CN104156921B - Self-adaptive low-illuminance or non-uniform-brightness image enhancement method - Google Patents
Self-adaptive low-illuminance or non-uniform-brightness image enhancement method Download PDFInfo
- Publication number
- CN104156921B CN104156921B CN201410389246.2A CN201410389246A CN104156921B CN 104156921 B CN104156921 B CN 104156921B CN 201410389246 A CN201410389246 A CN 201410389246A CN 104156921 B CN104156921 B CN 104156921B
- Authority
- CN
- China
- Prior art keywords
- brightness
- image
- preprocessing
- color space
- enhancement
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000007781 pre-processing Methods 0.000 claims abstract description 69
- 230000006870 function Effects 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000013507 mapping Methods 0.000 claims abstract description 19
- 230000008859 change Effects 0.000 claims abstract description 9
- 230000011218 segmentation Effects 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims abstract description 7
- 238000005286 illumination Methods 0.000 claims description 32
- 230000003044 adaptive effect Effects 0.000 claims description 24
- 238000012937 correction Methods 0.000 claims description 22
- 238000005516 engineering process Methods 0.000 claims description 15
- 230000014509 gene expression Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 9
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 7
- 238000012546 transfer Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000016776 visual perception Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000002207 retinal effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to a self-adaptive low-illuminance or non-uniform-brightness image enhancement method. The method comprises the following steps: 1), preprocessing is performed on a low-illuminance and non-uniform-brightness image, wherein the preprocessing includes brightness preprocessing on the low-illuminance and non-uniform-brightness image, and edge enhancement is performed on the image after brightness preprocessing, so that the preprocessed image is obtained; 2), region segmentation is performed according to the brightness of the preprocessed image, corresponding mapping functions are selected according to the different characteristics of all segmented regions and corresponding self-adaptive brightness enhancement is performed; 3), saturation enhancement processing is performed on the image subjected to self-adaptive brightness enhancement segment by segment through the change characteristics of initial saturation and brightness. According to the invention, the steps are adopted to process the image, therefore, the color saturation of the image is improved, the image is enabled to be bright in color and have a better visual effect. The self-adaptive image enhancement method can be widely popularized in the fields of biomedicine, real-time monitoring, satellite remote sensing and the like.
Description
Technical Field
The invention relates to an image enhancement method, in particular to a self-adaptive image enhancement method for an image with low illumination or uneven brightness.
Background
In image processing applications, when the illuminance of the ambient light source is low or uneven, image details are often unclear, information is lost, or image quality is seriously degraded, and at this time, an image enhancement technique is required to improve the image quality so as to facilitate subsequent image processing. The image enhancement technology is to purposefully emphasize the overall or local characteristics of an image according to the application occasion of a given image, to make the original unclear image clear, or emphasize some interesting characteristics to inhibit the uninteresting characteristics, to enlarge the difference between different object characteristics in the image, to improve the image quality, to enrich the information content, to enhance the image interpretation and recognition effect, and to meet the requirements of some special analysis and processing.
The existing image enhancement technology is mainly divided into a transform domain method and a spatial domain enhancement method, wherein the transform domain method is used for enhancing images in a frequency domain, a wavelet domain or other transform domains, is mainly used for images with low signal-to-noise ratio, but has high calculation complexity; the spatial domain enhancement method is to directly enhance the image in the spatial domain, and the calculation complexity is low. The spatial domain enhancement method mainly comprises a Histogram Equalization method, a contrast-limited Adaptive Histogram Equalization method (CLAHE), a gamma-correction method, a retinal cortex theory method (Retinex) and a brightness mapping function adjustment method. Among these methods, the luminance mapping function adjustment method has good adaptability and high flexibility, and thus is widely used.
The key of the brightness mapping adjustment method is the selection of a mapping function, and the commonly used mapping functions at present comprise a sine function, an exponential function, a logarithmic function and a parabolic function. In order to make the method adapt to different images, adaptive parameters are introduced into the mapping function, and the common adaptive parameters include image brightness, standard deviation, image entropy, and the like, and the defects of adopting the adaptive parameters are illustrated:
1) tao L, Asari V K, published in Journal of Electronic Imaging, 2005, 14(4): 043006-14, "Adaptive and integrated neighboring Adaptive enhancement for nonlinear enhancement of color images" (AINDANE, nonlinear Adaptive enhancement method based on global pixels and their neighborhoods) "uses an exponential function and a standard deviation parameter for improving the visual quality of images under low or non-uniform brightness conditions. The method comprises the steps of firstly converting an image into a gray image, and then carrying out self-adaptive brightness enhancement and self-adaptive contrast enhancement on the gray image. The self-adaptive brightness enhancement is to use a specially designed function to self-adaptively adjust the global brightness, to increase the brightness of darker pixels to a greater extent, and to compress the dynamic range of the image. The self-adaptive contrast enhancement is to adjust the brightness of a certain pixel according to the relative amplitude of the pixel and the adjacent pixel, the process is also controlled by the global statistical parameters of the image in a self-adaptive manner, after the two steps are finished, the obtained image is subjected to color restoration, namely, the obtained gray image is converted into a color image on the basis of the original image property, and the image is the enhanced image.
The disadvantages of using the above method are as follows: the technology is suitable for low-illumination images, but is not suitable for images with uneven brightness; the technology involves convolution operation when calculating the whole brightness distribution information, and complex exponential operation is applied to multiple places, so that the calculation amount is large; and thirdly, the brightness of the image can be enhanced, but the color vividness cannot be effectively maintained, so that the visual effect of the image is influenced.
2) An exponential function and an image brightness parameter are used in an image enhancement method based on a Nonlinear transfer function and an image local feature, which is published in IEEE Transactions on connector Electronics 2011, 57(2):858-865, Ghimire D, Lee J for contrast enhancement of a low-illumination image and an image with uneven brightness. Firstly, in an HSV color space, carrying out blocking enhancement on an image by using a nonlinear transfer function, wherein the size of a block can be accurate to each pixel; then, the image is subjected to adaptive contrast enhancement by using the characteristics of the central pixel and the surrounding pixels.
The disadvantages of using the above method are as follows: firstly, the technology adopts fixed brightness segmentation parameters, so that the image adaptability to the image with extremely uneven brightness distribution and large brightness fluctuation is poor; the technology involves convolution operation when calculating the brightness distribution information, and the calculated amount is large; and thirdly, the brightness of the image can be enhanced, but the color vividness cannot be effectively maintained, so that the visual effect of the image is influenced.
In summary, the common image enhancement method adopting adaptive parameters still has the problems of insufficient adaptability, large computation amount, insufficient vivid color and the like.
Disclosure of Invention
In view of the above problems, it is an object of the present invention to provide an adaptive image enhancement method for low-illuminance or uneven-brightness images.
In order to achieve the purpose, the invention adopts the following technical scheme: an adaptive image enhancement method for low-illumination or uneven-brightness images comprises the following steps:
1) preprocessing the low-illumination and uneven-brightness image, wherein the preprocessing comprises preprocessing the low-illumination and uneven-brightness image in brightness, and performing edge enhancement on the image subjected to brightness preprocessing to obtain a preprocessed image;
2) performing region segmentation according to the brightness of the preprocessed image, selecting corresponding mapping functions according to different characteristics of each segmented region, and performing corresponding adaptive brightness enhancement respectively to realize overall brightness adjustment of the image;
3) and performing saturation enhancement processing on the image subjected to the segmented adaptive brightness enhancement by utilizing the characteristics of the original saturation and the brightness change to obtain a final image.
The step 1) comprises the following steps:
firstly, converting an image with low illumination or uneven brightness from an RGB color space to an HSV color space to obtain an original image in the HSV color space;
selecting an image with low illumination or uneven brightness in an RGB color space, wherein the size of the image is MXN, M is the height of the image, and N is the width of the image; any point coordinate in the image is (x, y), and x belongs to [0, M-1], y belongs to [0, N-1 ];
for a pixel at any point (x, y), R (x, y), G (x, y), and B (x, y) are defined as red, green, and blue components of the pixel in the RGB color space; converting a pixel at any point in the low-illumination or uneven-brightness image from an RGB color space to an HSV color space so as to convert the low-illumination or uneven-brightness image in the RGB color space to the HSV color space, and obtaining an original image in the HSV color space, wherein components of the pixel in the HSV color space are as follows: v (x, y) is a luminance component, S (x, y) is a saturation component, and H (x, y) is a hue component;
② calculating the average brightness value V of the original image in HSV color spacea：
Comparing the average brightness value of the original image with a brightness preprocessing threshold, and performing brightness preprocessing when the average brightness value of the original image is not greater than the brightness preprocessing threshold, or else, not performing the brightness preprocessing;
threshold value V of pretreatment according to brightnessthAnd the average brightness value V of the original imageaThe size relationship between the two images determines whether brightness preprocessing needs to be performed on the original image in the HSV color space, and the principle is as follows:
if the average brightness value V of the original imageaNot greater than the threshold V of the brightness pre-processingthThen, brightness preprocessing is carried out on the original image in the HSV color space by adopting a gamma-correction technology;
adopting gamma-correction technology to carry out brightness preprocessing on an original image in HSV color space to obtain a brightness component V of the image after brightness preprocessing1(x,y)：
Wherein, γ1Is a parameter of the gamma-correction technique, gamma1Between (0, 1), VthAccording to the experimental requirements;
brightness pretreatment is carried out on the original image by adopting a gamma-correction technology, and the obtained brightness component V of the image after brightness pretreatment1(x, y) automatically becomes the average luminance value V of the original imageaAnd is compared with a threshold value V for brightness preprocessingthIf the value is not greater than the threshold value V of the brightness preprocessingthThen the gamma correction technique is adopted again to carry out the brightness pretreatment, and then the threshold value V of the brightness pretreatment is usedthComparing, iterating and looping until the average brightness value V of the original imageaGreater than the threshold V of the brightness pre-processingthThen, the next step is carried out; if the average brightness value V of the original imageaGreater than the threshold V of the brightness pre-processingthIf so, not performing brightness preprocessing on the original image in the HSV color space;
④ performing edge enhancement on the image after brightness preprocessing to obtain a preprocessed image Vp(x,y)。
The step 2) comprises the following steps:
firstly, carrying out region segmentation according to the brightness of a preprocessed image so as to carry out corresponding self-adaptive brightness enhancement according to different characteristics of each segmented region;
presetting a preprocessed image VpThe average brightness of (x, y) is Va-pThe preprocessed image V is processedpAll pixels of (x, y) are divided into two classes VlowAnd Vhigh：VlowRepresenting the average brightness, V, of low-brightness pixelshighRepresents the average luminance of the high-luminance pixels, and the respective expressions are as follows:
wherein,sgn (·) is a sign function;
the preprocessed image V is processedpThe pixels of (x, y) are classified into three types according to the brightness: brightness is in [0, V ]low) The pixels of the interval are the preprocessed image Vp(x, y) low illumination area pixels; brightness is in [ V ]low,Vhigh) The pixels of the interval are the preprocessed image VpNormal area pixels of (x, y); brightness is in [ V ]high,255]The pixels of the interval are the preprocessed image Vp(x, y) exposed area pixels;
selecting corresponding mapping functions according to different characteristics of each segmented region, and respectively performing corresponding adaptive brightness enhancement to realize overall brightness adjustment of the image;
preprocessed image VpThe brightness histograms corresponding to the three area pixels divided by the pixel (x, y) are respectively selected from the following mapping functions to enhance the image brightness, and the formula is as follows:
wherein, Venh(x, y) represents a luminance value of the pixel at the coordinate point (x, y) after the luminance enhancement, log10(. is a base 10 logarithm):
wherein, γ2Is a parameter of the gamma-correction technique, between (0, 1).
The step 3) comprises the following steps:
the brightness change Δ V (x, y) of the pixel at (x, y) of the segmented brightness enhanced image relative to the pre-processed image is
ΔV(x,y)＝[Venh(x,y)-Vp(x,y)]/255
Average saturation value S of original image in HSV color spaceaIs composed of
And performing saturation enhancement processing on the image with the enhanced segmented brightness, wherein the process is as follows:
wherein S isenh(x, y) represents a pixel saturation value of the image after saturation enhancement processing at (x, y);
and converting the image subjected to saturation enhancement processing from the HSV color space to the RGB color space to obtain a final color image.
Due to the adoption of the technical scheme, the invention has the following advantages: 1. the invention carries out preprocessing including brightness preprocessing and edge enhancement on an original image, carries out region segmentation on the brightness of the preprocessed image, selects a corresponding mapping function according to different characteristics of each segmented region, and determines segmented parameters and principles by the characteristics of the image, so that the invention has better self-adaptability and is particularly suitable for the image with extremely uneven brightness distribution and larger brightness fluctuation. 2. The invention adopts formula operation modes of multiplication, addition and exponential function with lower power, does not contain complex operation, and reduces the calculated amount, thereby improving the image processing efficiency and facilitating the real-time image processing. 3. The invention enhances the saturation after the image brightness is enhanced, and combines the image brightness change with the original image saturation during the image saturation enhancement, thereby providing the weight coefficients which are mutually restricted and balanced, so that the image saturation enhancement has better effect, the image color saturation is improved, the image color is bright, and better visual effect is achieved. Based on the reasons, the invention can be widely popularized in the fields of biomedicine, real-time monitoring, satellite remote sensing and the like.
Drawings
FIG. 1 is a schematic flow diagram of the present invention
FIG. 2a is an original image with a histogram as a peak
FIG. 2b is an image processed using gamma correction techniques alone on an original one-peak histogram image
FIG. 2c is an image processed using CLAHE for the original one-peak histogram image
FIG. 2d is an image after AINDANE processing is applied to the original one-peak histogram image
FIG. 2e is an image processed by an image enhancement method based on a non-linear transfer function and local features of the image on an original one-peak histogram image
FIG. 2f is an image processed according to the present invention on an original one-peak histogram image
FIG. 3a is an original image with a histogram of two peaks
FIG. 3b is an image processed using gamma correction techniques alone on an original two-peak histogram image
FIG. 3c is an image processed using CLAHE for the original two-peak histogram image
FIG. 3d is an image of an original bi-peak histogram image after being processed using AINDANE
FIG. 3e is an image processed by an image enhancement method based on a non-linear transfer function and local features of the image on an original biceak histogram image
FIG. 3f is an image processed according to the present invention on an original two-peak histogram image
FIG. 4a is an original image with a histogram of three peaks
FIG. 4b is an image processed using gamma correction techniques alone on an original tri-peak histogram image
FIG. 4c is an image processed using CLAHE for the original tri-peak histogram image
FIG. 4d is an image after AINDANE processing is applied to the original tri-peak histogram image
FIG. 4e is an image processed by an image enhancement method based on a non-linear transfer function and local features of the image on an original tri-peak histogram image
FIG. 4f is an image processed according to the present invention on an original tri-peak histogram image
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
The invention processes low-illumination images or images with uneven brightness, wherein the low-illumination images refer to images with low overall brightness values, and the images with uneven brightness refer to images with uneven brightness distribution and large fluctuation.
As shown in fig. 1, the adaptive image enhancement method for low-illumination or uneven-brightness images of the present invention includes the following steps:
1) preprocessing an image with low illumination and uneven brightness, wherein the preprocessing comprises the steps of preprocessing the image with low illumination and uneven brightness, and performing edge enhancement on the image after the brightness preprocessing to obtain a preprocessed image, and the preprocessing comprises the following steps:
firstly, converting an image with low illumination or uneven brightness from an RGB color space to an HSV color space so as to be more intuitively processed (because the invention mainly processes the brightness and the saturation of the image in the HSV color space);
selecting an image with low illumination or uneven brightness in an RGB color space, wherein the size of the image is M multiplied by N, M is the height of the image, and N is the width of the image. Any point coordinate in the image is (also called a pixel point) (x, y), and x belongs to [0, M-1], y belongs to [0, N-1 ].
For a pixel at any point (x, y), R (x, y), G (x, y), and B (x, y) are defined as red, green, and blue components of the pixel in the RGB color space. Converting a pixel at any point in the low-illumination or uneven-brightness image from an RGB color space to an HSV color space through formulas (1) - (3) to convert the low-illumination or uneven-brightness image in the RGB color space to the HSV color space, and obtaining an original image in the HSV color space, wherein a brightness component V (x, y), a saturation component S (x, y) and a hue component H (x, y) of the pixel in the HSV color space are as follows:
V(x,y)＝[R(x,y)+G(x,y)+B(x,y)]/3 (1)
S(x,y)＝1-min[R(x,y),G(x,y),B(x,y)]/V(x,y) (2)
wherein, R (x, y) belongs to [0,255], G (x, y) belongs to [0,255], B (x, y) belongs to [0,255], V (x, y) belongs to [0,255] is obtained according to the formula (1), S (x, y) belongs to [0,1] is obtained according to the formula (2), H (x, y) belongs to [0,2 pi ] is obtained according to the formula (3), a min [ DEG ] function is the minimum value of all elements in the calculation [ DEG ], and arccos [ DEG ] is an inverse cosine function.
② calculating the average brightness value V of the original image in HSV color spacea：
Carrying out brightness preprocessing on an original image in the HSV color space;
threshold value V of pretreatment according to brightnessthAnd the average brightness value V of the original imageaThe size relationship between the two images determines whether brightness preprocessing needs to be performed on the original image in the HSV color space, and the principle is as follows:
if the average brightness value V of the original imageaNot greater than the threshold V of the brightness pre-processingthThen, the gamma-correction technology is adopted to carry out brightness preprocessing on the original image in the HSV color space, so that the effect is obvious when brightness enhancement is carried out subsequently.
Adopting gamma-correction technology to carry out brightness preprocessing on an original image in HSV color space to obtain a brightness component V of the image after brightness preprocessing1(x,y)：
Wherein, γ1Is a parameter of the gamma-correction technique, gamma1Between (0, 1), and is generally taken as γ1＝0.5。VthIs determined according to experimental requirements, Vth＝50。
Brightness pretreatment is carried out on the original image by adopting a gamma-correction technology, and the obtained brightness component V of the image after brightness pretreatment1(x, y) automatically becomes the average luminance value V of the original imageaAnd is compared with a threshold value V for brightness preprocessingthIf the value is not greater than the threshold value V of the brightness preprocessingthThen the gamma correction technique is adopted again to carry out the brightness pretreatment, and then the threshold value V of the brightness pretreatment is usedthComparing, iterating and looping until the average brightness value V of the original imageaGreater than the threshold V of the brightness pre-processingthSo far, then the next step is carried out.
If the average brightness value V of the original imageaGreater than the threshold V of the brightness pre-processingthThen the original image in the HSV color space is not luminance preprocessed. It should be noted that edge enhancement is required after the brightness preprocessing is not performed, so that the average brightness value V of the original image is obtained in the subsequent edge enhancement stepaGreater than the threshold V of the brightness pre-processingthThen, it is regarded that the brightness preprocessing is performed with the brightness kept unchanged.
And fourthly, performing edge enhancement on the image after brightness preprocessing, wherein the image after edge enhancement can more clearly display the boundaries of different types of objects or phenomena or the traces of linear images so as to be convenient for identifying the different types of objects and delineating the distribution range of the objects, further enable the boundaries to be clear and enable the image to have better visual effect.
In this embodiment, the laplacian gaussian detection operator is used to perform edge enhancement on the image after the brightness preprocessing, and other methods may also be used to perform edge enhancement on the image after the brightness preprocessing, which is not limited herein.
The Laplacian of Gaussian (LoG) detector combines Gaussian filtering and Laplacian detector to enhance the edges of the image, and is generally called Laplacian of Gaussian. Adopting a Gaussian Laplacian detection operator to carry out edge enhancement on the image after brightness preprocessing, and comprising the following contents:
firstly, the image brightness component V after brightness preprocessing is carried out by adopting a Gaussian function Gauss (x, y)1(x, y) is subjected to smoothing filtering, namely Gaussian filtering, then the smoothed image brightness component V2(x, y) is as follows:
wherein,representing a convolution operation;sigma is a spatial scale factor, and the value of sigma in the invention is 2.25.
Secondly, the Laplace detection operator is adopted to carry out the smoothing on the brightness component V of the image2(x, y) edge enhancement, the edge-enhanced image Vp(x, y), i.e. the preprocessed image Vp(x, y) is as follows:
Vp(x,y)＝▽2[V2(x,y)](7)
wherein, ▽2[·]A binary second order gradient.
2) According to the brightness of the preprocessed image, carrying out region segmentation, according to different characteristics of each segmented region, selecting corresponding mapping functions, and respectively carrying out corresponding adaptive brightness enhancement to realize the overall brightness adjustment of the image, wherein the method comprises the following steps:
firstly, image segmentation is carried out according to the brightness of the preprocessed image so as to carry out corresponding self-adaptive brightness enhancement according to different characteristics of each segmented region;
let pass throughPreprocessed image VpThe average brightness of (x, y) is Va-pThe preprocessed image V is processedpAll pixels of (x, y) are divided into two classes VlowAnd Vhigh：VlowRepresenting the average brightness, V, of low-brightness pixelshighRepresents the average luminance of the high-luminance pixels, and the respective expressions are as follows:
wherein,sgn (·) is a sign function.
The preprocessed image V is processedpThe pixels of (x, y) are classified into three types according to brightness: brightness is in [0, V ]low) The pixels of the interval are the preprocessed image Vp(x, y) low illumination area pixels; brightness is in [ V ]low,Vhigh) The pixels of the interval are the preprocessed image VpNormal area pixels of (x, y); brightness is in [ V ]high,255]The pixels of the interval are the preprocessed image VpAnd (x, y) exposing the area pixels. These three area pixels: the low illumination area pixel, the normal area pixel and the exposure area pixel are divided according to the preprocessed image Vp(x, y) self brightness characteristics are calculated, and the three parameters are used for classifying image pixels so that the subsequent processing is more targeted, thereby having stronger adaptability.
Selecting corresponding mapping functions according to different characteristics of each segmented region, and respectively performing corresponding adaptive brightness enhancement to realize overall brightness adjustment of the image;
preprocessed image VpThe brightness histograms corresponding to the three area pixels divided by the pixel (x, y) are respectively selected from the following mapping functions to enhance the image brightness, and the formula is as follows:
wherein, Venh(x, y) represents a luminance value of the pixel at the coordinate point (x, y) after the luminance enhancement, log10(. is a base 10 logarithm):
wherein, γ2Also a parameter of the gamma-correction technique, is between (0, 1).
3) And performing saturation enhancement processing on the image subjected to the segmented adaptive brightness enhancement by utilizing the characteristics of the original saturation and the brightness change so as to improve the visual effect of image enhancement and obtain a final image.
The brightness change Δ V (x, y) of the pixel at (x, y) of the segmented brightness enhanced image relative to the pre-processed image is
ΔV(x,y)＝[Venh(x,y)-Vp(x,y)]/255 (12)
Average saturation value S of original image in HSV color spaceaIs composed of
And performing saturation enhancement processing on the image with the enhanced segmented brightness, wherein the process is as follows:
wherein S isenh(x, y) represents a pixel saturation value of the image after the saturation enhancement processing at (x, y). In the image saturation enhancement, the image brightness mapping transformation is combined with the original image saturation, and weight coefficients which are mutually restricted and balanced are given according to the combination, so that the image saturation enhancement has a better effect. It can be seen that the coefficients and the like adopted by the saturation enhancement function are determined by the characteristics of the image, so that the method has good enhancement effect and application range.
And converting the image subjected to saturation enhancement processing from the HSV color space to the RGB color space to obtain a final color image, wherein the conversion formula is as follows:
wherein, cos [ ·]Is a cosine function, Renh(x,y)，Genh(x, y) and Benh(x, y) are the enhanced red, green and blue components of the pixel at (x, y) in the RGB color space, respectively. The image obtained by the invention has the advantages of enhanced brightness and prominent detail, and the added saturation enhancement has more bright color and is more suitable for human visual perception.
In the above embodiment, the image conversion between the HSV color space and the RGB color space may be converted by using the above listed formulas, or may be converted by using other labeling conversion formulas, which is not limited herein.
In summary, the principle of the invention is as follows: firstly, converting an image with low illumination and uneven brightness in an HSV color space into the HSV color space to obtain an original image, and preprocessing the original image, including brightness preprocessing and image edge enhancement. Then, according to the brightness of the preprocessed image, carrying out region segmentation, and according to different characteristics of each segmented region, selecting corresponding mapping functions, and respectively carrying out corresponding self-adaptive brightness enhancement. And finally, performing saturation enhancement processing on the image subjected to the segmented adaptive brightness enhancement by utilizing the characteristics of the original saturation and brightness change, and converting the obtained image back to an RGB color space to obtain a final image. The invention combines the self-adaptive brightness enhancement and the self-adaptive saturation enhancement, thereby having better enhancement effect on the image with extremely uneven brightness distribution and larger brightness fluctuation and leading the image to have better visual effect.
To better illustrate the effectiveness of the present invention, the following is illustrated by FIGS. 2-4:
in the processing result diagrams shown in fig. 2 to 4, on one hand, the effectiveness of the invention can be judged from the image processing perspective, for example, an image evaluation criterion is adopted: the image entropy judges whether the image processed by the method has uniform brightness distribution or not and good image quality.
The definition of the image entropy is:
where h (x) is the image entropy and p (i) is the probability that the image gray value i appears in the entire gray value of the image. The larger the image entropy, the more uniform the image brightness distribution is represented, and the better the image quality is. As shown in table 1, the entropy of the image processed by the method of the present invention is the largest, and the method of the present invention can better enhance the details of the image, make the image brighter, and better adapt to human visual perception, improve the visual quality of the image, and also facilitate the extraction of the required or interested region for further processing the image.
TABLE 1 entropy of images
| Entropy of images | a | b | c | d | e | f |
| FIG. 2 | 4.663 | 5.913 | 6.128 | 6.447 | 6.480 | 6.839 |
| FIG. 3 | 6.703 | 7.376 | 6.536 | 7.082 | 7.460 | 7.474 |
| FIG. 4 | 7.327 | 7.328 | 7.119 | 7.294 | 7.308 | 7.385 |
On the other hand, the algorithm complexity in the text can be proved to have more obvious enhancement effect in a lower enhancement degree from the running time. As shown in table 2, the runtime of each algorithm under VC6.0 and opencv1.0 conditions can also be seen as a distinct advantage of the runtime of the present invention, i.e. lower computational complexity, through the processing time.
TABLE 2 run time
| Run time/ms | b | c | d | e | f |
| FIG. 2 | 69 | 171 | 155 | 142 | 95 |
| FIG. 3 | 65 | 165 | 153 | 139 | 96 |
| FIG. 4 | 142 | 314 | 307 | 287 | 209 |
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (3)
1. An adaptive image enhancement method for low-illumination or uneven-brightness images comprises the following steps:
1) preprocessing the low-illumination and uneven-brightness image, wherein the preprocessing comprises preprocessing the low-illumination and uneven-brightness image in brightness, and performing edge enhancement on the image subjected to brightness preprocessing to obtain a preprocessed image;
2) performing region segmentation according to the brightness of the preprocessed image, selecting corresponding mapping functions according to different characteristics of each segmented region, and performing corresponding adaptive brightness enhancement respectively to realize overall brightness adjustment of the image;
3) the image with the segmented self-adaptive brightness enhancement is subjected to saturation enhancement processing by utilizing the characteristics of original saturation and brightness change to obtain a final image,
the step 1) comprises the following steps:
firstly, converting an image with low illumination or uneven brightness from an RGB color space to an HSV color space to obtain an original image in the HSV color space;
selecting an image with low illumination or uneven brightness in an RGB color space, wherein the size of the image is MXN, M is the height of the image, and N is the width of the image; any point coordinate in the image is (x, y), and x belongs to [0, M-1], y belongs to [0, N-1 ];
for a pixel at any point (x, y), R (x, y), G (x, y), and B (x, y) are defined as red, green, and blue components of the pixel in the RGB color space; converting a pixel at any point in the low-illumination or uneven-brightness image from an RGB color space to an HSV color space so as to convert the low-illumination or uneven-brightness image in the RGB color space to the HSV color space, and obtaining an original image in the HSV color space, wherein components of the pixel in the HSV color space are as follows: v (x, y) is a luminance component, S (x, y) is a saturation component, and H (x, y) is a hue component;
② calculating the average brightness value V of the original image in HSV color spacea：
Comparing the average brightness value of the original image with a brightness preprocessing threshold, and performing brightness preprocessing when the average brightness value of the original image is not greater than the brightness preprocessing threshold, or else, not performing the brightness preprocessing;
threshold value V of pretreatment according to brightnessthAnd the average brightness value V of the original imageaThe size relationship between the two images determines whether brightness preprocessing needs to be performed on the original image in the HSV color space, and the principle is as follows:
if the average brightness value of the original imageVaNot greater than the threshold V of the brightness pre-processingthThen, brightness preprocessing is carried out on the original image in the HSV color space by adopting a gamma-correction technology;
adopting gamma-correction technology to carry out brightness preprocessing on the original image in the HSV color space to obtain a brightness component V of the image after brightness preprocessing1(x,y)：
Wherein, γ1Is a parameter of the gamma-correction technique, gamma1Between (0, 1), VthAccording to the experimental requirements;
after brightness pretreatment is carried out on the original image by adopting a gamma-correction technology, the brightness component V of the image after the brightness pretreatment is obtained1(x, y) obtaining an average luminance value V of the original imageaAnd is compared with a threshold value V for brightness preprocessingthIf the value is not greater than the threshold value V of the brightness preprocessingthThen the gamma correction technique is adopted again to carry out the brightness pretreatment, and then the threshold value V of the brightness pretreatment is usedthComparing, iterating and looping until the average brightness value V of the original imageaGreater than the threshold V of the brightness pre-processingthThen, the next step is carried out; if the average brightness value V of the original imageaGreater than the threshold V of the brightness pre-processingthIf so, not performing brightness preprocessing on the original image in the HSV color space;
④ performing edge enhancement on the image after brightness preprocessing to obtain a preprocessed image Vp(x,y)。
2. The method of claim 1, wherein the adaptive image enhancement method comprises: the step 2) comprises the following steps:
firstly, carrying out region segmentation according to the brightness of a preprocessed image so as to carry out corresponding self-adaptive brightness enhancement according to different characteristics of each segmented region;
presetting a pre-processed imageVpThe average brightness of (x, y) is Va-pThe preprocessed image V is processedpAll pixels of (x, y) are divided into two classes VlowAnd Vhigh：VlowRepresenting the average brightness, V, of low-brightness pixelshighRepresents the average luminance of the high-luminance pixels, and the respective expressions are as follows:
wherein,sgn (·) is a sign function;
the preprocessed image V is processedpThe pixels of (x, y) are classified into three types according to the brightness: brightness is in [0, V ]low) The pixels of the interval are the preprocessed image Vp(x, y) low illumination area pixels; brightness is in [ V ]low,Vhigh) The pixels of the interval are the preprocessed image VpNormal area pixels of (x, y); brightness is in [ V ]high,255]The pixels of the interval are the preprocessed image Vp(x, y) exposed area pixels;
selecting corresponding mapping functions according to different characteristics of each segmented region, and respectively performing corresponding adaptive brightness enhancement to realize overall brightness adjustment of the image;
preprocessed image VpThe brightness histograms corresponding to the three area pixels divided by the pixel (x, y) are respectively selected from the following mapping functions to enhance the image brightness, and the formula is as follows:
wherein, Venh(x, y) represents an image at the coordinate point (x, y) after the luminance enhancementValue of the luminance of the element log10(. is a base 10 logarithm):
wherein, γ2Is a parameter of the gamma-correction technique, between (0, 1).
3. The method as claimed in claim 2, wherein the adaptive image enhancement method comprises: the step 3) comprises the following steps:
the brightness change Δ V (x, y) of the pixel at (x, y) of the segmented brightness enhanced image relative to the pre-processed image is
ΔV(x,y)＝[Venh(x,y)-Vp(x,y)]/255
Average saturation value S of original image in HSV color spaceaIs composed of
And performing saturation enhancement processing on the image with the enhanced segmented brightness, wherein the process is as follows:
wherein S isenh(x, y) represents a pixel saturation value of the image after saturation enhancement processing at (x, y);
and converting the image subjected to saturation enhancement processing from the HSV color space to the RGB color space to obtain a final color image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410389246.2A CN104156921B (en) | 2014-08-08 | 2014-08-08 | Self-adaptive low-illuminance or non-uniform-brightness image enhancement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410389246.2A CN104156921B (en) | 2014-08-08 | 2014-08-08 | Self-adaptive low-illuminance or non-uniform-brightness image enhancement method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104156921A CN104156921A (en) | 2014-11-19 |
| CN104156921B true CN104156921B (en) | 2017-02-22 |
Family
ID=51882412
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410389246.2A Expired - Fee Related CN104156921B (en) | 2014-08-08 | 2014-08-08 | Self-adaptive low-illuminance or non-uniform-brightness image enhancement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104156921B (en) |
Families Citing this family (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104517268B (en) * | 2014-12-24 | 2017-09-26 | 小米科技有限责任公司 | Adjust the method and device of brightness of image |
| CN104754184A (en) * | 2015-04-10 | 2015-07-01 | 四川理工学院 | Real-time monitoring video illumination compensation method and real-time monitoring video illumination compensation system |
| CN106441804B (en) * | 2015-08-04 | 2019-08-30 | 宁波舜宇光电信息有限公司 | Resolving power test method |
| CN105374018B (en) * | 2015-12-18 | 2018-10-19 | 厦门大学 | A method of region enhancing is carried out to image |
| CN105701780B (en) * | 2016-01-12 | 2018-09-28 | 中国科学院深圳先进技术研究院 | a kind of remote sensing image processing method and system |
| CN106023117B (en) * | 2016-06-01 | 2019-02-19 | 哈尔滨工业大学（威海） | Backlight image recovery method based on nonlinear brightness enhancement model |
| CN106327437B (en) * | 2016-08-10 | 2019-04-05 | 大连海事大学 | A kind of color documents images bearing calibration and system |
| WO2018058690A1 (en) | 2016-09-30 | 2018-04-05 | 华为技术有限公司 | Display method for edges of rectangular frame, and terminal |
| CN106504281B (en) * | 2016-12-02 | 2019-01-22 | 中国电子科技集团公司第四十四研究所 | Image quality enhancing and filtering method applied to cmos image sensor |
| CN107656454A (en) * | 2017-09-21 | 2018-02-02 | 深圳市晟达机械设计有限公司 | A kind of efficient cell monitoring management system |
| CN107644409B (en) * | 2017-09-28 | 2022-01-04 | 深圳Tcl新技术有限公司 | Image enhancement method, display device and computer-readable storage medium |
| CN108305227A (en) * | 2018-01-23 | 2018-07-20 | 中国航空工业集团公司洛阳电光设备研究所 | A kind of method that the image low brightness area that contrast is constant highlights |
| CN110136071B (en) * | 2018-02-02 | 2021-06-25 | 杭州海康威视数字技术股份有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN108364263B (en) * | 2018-02-05 | 2022-01-07 | 苏州沃科汽车科技有限公司 | Vehicle-mounted image processing method for standard definition input and high definition output |
| CN108470329A (en) * | 2018-02-12 | 2018-08-31 | 深圳市华星光电半导体显示技术有限公司 | A kind of image processing method and system |
| CN109064426B (en) * | 2018-07-26 | 2021-08-31 | 电子科技大学 | Method and device for suppressing glare in low-illumination image and enhancing image |
| CN109146811A (en) * | 2018-08-14 | 2019-01-04 | 长沙全度影像科技有限公司 | A kind of Adaptive contrast enhancement method of color image |
| CN109377462A (en) * | 2018-10-23 | 2019-02-22 | 上海鹰瞳医疗科技有限公司 | Method for processing fundus images and equipment |
| CN109493289B (en) * | 2018-10-26 | 2021-06-01 | 华侨大学 | Method for enhancing dual nonlinear images with brightness and saturation |
| CN109829859B (en) * | 2018-12-05 | 2024-05-24 | 平安科技（深圳）有限公司 | Image processing method and terminal equipment |
| CN109697706A (en) * | 2018-12-28 | 2019-04-30 | 哈尔滨工业大学 | A kind of self defined area Enhancement Method of soft image |
| CN111626965B (en) * | 2020-06-04 | 2021-03-16 | 成都星时代宇航科技有限公司 | Remote sensing image processing method, device, electronic equipment and storage medium |
| CN111931671A (en) * | 2020-08-17 | 2020-11-13 | 青岛北斗天地科技有限公司 | Face recognition method for illumination compensation in underground coal mine adverse light environment |
| WO2022087973A1 (en) * | 2020-10-29 | 2022-05-05 | Oppo广东移动通信有限公司 | Image processing method and apparatus, computer-readable medium, and electronic device |
| CN112541869A (en) * | 2020-12-07 | 2021-03-23 | 南京工程学院 | Retinex image defogging method based on matlab |
| CN112561906B (en) * | 2020-12-24 | 2024-08-02 | 百果园技术(新加坡)有限公司 | Image processing method, device, equipment and medium |
| CN114827482B (en) * | 2021-01-28 | 2023-11-03 | 抖音视界有限公司 | Image brightness adjusting method and device, electronic equipment and medium |
| CN113450272B (en) * | 2021-06-11 | 2024-04-16 | 广州方图科技有限公司 | Image enhancement method based on sinusoidal variation and application thereof |
| CN114049732B (en) * | 2021-09-29 | 2023-07-21 | 国网山东省电力公司郓城县供电公司 | Substation video monitoring method, system and storage medium |
| TWI819411B (en) * | 2021-11-23 | 2023-10-21 | 瑞昱半導體股份有限公司 | Image processing apparatus and image processing method for contrast enhancement |
| CN113822826B (en) * | 2021-11-25 | 2022-02-11 | 江苏游隼微电子有限公司 | Low-illumination image brightness enhancement method |
| CN114998159B (en) * | 2022-08-04 | 2022-10-28 | 邹城市天晖软件科技有限公司 | Design image self-adaptive enhancement method |
| CN115393228B (en) * | 2022-10-27 | 2023-03-24 | 摩尔线程智能科技(北京)有限责任公司 | Image processing method and device and graphic processing equipment |
| CN116528060B (en) * | 2023-07-04 | 2023-09-19 | 长春希达电子技术有限公司 | Dark light image enhancement device, method and device and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101340511A (en) * | 2008-08-07 | 2009-01-07 | 中兴通讯股份有限公司 | Adaptive video image enhancing method based on lightness detection |
| CN101742339A (en) * | 2010-01-14 | 2010-06-16 | 中山大学 | Method for enhancing color image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BRPI0302384B1 (en) * | 2002-07-20 | 2018-06-19 | Samsung Electronics Co., Ltd. | "METHOD FOR ADAPTABLE COLORING A COLOR, AND EQUIPMENT FOR ADAPTABLE COLORING AN IMAGE" |
-
2014
- 2014-08-08 CN CN201410389246.2A patent/CN104156921B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101340511A (en) * | 2008-08-07 | 2009-01-07 | 中兴通讯股份有限公司 | Adaptive video image enhancing method based on lightness detection |
| CN101742339A (en) * | 2010-01-14 | 2010-06-16 | 中山大学 | Method for enhancing color image |
Non-Patent Citations (1)
| Title |
|---|
| 彩色图像增强去噪研究;印文帅;《中国优秀硕士论文全文数据库 信息科技辑》;20120715;第44-45页第4.4节，图4.22 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104156921A (en) | 2014-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104156921B (en) | Self-adaptive low-illuminance or non-uniform-brightness image enhancement method | |
| Parihar et al. | Fuzzy-contextual contrast enhancement | |
| CN108122213B (en) | A kind of soft image Enhancement Method based on YCrCb | |
| Fu et al. | Retinex-based perceptual contrast enhancement in images using luminance adaptation | |
| Huang et al. | Efficient contrast enhancement using adaptive gamma correction with weighting distribution | |
| Gupta et al. | Minimum mean brightness error contrast enhancement of color images using adaptive gamma correction with color preserving framework | |
| Vishwakarma et al. | Color image enhancement techniques: a critical review | |
| CN103295206B (en) | A kind of twilight image Enhancement Method and device based on Retinex | |
| CN109919859B (en) | Outdoor scene image defogging enhancement method, computing device and storage medium thereof | |
| CN109493291A (en) | A kind of method for enhancing color image contrast ratio of adaptive gamma correction | |
| CN108154490A (en) | Based on the high-voltage transmission line insulator image enchancing method for improving fuzzy set theory | |
| Xu et al. | Colour image enhancement by virtual histogram approach | |
| Gupta et al. | New contrast enhancement approach for dark images with non-uniform illumination | |
| CN104021531A (en) | Improved method for enhancing dark environment images on basis of single-scale Retinex | |
| Priyanka et al. | Low-light image enhancement by principal component analysis | |
| CN114331873A (en) | Non-uniform illumination color image correction method based on region division | |
| Hao et al. | Retinex-like method for image enhancement in poor visibility conditions | |
| CN111968065A (en) | Self-adaptive enhancement method for image with uneven brightness | |
| Liu et al. | Enhancement of low illumination images based on an optimal hyperbolic tangent profile | |
| Kaur et al. | Image enhancement techniques: A selected review | |
| Tung et al. | ICEBIN: Image contrast enhancement based on induced norm and local patch approaches | |
| Jindal et al. | Bio-medical image enhancement based on spatial domain technique | |
| Parihar | Histogram modification and DCT based contrast enhancement | |
| David | Low illumination image enhancement algorithm using iterative recursive filter and visual gamma transformation function | |
| Gao et al. | Adaptive Low-Light Image Enhancement with Decomposition Denoising |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170222 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |