enhancement method | |
| Liu et al. | Detail enhancement for high-dynamic-range infrared images based on guided image filter | |
| Ma et al. | An effective fusion defogging approach for single sea fog image | |
| WO2021114564A1 (en) | Enhancement method for low-contrast infrared image | |
| Yuan et al. | A region-wised medium transmission based image dehazing method | |
| CN109919859B (en) | Outdoor scene image defogging enhancement method, computing device and storage medium thereof | |
| Wang et al. | Variational single nighttime image haze removal with a gray haze-line prior | |
| CN110619647B (en) | Method for positioning fuzzy region of image based on combination of edge point frequency domain and spatial domain characteristics | |
| CN112116542B (en) | Image contrast enhancement method, device, electronic equipment and storage medium | |
| WO2024045821A1 (en) | Image processing method and apparatus, computer device, and storage medium | |
| Park et al. | High dynamic range and super-resolution imaging from a single image | |
| CN112991197B (en) | Low-illumination video enhancement method and device based on detail preservation of dark channel | |
| CN113222866B (en) | Gray scale image enhancement method, computer readable medium and computer system | |
| Mu et al. | Low and non-uniform illumination color image enhancement using weighted guided image filtering | |
| Jiang et al. | Color image enhancement with brightness preservation using a histogram specification approach | |
| Wen et al. | Autonomous robot navigation using Retinex algorithm for multiscale image adaptability in low-light environment | |
| Xin et al. | Specular reflection image enhancement based on a dark channel prior | |
| CN110298796B (en) | Low-illumination image enhancement method based on improved Retinex and logarithmic image processing | |
| CN110910323A (en) | Underwater image enhancement method based on self-adaptive fractional order multi-scale entropy fusion | |
| WO2020107308A1 (en) | Low-light-level image rapid enhancement method and apparatus based on retinex |
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: 20180323 |