CN112184601B - Method for enhancing vein image under near infrared light source by utilizing improved CLAHE algorithm - Google Patents
Method for enhancing vein image under near infrared light source by utilizing improved CLAHE algorithm Download PDFInfo
- Publication number
- CN112184601B CN112184601B CN202010942408.6A CN202010942408A CN112184601B CN 112184601 B CN112184601 B CN 112184601B CN 202010942408 A CN202010942408 A CN 202010942408A CN 112184601 B CN112184601 B CN 112184601B
- Authority
- CN
- China
- Prior art keywords
- histogram
- image
- vein
- infrared light
- value
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 210000003462 vein Anatomy 0.000 title claims abstract description 42
- 230000002708 enhancing effect Effects 0.000 title claims abstract description 22
- 238000000638 solvent extraction Methods 0.000 claims abstract description 3
- 230000006835 compression Effects 0.000 claims description 12
- 238000007906 compression Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000012805 post-processing Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000010008 shearing Methods 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 by the use of histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/10048—Infrared 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
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Abstract
The invention provides a method for enhancing vein images under a near infrared light source by utilizing an improved CLAHE algorithm, which comprises the following steps: step 1: partitioning; step 2: calculating a histogram; step 3: the clipping Limit is calculated: step 4: pixel point redistribution; obtaining a histogram h' (x) after the reassignment treatment; step 5: equalizing the histogram; step 6: pre-outputting gray value reconstruction by pixel points; step 7: and outputting gray value reconstruction by the pixel points. The image can better emphasize a dark area or a bright area after the CLAHE image contrast enhancement algorithm is improved, and the characteristics of the vein area can be better emphasized in the vein image under the near infrared light source.
Description
Technical Field
The invention relates to a method for enhancing a vein image under a near-infrared light source by utilizing an improved CLAHE algorithm, in particular to a method for adjusting gray value remapping distribution by introducing a sine function power exponent function.
Background
At present, the vein image is mostly studied by illuminating a vein region by a near infrared light source and then adopting a method of filtering and enhancing contrast to highlight the structural characteristics of the vein.
Histogram equalization is the most common method of image enhancement contrast. Histogram equalization is largely divided into two categories, global and local. The global enhancement method mainly achieves the purpose of contrast enhancement by modifying the distribution of the image histogram; the local enhancement method mainly comprises the steps of defining a local contrast in advance, and then enhancing the local contrast to achieve the effect of enhancing image details by classical local histogram equalization technology, wherein the local histogram equalization technology comprises contrast-limited adaptive histogram equalization (contrast limited adaptive histogram equalization, CLAHE), sub-block overlapped histogram equalization and sub-block partially overlapped histogram equalization. The CLAHE method combines the advantages of two technologies of self-adaptive histogram equalization and limited contrast, is particularly suitable for low-contrast images, and has a low implementation process.
The general global histogram equalization algorithm has the problem that the histogram equalization result is not very balanced, the gray level of the equalized image is reduced, and certain details disappear; some images are not naturally over-enhanced in contrast after equalization, and thus the enhancement is not very desirable. The local method comprehensively considers the position and gray information of the pixel points, and the processing effect is often better than that of the global method. Classical local histogram equalization techniques include contrast-limited adaptive histogram equalization (contrast limited adaptive histogram equalization, CLAHE), sub-block overlap histogram equalization, sub-block partial overlap histogram equalization. The CLAHE method combines the advantages of two technologies of self-adaptive histogram equalization and limited contrast, is particularly suitable for low-contrast images, and has a low implementation process. However, the CLAHE method cannot better emphasize the dark region, i.e., the vein, when processing the vein image under the near infrared light source, so that the vein features cannot be well emphasized when the gray value of the image is uniform.
Accordingly, improvements in the art are needed.
Disclosure of Invention
The invention aims to provide a method for enhancing a vein image under a near infrared light source by using an improved CLAHE algorithm with high efficiency.
In order to solve the technical problems, the invention provides a method for enhancing vein images under a near infrared light source by utilizing an improved CLAHE algorithm, which comprises the following steps:
step 1: partitioning; dividing an input image into c x r non-overlapping sub-blocks with equal size, wherein the number of pixels contained in each sub-block is M;
step 2: calculating a histogram; h (x) is used for representing the histogram of the subblock, x represents the gray level, the value range is [0, L-1], and L is the gray level number which can appear;
step 3: the clipping Limit is calculated:
wherein: the norm Clip Limit is the contrast enhancement amplitude value;
step 4: pixel point redistribution; obtaining a histogram h' (x) after the reassignment treatment;
step 5: equalizing the histogram; carrying out histogram equalization on the histogram h' (x) subjected to the reassignment treatment, wherein the equalization result is denoted by f (x);
step 6: pre-outputting gray value reconstruction by pixel points; according to the equalization result f (x), gray values of pixel points of each sub-block are obtained and used as reference points, and gray values g of each point in the pre-output image are calculated;
step 7: and outputting gray value reconstruction by the pixel points.
As an improvement to the method of the present invention for enhancing vein images under near infrared light sources using the improved CLAHE algorithm:
in step 4:
for each sub-block, clipping the histogram h (x) of the sub-block using a corresponding clipping threshold, uniformly reassigning the clipped pixel total difference value to each gray level of the histogram, including:
avgBincr＝totalE/L
wherein total E refers to the total difference of pixels exceeding a clipping Limit; avg BIncr refers to the pixel value in the histogram that averages each gray level increase;
repeating the distribution process until all the sheared pixel points are distributed.
As a further improvement to the method of the present invention for enhancing vein images under near infrared light sources using the improved CLAHE algorithm:
in step 4:
h' (x) is used to represent the histogram of h (x) after reassignment, and there is
As a further improvement to the method of the present invention for enhancing vein images under near infrared light sources using the improved CLAHE algorithm:
in step 6:
gray values g for points in the pre-output image are calculated using bilinear interpolation techniques.
As a further improvement to the method of the present invention for enhancing vein images under near infrared light sources using the improved CLAHE algorithm:
in step 7:
according to the gray value g of each point in the pre-output image obtained in the step 6, the gray value f of each pixel point in the final image is obtained by remapping the g value through a sine function power exponent function, the effect that the vein image further enhances and highlights the vein region is achieved, and the method comprises the following steps:
wherein alpha is a compression degree coefficient of a dark region, and the region mapping degree of the dark region is controlled when the gray value of the image is remapped; beta is the compression degree coefficient of the bright region, and the region mapping degree of the bright region is controlled when the gray value of the image is remapped; and adjusting the bright/dark area characteristics of the image by using the adjustment intensity of the alpha and beta parameters through the sine function power exponent function image characteristics.
As a further improvement to the method of the present invention for enhancing vein images under near infrared light sources using the improved CLAHE algorithm:
the contrast enhancement amplitude value norm Clip Limit is 4-15.
As a further improvement to the method of the present invention for enhancing vein images under near infrared light sources using the improved CLAHE algorithm:
the compression degree coefficient α=1.8 for the dark region and the compression degree coefficient β=1.9 for the bright region.
The technical scheme of the invention is as follows: the method for adjusting the gray value remapping distribution by introducing a sine function power exponent function when the gray value remapping is performed on the basis of CLAHE image enhancement; the method comprises the following steps:
step one: and obtaining a gray level map of each sub-block area counted by the CLAHE.
Step two: setting a compression degree coefficient alpha of the dark region, and controlling the region mapping degree of the dark region when the image gray value is remapped.
Step three: setting a compression degree coefficient beta of the bright region, and controlling the region mapping degree of the bright region when the gray value of the image is remapped.
Step four: introducing a sinusoidal function power exponent functionAnd (3) reflecting the remapping of the gray values after the image enhancement, wherein g is the pre-output gray value after the original CLAHE algorithm processing.
The improved vein image result is shown in fig. 3, a in fig. 3 is an original image, b in fig. 3 is a classical histogram equalization post-processing result, c in fig. 3 is an interpolated CLAHE processing result, d in fig. 3 is an improved CLAHE final processing result of the present invention, the improved CLAHE avoids some details in histogram equalization from disappearing and contrast from being excessively enhanced abnormally, and the problem that vein region characteristics are poor after CLAHE processing is solved, so as to achieve the effect of emphasizing vein region characteristics.
The method for enhancing the vein image under the near infrared light source by utilizing the improved CLAHE algorithm has the technical advantages that:
the image can better emphasize dark areas or bright areas after the CLAHE image contrast enhancement algorithm is improved, and the characteristics of the vein areas can be better emphasized in the vein image under the near infrared light source.
Drawings
The following describes the embodiments of the present invention in further detail with reference to the accompanying drawings.
Fig. 1 is a CLAHE algorithm. (a) histogram clipping; (b) a histogram after CLAHE reassignment;
FIG. 2 is a flow chart for improving the contrast enhancement of an image by the CLAHE algorithm;
FIG. 3 is a modified vein image; a is original image, b is classical histogram equalization post-processing result, c is interpolated CLAHE processing result, and d is improved final CLAHE processing result.
Detailed Description
The invention will be further described with reference to specific examples, but the scope of the invention is not limited thereto.
Example 1, method of enhancing vein images under near infrared light source using modified CLAHE algorithm, as shown in figures 1-3,
the invention makes the vein image vein region feature under the near infrared light source more obvious by using the image enhancement method that the controllable bright and dark region is emphasized by utilizing the adjustment of the CLAHE equalization when the gray value of the image is remapped.
The CLAHE limits the enhancement amplitude of the local contrast by limiting the height of the local histogram, thereby limiting the amplification of noise and the excessive enhancement of the local contrast. Firstly, dividing an image into a plurality of sub-blocks, then carrying out histogram shearing on each sub-block (see (a) in fig. 1), then carrying out histogram equalization on each sub-block (see (b) in fig. 1), and finally obtaining a converted gray value on each pixel through interpolation operation, thereby realizing contrast limited self-adaptive image enhancement.
As shown in fig. 2, the improved CLAHE algorithm flow chart mainly comprises the following 7 steps:
step 1: and (5) blocking. The input image is divided into c x r non-overlapping sub-blocks of equal size, each sub-block containing M pixels. The larger the sub-block, the more obvious the enhancement effect, but the more image detail is lost.
Step 2: a histogram is calculated. The histogram of the sub-block is represented by h (x), where x represents the gray level, its range is [0, L-1], L is the number of possible gray levels being 256.
Step 3: the clipping Limit is calculated:
wherein: the norm Clip Limit is a contrast enhancement amplitude value that determines the amplitude of contrast enhancement, and is determined experimentally, typically taking a value between 4 and 15.
Step 4: and (5) reassigning pixel points. For each sub-block, clipping the histogram h (x) of the sub-block using a corresponding clipping threshold, uniformly reassigning the clipped pixel total difference value to each gray level of the histogram, including:
avgBincr＝totalE/L
where total E refers to the total difference of pixels exceeding the clipping Limit. avg BIncr refers to the pixel value in the histogram that averages each gray level increase.
The above-mentioned allocation process is repeated until all the sheared pixel points are allocated, as shown in (b) of fig. 1. If h' (x) is used to represent the histogram of h (x) after the reassignment process, there is
Step 5: and (5) histogram equalization. And (3) carrying out histogram equalization on the histogram h' (x) subjected to the reassignment treatment, wherein the equalization result is denoted by f (x).
Step 6: and (5) reconstructing the pre-output gray value of the pixel point. And (3) according to the equalization result f (x), obtaining gray values of central pixel points of each sub-block, taking the gray values as reference points, and calculating gray values g of each point in the pre-output image by adopting bilinear interpolation technology.
Step 7: and outputting gray value reconstruction by the pixel points. According to the gray value g of each point in the pre-output image obtained in the step 6, the gray value f of each pixel point in the final image is obtained by remapping the g value through a sine function power exponent function, the effect that the vein image further enhances and highlights the vein region is achieved, and the method comprises the following steps:
where α is a compression degree coefficient of the dark area, and when the image gray value is remapped, the area mapping degree of the dark area is controlled. Beta is the compression degree coefficient of the bright region, and the region mapping degree of the bright region is controlled when the image gray value is remapped. And adjusting the bright/dark area characteristics of the image by using the adjustment intensity of the alpha and beta parameters through the sine function power exponent function image characteristics. The vein region features are more pronounced by experimental acquisition of α=1.8, β=1.9 under irradiation from near infrared ambient light.
Finally, it should also be noted that the above list is merely a few specific embodiments of the present invention. Obviously, the invention is not limited to the above embodiments, but many variations are possible. All modifications directly derived or suggested to one skilled in the art from the present disclosure should be considered as being within the scope of the present invention.
Claims (5)
1. A method for enhancing vein images under near infrared light using improved CLAHE algorithm, characterized by: the method comprises the following steps:
step 1: partitioning; dividing an input image into c x r non-overlapping sub-blocks with equal size, wherein the number of pixels contained in each sub-block is M;
step 2: calculating a histogram; h (x) is used for representing the histogram of the subblock, x represents the gray level, the value range is [0, L-1], and L is the gray level number which can appear;
step 3: the clipping Limit is calculated:
wherein: the norm Clip Limit is the contrast enhancement amplitude value;
step 4: pixel point redistribution; obtaining a histogram h' (x) after the reassignment treatment;
step 5: equalizing the histogram; carrying out histogram equalization on the histogram h' (x) subjected to the reassignment treatment, wherein the equalization result is denoted by f (x);
step 6: pre-outputting gray value reconstruction by pixel points; according to the equalization result f (x), gray values of pixel points of each sub-block are obtained and used as reference points, and gray values g of each point in the pre-output image are calculated;
step 7: reconstructing the output gray value of the pixel point;
in step 4:
for each sub-block, clipping the histogram h (x) of the sub-block using a corresponding clipping threshold, uniformly reassigning the clipped pixel total difference value to each gray level of the histogram, including:
avgBincr＝totalE/L
wherein total E refers to the total difference of pixels exceeding a clipping Limit; avg BIncr refers to the pixel value in the histogram that averages each gray level increase;
repeating the distribution process until all the sheared pixel points are distributed;
in step 4:
h' (x) is used to represent the histogram of h (x) after reassignment, and there is
2. The method for enhancing a vein image under a near-infrared light source using a modified CLAHE algorithm as claimed in claim 1, wherein:
in step 6:
gray values g for points in the pre-output image are calculated using bilinear interpolation techniques.
3. The method of enhancing a vein image under a near-infrared light source using a modified CLAHE algorithm as claimed in claim 2, wherein:
in step 7:
according to the gray value g of each point in the pre-output image obtained in the step 6, the gray value f of each pixel point in the final image is obtained by remapping the g value through a sine function power exponent function, the effect that the vein image further enhances and highlights the vein region is achieved, and the method comprises the following steps:
wherein alpha is a compression degree coefficient of a dark region, and the region mapping degree of the dark region is controlled when the gray value of the image is remapped; beta is the compression degree coefficient of the bright region, and the region mapping degree of the bright region is controlled when the gray value of the image is remapped; and adjusting the bright/dark area characteristics of the image by using the adjustment intensity of the alpha and beta parameters through the sine function power exponent function image characteristics.
4. A method of enhancing a vein image under a near-infrared light source using a modified CLAHE algorithm as claimed in claim 3, wherein:
the contrast enhancement amplitude value norm Clip Limit is 4-15.
5. The method for enhancing a vein image under a near-infrared light source using a modified CLAHE algorithm as claimed in claim 4, wherein:
the compression degree coefficient α=1.8 for the dark region and the compression degree coefficient β=1.9 for the bright region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010942408.6A CN112184601B (en) | 2020-09-09 | 2020-09-09 | Method for enhancing vein image under near infrared light source by utilizing improved CLAHE algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010942408.6A CN112184601B (en) | 2020-09-09 | 2020-09-09 | Method for enhancing vein image under near infrared light source by utilizing improved CLAHE algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112184601A CN112184601A (en) | 2021-01-05 |
| CN112184601B true CN112184601B (en) | 2023-10-27 |
Family
ID=73920291
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010942408.6A Active CN112184601B (en) | 2020-09-09 | 2020-09-09 | Method for enhancing vein image under near infrared light source by utilizing improved CLAHE algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112184601B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114283076B (en) * | 2021-12-08 | 2024-03-29 | 凌云光技术股份有限公司 | Image processing method based on transmissivity and CLAHE algorithm |
| CN114092361B (en) * | 2022-01-20 | 2022-06-07 | 浙江芯昇电子技术有限公司 | Image local contrast enhancement method for optimizing CLAHE |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504177A (en) * | 2016-09-30 | 2017-03-15 | 广东技术师范学院 | A kind of low embedded rate compressed sensing general steganalysis method of coloured image |
| CN106651818A (en) * | 2016-11-07 | 2017-05-10 | 湖南源信光电科技有限公司 | Improved Histogram equalization low-illumination image enhancement algorithm |
| CN108389163A (en) * | 2018-01-22 | 2018-08-10 | 西安工程大学 | A kind of self-adapting enhancement method based on half-light coloured image |
| CN110852955A (en) * | 2018-08-21 | 2020-02-28 | 中南大学 | Image enhancement method based on image intensity threshold and adaptive cutting |
-
2020
- 2020-09-09 CN CN202010942408.6A patent/CN112184601B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106504177A (en) * | 2016-09-30 | 2017-03-15 | 广东技术师范学院 | A kind of low embedded rate compressed sensing general steganalysis method of coloured image |
| CN106651818A (en) * | 2016-11-07 | 2017-05-10 | 湖南源信光电科技有限公司 | Improved Histogram equalization low-illumination image enhancement algorithm |
| CN108389163A (en) * | 2018-01-22 | 2018-08-10 | 西安工程大学 | A kind of self-adapting enhancement method based on half-light coloured image |
| CN110852955A (en) * | 2018-08-21 | 2020-02-28 | 中南大学 | Image enhancement method based on image intensity threshold and adaptive cutting |
Non-Patent Citations (2)
| Title |
|---|
| 手掌静脉图像增强算法研究;黎蔚 等;微电子学与计算机;第27卷(第7期);全文 * |
| 高分辨率视频图像实时增强系统的设计;孔壮 等;视频应用与工程;第39卷(第20期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112184601A (en) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112184601B (en) | Method for enhancing vein image under near infrared light source by utilizing improved CLAHE algorithm | |
| Stark | Adaptive image contrast enhancement using generalizations of histogram equalization | |
| CN107527333B (en) | Quick image enhancement method based on gamma transformation | |
| Lin et al. | Multi-scale retinex improvement for nighttime image enhancement | |
| US6915024B1 (en) | Image sharpening by variable contrast mapping | |
| Kim et al. | Adaptive contrast enhancement using gain-controllable clipped histogram equalization | |
| CN112365424B (en) | Local self-adaptive CLAHE-based infrared image denoising enhancement method, device and system and computer-readable storage medium | |
| CN102789635B (en) | Image enhancement method and image enhancement device | |
| CN107730475A (en) | Image enchancing method and system | |
| CN114092361B (en) | Image local contrast enhancement method for optimizing CLAHE | |
| CN104268843A (en) | Image self-adaptation enhancing method based on histogram modification | |
| JP2010503056A (en) | Image enhancement method and apparatus | |
| Sonker et al. | Comparison of histogram equalization techniques for image enhancement of grayscale images of dawn and dusk | |
| Premkumar et al. | An efficient approach for colour image enhancement using Discrete Shearlet Transform | |
| CN111144419B (en) | Historical document image binarization method based on block self-adaptive homomorphic filtering | |
| CN110310250B (en) | Global histogram equalization method based on optimization model | |
| CN114627009A (en) | Image enhancement method and system based on brightness correction and fusion channel prior | |
| CN115994875A (en) | Method and system for improving digital image quality | |
| CN113947553A (en) | Image brightness enhancement method and device | |
| Wu et al. | Low-Light image enhancement algorithm based on HSI color space | |
| CN112419195A (en) | Image enhancement method based on nonlinear transformation | |
| Zhu et al. | Image enhancement using fuzzy intensity measure and adaptive clipping histogram equalization | |
| CN116703789A (en) | Image enhancement method and system | |
| Omarova et al. | Application of the Clahe method contrast enhancement of X-Ray Images | |
| Ohchi et al. | A nonlinear filter system for beautifying facial images with contrast enhancement |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |