CN114418906A - Image contrast enhancement method and system - Google Patents

Image contrast enhancement method and system Download PDF

Info

Publication number
CN114418906A
CN114418906A CN202111460339.6A CN202111460339A CN114418906A CN 114418906 A CN114418906 A CN 114418906A CN 202111460339 A CN202111460339 A CN 202111460339A CN 114418906 A CN114418906 A CN 114418906A
Authority
CN
China
Prior art keywords
image
layer
corrected image
corrected
detail
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
Application number
CN202111460339.6A
Other languages
Chinese (zh)
Inventor
陈振国
陈水忠
揭斐然
万锦锦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Northwestern Polytechnical University
Luoyang Institute of Electro Optical Equipment AVIC
Original Assignee
Northwestern Polytechnical University
Luoyang Institute of Electro Optical Equipment AVIC
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Northwestern Polytechnical University, Luoyang Institute of Electro Optical Equipment AVIC filed Critical Northwestern Polytechnical University
Priority to CN202111460339.6A priority Critical patent/CN114418906A/en
Publication of CN114418906A publication Critical patent/CN114418906A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G06T5/70—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
    • G06T5/94—
    • 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
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging

Abstract

The invention provides an image contrast enhancement method and system, and belongs to the technical field of image processing. Firstly, acquiring an image to be processed, setting different gamma parameters to correct the image to be processed, decomposing each corrected image into a basic layer and a detail layer, then calculating a weighting coefficient matrix of the basic layer and the detail layer of each corrected image, and finally performing weighting fusion on the basic layer and the detail layer of each corrected image to obtain an image contrast enhancement result. The method can realize the contrast stretching of different gray scale intervals of different areas of the image in different degrees, simultaneously not only retains the original space structure of the image, but also highlights the detail information of the image, and integrates the optimal parts in different gamma correction results in the fusion process, so that the different gray scale intervals of different areas in the image to be processed can obtain good contrast and detail enhancement effect, and the method can be more suitable for the contrast enhancement requirements of complex images under different conditions.

Description

Image contrast enhancement method and system
Technical Field
The invention relates to an image contrast enhancement method and system, and belongs to the technical field of image processing.
Background
In the process of forming, transmitting or transforming a digital image, the digital image is influenced by various uncertain or uncontrollable factors, such as insufficient illumination, insufficient or excessive exposure, backlight, shadow, signal attenuation and the like, and the whole or local image may show a phenomenon of insufficient contrast, which causes discomfort of human eye observation or difficulty of information extraction, so that the digital image needs to be subjected to image enhancement to improve the image quality, enrich the image information, enhance the image interpretation and identification effects and meet the requirements of human eye observation or processing analysis.
Contrast enhancement algorithms are processes that modify the original gray (or color) values with some brightness correction function. The traditional contrast enhancement algorithm mainly comprises histogram equalization, linear transformation, derivative methods thereof and the like, and the methods are simple but have weak adaptability and are easy to generate an over-enhancement phenomenon, so that the details of part of images can be sacrificed while the contrast is improved. In recent years, adaptive contrast enhancement algorithms such as Retinex, homomorphic filtering, a content-based multi-channel low-brightness image enhancement algorithm (CA-CD), a weight distribution adaptive gamma correction contrast enhancement Algorithm (AGCWD) and the like are proposed, and the adaptive contrast enhancement algorithms extract and analyze global or local features of an image and automatically select appropriate algorithm parameters or generate correction functions suitable for the features according to the features to realize targeted and adaptive effective processing on the image. However, each image is complex, and when the contrast stretching of a certain region of the image is realized through one continuous correction function, the gray scale (color) distribution of other regions in the image is often suppressed, so that the contrast enhancement requirement of a complex image with multiple characteristics cannot be met, and the subsequent image processing and research are not facilitated.
Disclosure of Invention
The invention aims to provide an image contrast enhancement method and system, which are used for meeting the contrast enhancement requirements of complex images under different conditions.
The invention provides an image contrast enhancement method, which comprises the following steps:
1) acquiring an image G to be processed; setting at least two gamma parameters to respectively correct the image G to be processed to obtain at least two corresponding corrected images Gn；
2) Each corrected image GnAre all decomposed into a base layer
Figure BDA0003389689340000021
And detail layer
Figure BDA0003389689340000022
Obtaining a base layer for each corrected image
Figure BDA0003389689340000023
And a detail layer for each corrected image
Figure BDA0003389689340000024
Base layer of each corrected image
Figure BDA0003389689340000025
Obtaining the corrected image by mean filtering;
3) calculating the weighting coefficient matrix of the basic layer and the detail layer of each corrected image to obtain the weighting coefficient matrix corresponding to the basic layer of each corrected image
Figure BDA0003389689340000026
Weighting coefficient matrix corresponding to each corrected image detail layer
Figure BDA0003389689340000027
When calculating the weighting coefficient matrix of each corrected image base layer, firstly setting an operator and a first window size, calculating the characteristic intensity of each pixel point of each corrected image base layer by using the setting operator, and corresponding to the same pixel position of each corrected image base layerObtaining a base layer preliminary weighting coefficient matrix according to the characteristic intensity, and guiding and filtering the base layer preliminary weighting coefficient matrix according to the set first window size; when the weighting coefficient matrix of each corrected image detail layer is calculated, obtaining a detail layer preliminary weighting coefficient matrix according to the absolute value of the pixel value of the same pixel position of each corrected image detail layer, then setting a second window size, and guiding and filtering the detail layer preliminary weighting coefficient matrix according to the set second window size;
4) according to the weighting coefficient matrix of each corrected image base layer
Figure BDA0003389689340000028
And a weighting coefficient matrix for each corrected image detail layer
Figure BDA0003389689340000029
And performing weighted fusion on the basic layer and the detail layer of all the corrected images to realize image enhancement of the image to be processed.
The invention also provides an image contrast enhancement system comprising a processor and a memory, the processor executing a computer program stored by the memory to implement the image contrast enhancement method according to the invention.
The method comprises the steps of firstly correcting an image to be processed by setting different gamma parameters, decomposing the image corrected by each gamma parameter into a basic layer and a characteristic layer, then calculating a weighting coefficient matrix of the basic layer and the detail layer of each corrected image, and finally performing weighting fusion on each corrected image basic layer and each corrected image detail layer to obtain an image contrast enhancement result. The method realizes the contrast stretching of different gray scale intervals of different regions of the image to be processed in different degrees by setting different gamma correction parameters, decomposes the image into a basic layer and a detail layer and adopts guide filtering for smoothing, not only retains the original space structure of the image, but also highlights the detail information of the image, and finally integrates the optimal layout in different gamma correction results in the fusion process, so that the different gray scale intervals of different regions of the image to be processed can obtain good contrast and detail enhancement effects, and the method can be more suitable for the contrast enhancement requirements of complex images under different conditions.
Further, in order to highlight the image detail information while retaining the original structure information of the image, the corrected image decomposition base layer in the step 2) is
Figure BDA00033896893400000210
And detail layer
Figure BDA00033896893400000211
The formula of (1) is:
Figure BDA0003389689340000031
Figure BDA0003389689340000032
in the formula, GnFor the gamma corrected image, a is the mean filter and a convolution operation.
Further, in order to highlight the optimal information of the image base layer, the weighted matrix calculation formula of the corrected image base layer in step 3) is as follows:
Figure BDA0003389689340000033
Figure BDA0003389689340000034
Figure BDA0003389689340000035
Figure BDA0003389689340000036
Figure BDA0003389689340000037
wherein L is 3X 3 Laplacian, | HnIs to H |nThe absolute value of (d) is taken,
Figure BDA0003389689340000038
is represented by GnTo guide the image, rBTo guide the filtering window size pair
Figure BDA0003389689340000039
A guided filtering operation is performed.
Further, in order to better achieve the smoothing of the base layer weighting coefficients, the first window size is twice or more than the second window size.
Further, in order to highlight the optimal information of the image detail layer, the weighting coefficient matrix of the corrected image detail layer in step 3) is calculated by the following formula:
Figure BDA00033896893400000310
Figure BDA00033896893400000311
Figure BDA00033896893400000312
Figure BDA00033896893400000313
in the formula (I), the compound is shown in the specification,
Figure BDA0003389689340000041
is to
Figure BDA0003389689340000042
The absolute value of (d) is taken,
Figure BDA0003389689340000043
is represented by GnTo guide the image, rDTo guide the filtering window size pair
Figure BDA0003389689340000044
A guided filtering operation is performed.
Further, in order to achieve smoothing of weighting coefficients of the image detail layer, the second window size value interval is [3, 21 ].
Further, the weighted fusion formula in step 4) is:
Figure BDA0003389689340000045
in the formula, E is the result of image contrast enhancement, and is a dot product operation.
Further, in order to enable images under different gray information to obtain a good contrast stretching effect, when the image to be processed is dark, the gamma parameter smaller than 1 is set to be small; when the image to be processed is bright, the gamma parameter setting larger than 1 is large.
Drawings
FIG. 1 is a flow chart of an image contrast enhancement method of the present invention;
FIG. 2 is an image to be processed in an embodiment of the present invention;
fig. 3 is a correction result of an image to be processed when γ is 0.5 in the embodiment of the present invention;
fig. 4 is a correction result of an image to be processed when γ is 0.8 in the embodiment of the present invention;
fig. 5 is a correction result of an image to be processed when γ is 1.25 in the embodiment of the present invention;
fig. 6 is a correction result of an image to be processed when γ is 2 in the embodiment of the present invention;
FIG. 7 is a graph illustrating the result of image contrast enhancement after fusion of different gamma correction results according to an embodiment of the present invention;
fig. 8 is a base layer image obtained by decomposing the corrected image when γ is 0.5 in the embodiment of the present invention;
fig. 9 is an image of the base layer image corresponding to the initial weighting coefficient matrix when γ is 0.5 in the embodiment of the present invention;
fig. 10 is an image under the weight coefficient matrix after filtering corresponding to the base layer image when γ is 0.5 in the embodiment of the present invention;
fig. 11 is a detail layer image obtained by decomposing the corrected image when γ is 0.5 in the embodiment of the present invention;
fig. 12 is an image of a detail layer image corresponding to an initial weighting coefficient matrix when γ is 0.5 in the embodiment of the present invention;
fig. 13 is an image in the weight coefficient matrix after filtering corresponding to the detail layer image when γ is 0.5 in the embodiment of the present invention.
Detailed Description
The following further describes embodiments of the present invention with reference to the drawings.
The specific flow of the image contrast enhancement method provided by the invention is shown in fig. 1. Firstly, acquiring an image to be processed, setting at least two gamma parameters to correct the image to be processed, decomposing the image corrected by each gamma parameter into a basic layer and a characteristic layer, then calculating a weighting coefficient matrix of the basic layer and the detail layer of each corrected image, and finally performing weighting fusion on each corrected image basic layer and each corrected image detail layer to realize image contrast enhancement. The method realizes the contrast stretching of different degrees of different gray scale intervals of different regions of an image to be processed by setting different gamma correction parameters, decomposes the image into a basic layer and a detail layer for smoothing by adopting guide filtering, not only retains the original space structure of the image, but also highlights the detail information of the image, and finally integrates the optimal parts in different gamma correction results in the fusion process, so that the different gray scale intervals of different regions in the image to be processed can obtain good contrast and detail enhancement effects, and the method can be more suitable for the contrast enhancement requirements of complex images under different conditions.
Step 1. obtaining image and correcting image
First, a to-be-processed image G, which is shown in fig. 2 in this embodiment, is acquired. In order to realize contrast stretching of different degrees of different gray scale intervals of an image, at least two gamma parameters gamma are setnAnd respectively correcting the modulated images by the set gamma parameters to obtain corrected images Gn(N ═ 1, 2., N), where N is the number of gamma parameters set. The gamma parameter less than 1 is used for realizing the stretching of the dark part area of the image and enhancing the detail information of the dark part area of the image, and under the condition of dark images, the smaller the gamma parameter less than 1 is, the more the detail information of the dark part of the image can be enhanced; the gamma parameter is larger than 1, so as to stretch the bright part area of the image, the detail information of the bright part area of the image is enhanced, and when the image is bright, the detail information of the bright part of the image can be enhanced as the gamma parameter larger than 1 is set.
In the present embodiment, the gamma parameter γnSetting to {0.5, 0.8, 1, 1.25, 2}, and correcting the images to be processed G by using the 5 gamma parameters to obtain corresponding 5 corrected images Gn (n ═ 1.., 5); when γ is 0.5, the corrected image of the image to be processed is as shown in fig. 3, and when γ is 0.8; the corrected image of the image to be processed is shown in fig. 4; when gamma is 1, the image to be processed is still as shown in fig. 1 without any change; when γ is 1.25, the corrected image of the image to be processed is as shown in fig. 5; when γ is 2, the corrected image of the image to be processed is as shown in fig. 6. As can be seen from fig. 3 and 4, comparing fig. 1, when the gamma value is less than 1, the information of the dark area of the image is enhanced, i.e. the shadows in the face and window of the right side part in the image are enhanced, and the information of the bright area is suppressed, i.e. the tree on the left side in the image is not as clear as in fig. 2, and meanwhile, the smaller the value of gamma is, the more obvious the detail enhancement of the dark area in the image to be processed is, the better the stretching effect is, the more obvious the suppression of the bright area of the image to be processed is; as can be seen from fig. 5 and 6, when the gamma value is greater than 1, the information of the bright area of the image is enhanced, i.e. the left part of the tree is more clear, and the information of the dark area is suppressed, i.e. the right part of the tree is suppressed, as compared with fig. 2The shadows in part of the human faces and the vehicle windows are obviously less clear than those in the image 2, and meanwhile, the larger the value of gamma is, the more obvious the detail enhancement of the dark part area in the image to be processed is, the better the stretching effect is, and the more obvious the inhibition of the dark part area of the image to be processed is.
Step 2, decomposition of corrected image
In order to keep the original structure information of each corrected image and highlight the detail information of each corrected image, the invention makes each corrected image Gn(N ═ 1, 2.., N) is decomposed into base layers
Figure BDA0003389689340000061
And detail layer
Figure BDA0003389689340000062
Wherein the base layer is obtained by mean filtering the corrected image, and the detail layer is the corrected image GnMinus the base layer
Figure BDA0003389689340000063
Namely the fine pitch layer
Figure BDA0003389689340000064
G is to ben(N ═ 1.., N) is decomposed into base layers
Figure BDA0003389689340000065
And detail layer
Figure BDA0003389689340000066
The calculation formula of (2) is as follows:
Figure BDA0003389689340000067
Figure BDA0003389689340000068
in the formula, a is an average filter and a convolution operation.
In this embodiment, 5 corrected images are obtained through step 1, and all of the 5 corrected images are decomposed into a base layer and a detail layer according to the above formula (1) and formula (2). When γ is 0.5, the base layer generated after the corrected image is decomposed is as shown in fig. 8, and the detail layer is as shown in fig. 11, it can be seen that the base information and the detail information in fig. 3 are obviously decomposed, not only the original structure of the image is retained, but also the details of the image are highlighted.
Step 3, calculating the weight coefficient matrix of the basic layer and the detail layer
Obtaining the base layer of each corrected image through step 2
Figure BDA0003389689340000069
And detail layer
Figure BDA00033896893400000610
In order to extract the information of the base layer and the information of the detail layer of each corrected image and obtain the optimal information of the base layer and the detail layer of each corrected image, the invention needs to calculate the weight coefficient matrix of the base layer and the detail layer of each corrected image, and represents the importance degree of the information in the base layer and the detail layer of each corrected image according to the calculated weight coefficient.
When calculating the weight coefficient matrix of each corrected image base layer, firstly performing convolution processing on the corrected image base layer by using a set Laplacian operator to calculate the characteristic intensity of each pixel point of the image, and then comparing the characteristic intensities corresponding to the same pixel position of each corrected image base layer to obtain a primary base layer weight coefficient matrix
Figure BDA0003389689340000071
Then setting a first window size, and guiding and filtering the preliminary base layer weighting coefficient matrix according to the first window size and the corrected image to obtain the weighting coefficient matrix of each corrected image base layer
Figure BDA0003389689340000072
The calculation formula is as follows:
Figure BDA0003389689340000073
Figure BDA0003389689340000074
Figure BDA0003389689340000075
Figure BDA0003389689340000076
Figure BDA0003389689340000077
wherein L is 3X 3 Laplacian, | HnIs to H |nThe absolute value of (d) is taken,
Figure BDA0003389689340000078
is represented by GnTo guide the image, rBGuiding the pair of filter window sizes for a first window size
Figure BDA0003389689340000079
Conducting a guided filtering operation, rBIs a positive integer with a value range of [21, 51 ]]. In this embodiment, the operator is set to laplacian, and the first window size is set to 45. As other embodiments, the selection of the operator and the setting of the first window size may both be determined according to the specific input image. The first window size is set in relation to the second window size, and is typically twice or more as large as the second window size, but may not be set too large.
When calculating the weight coefficient matrix of each corrected image detail layer, the same pixel bit of each corrected image detail layer is comparedSetting the absolute value of the pixel value to obtain a primary detail layer weighting coefficient matrix
Figure BDA00033896893400000710
Then setting a second window size, and conducting guide filtering processing on the preliminary detail layer weighting coefficient matrix according to the second window size to obtain the weighting coefficient matrix of each corrected image detail layer
Figure BDA00033896893400000711
The calculation formula is as follows:
Figure BDA0003389689340000081
Figure BDA0003389689340000082
Figure BDA0003389689340000083
Figure BDA0003389689340000084
in the formula (I), the compound is shown in the specification,
Figure BDA0003389689340000085
is to
Figure BDA0003389689340000086
The absolute value of (d) is taken,
Figure BDA0003389689340000087
is represented by GnTo guide the image, rDFor the second window size, i.e. the guide filter window size pair
Figure BDA0003389689340000088
A guided filtering operation is performed. r isDTo be just neatNumber, value range is [3, 21]]. In the present embodiment, the second window size is set to 7. As another embodiment, the setting of the size of the second window may be determined according to a specific input image.
In this embodiment, 5 base layers and detail layers obtained in step 2 are calculated by using the above weight calculation formula, so as to obtain an image corresponding to the initial weighting coefficient matrix and an image corresponding to the filtered weighting coefficient matrix corresponding to each base layer and detail layer. In the base layer image (fig. 8) and the detail layer image (fig. 11) when γ is 0.5, the obtained image corresponding to the base layer preliminary weighting coefficient matrix is shown in fig. 9, the image corresponding to the base layer filtered weighting coefficient matrix is shown in fig. 10, the obtained image corresponding to the detail layer preliminary weighting coefficient matrix is shown in fig. 12, and the image corresponding to the detail layer filtered weighting coefficient matrix is shown in fig. 13. By calculating the weight coefficients of the base layer and the detail layer, the basic information and the detail information in the image are better highlighted, the optimal information of the gamma-corrected image base layer and the detail layer is obtained, and the image detail and the image contrast are further enhanced.
Step 4, image weighted fusion
In order to enhance the contrast of the image to be processed, the optimal information of each corrected image base layer and each corrected image detail layer can be obtained according to the weight coefficient of each corrected image base layer and each corrected image detail layer, and the optimal information of each corrected image base layer and each corrected image detail layer is fused, so that different gray scale intervals in different areas in the image to be processed can obtain good contrast and detail enhancement effects, and the contrast enhancement of the image to be processed is completed.
Obtaining a weight coefficient matrix of each corrected image base layer according to the step 3
Figure BDA0003389689340000091
And a weight coefficient matrix for each corrected image detail layer
Figure BDA0003389689340000092
For each corrected image base layer
Figure BDA0003389689340000093
And each corrected image detail layer
Figure BDA0003389689340000094
Carrying out weighted fusion to obtain an image enhancement result E:
Figure BDA0003389689340000095
in the formula, the product is a dot product operation.
In this embodiment, the 5 corrected image base layer and detail layer pairs obtained in step 3
Figure BDA0003389689340000096
And
Figure BDA0003389689340000097
the image contrast enhancement results obtained by performing weighted fusion are shown in fig. 7. Taking gamma equal to 0.5 as an example, a contrast image 2 (original image) and a contrast image 7 are obtained, and the enhancement effect of each corrected image is synthesized in the contrast image 7, so that the bright part and the dark part in the final fusion result image are both enhanced in contrast and detail, and as is obvious from the contrast image 7, compared with the contrast image 2, the human face and the shadow in the vehicle window in the dark part area on the right side are both enhanced, and meanwhile, the tree in the bright part area on the left side is clearer. The invention proves that the image can obtain good contrast and detail enhancement effect in different gray scale intervals, and the contrast enhancement requirement of the image can be met.
System embodiment
The system proposed by the present invention comprises a processor, a memory in which a computer program is stored which is executable on the processor, said processor implementing the method of the above-described method embodiments when executing the computer program. That is, the method in the above method embodiments is to be understood as a flow chart in which the image contrast enhancement method can be implemented by computer program instructions. These computer program instructions may be provided to a processor such that execution of the instructions by the processor results in the implementation of the functions specified in the method flow described above.
The processor referred to in this embodiment refers to a processing device such as a microprocessor MCU or a programmable logic device FPGA; the memory referred to in this embodiment includes a physical device for storing information, and generally, information is digitized and then stored in a medium using an electric, magnetic, optical, or the like. For example: various memories for storing information by using an electric energy mode, such as RAM, ROM and the like; various memories for storing information by magnetic energy, such as hard disk, floppy disk, magnetic tape, magnetic core memory, bubble memory, and U disk; various types of memory, CD or DVD, that store information optically. Of course, there are other types of memory, such as quantum memory, graphene memory, and the like.
The apparatus comprising the memory, the processor and the computer program is realized by the processor executing corresponding program instructions in the computer, and the processor can be loaded with various operating systems, such as windows operating system, linux system, android, iOS system, and the like. As other embodiments, the system may further include a display for displaying the result of the image contrast enhancement for reference by the staff.

Claims (9)

1. An image contrast enhancement method, characterized in that it comprises the steps of:
1) acquiring an image G to be processed, setting at least two gamma parameters to correct the image G to be processed respectively, and obtaining at least two corresponding corrected images Gn；
2) Each corrected image GnAre all decomposed into a base layer
Figure FDA0003389689330000011
And detail layer
Figure FDA0003389689330000012
Obtaining a base layer for each corrected image
Figure FDA0003389689330000013
And a detail layer for each corrected image
Figure FDA0003389689330000014
Base layer of each corrected image
Figure FDA0003389689330000015
Obtaining the corrected image by mean filtering;
3) calculating the weighting coefficient matrix of the basic layer and the detail layer of each corrected image to obtain the weighting coefficient matrix corresponding to the basic layer of each corrected image
Figure FDA0003389689330000016
Weighting coefficient matrix corresponding to each corrected image detail layer
Figure FDA0003389689330000017
When calculating the weighting coefficient matrix of each corrected image base layer, firstly setting an operator and a first window size, calculating the characteristic intensity of each pixel point of each corrected image base layer by using the setting operator, obtaining a base layer preliminary weighting coefficient matrix according to the characteristic intensity corresponding to the same pixel position of each corrected image base layer, and guiding and filtering the base layer preliminary weighting coefficient matrix according to the set first window size; when the weighting coefficient matrix of each corrected image detail layer is calculated, obtaining a detail layer preliminary weighting coefficient matrix according to the absolute value of the pixel value of the same pixel position of each corrected image detail layer, then setting a second window size, and guiding and filtering the detail layer preliminary weighting coefficient matrix according to the set second window size;
4) according to the weighting coefficient matrix of each corrected image base layer
Figure FDA0003389689330000018
And a weighting coefficient matrix for each corrected image detail layer
Figure FDA0003389689330000019
And performing weighted fusion on the basic layer and the detail layer of all the corrected images to realize image enhancement of the image to be processed.
2. The image contrast enhancement method of claim 1, wherein the corrected image decomposition base layer in step 2)
Figure FDA00033896893300000110
And detail layer
Figure FDA00033896893300000111
The formula of (1) is:
Figure FDA00033896893300000112
Figure FDA00033896893300000113
in the formula, GnFor the corrected image, a is the mean filter and a convolution operation.
3. The method for enhancing image contrast of claim 1, wherein the weighting matrix of the corrected image base layer in step 3) is calculated by the following formula:
Figure FDA00033896893300000114
Figure FDA00033896893300000115
Figure FDA0003389689330000021
Figure FDA0003389689330000022
Figure FDA0003389689330000023
wherein L is 3X 3 Laplacian, | HnIs to H |nThe absolute value of (d) is taken,
Figure FDA0003389689330000024
is represented by GnTo guide the image, rBIs a first window size pair
Figure FDA0003389689330000025
A guided filtering operation is performed.
4. The method for enhancing image contrast of claim 1, wherein the first window size in step 3) is twice or more the second window size.
5. The image contrast enhancement method according to claim 1 or 3, wherein the weighting coefficient matrix of the corrected image detail layer in step 3) is calculated by the following formula:
Figure FDA0003389689330000026
Figure FDA0003389689330000027
Figure FDA0003389689330000028
Figure FDA0003389689330000029
in the formula (I), the compound is shown in the specification,
Figure FDA00033896893300000210
is to
Figure FDA00033896893300000211
The absolute value of (d) is taken,
Figure FDA00033896893300000212
is represented by GnTo guide the image, rDIs the second window size pair
Figure FDA00033896893300000213
A guided filtering operation is performed.
6. The method of image contrast enhancement according to claim 1, wherein the second window size interval is [3, 21 ].
7. The image contrast enhancement method according to claim 1, wherein the weighted fusion formula in step 4) is:
Figure FDA00033896893300000214
in the formula, E is the result of image contrast enhancement, and is a dot product operation.
8. The image contrast enhancement method according to claim 1, wherein when the image to be processed is dark, the gamma parameter setting smaller than 1 is small; when the image to be processed is bright, the gamma parameter setting larger than 1 is large.
9. An image contrast enhancement system comprising a processor and a memory, said processor executing a computer program stored by said memory to implement the image contrast enhancement method as claimed in any one of claims 1 to 8.
CN202111460339.6A 2021-12-02 2021-12-02 Image contrast enhancement method and system Pending CN114418906A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111460339.6A CN114418906A (en) 2021-12-02 2021-12-02 Image contrast enhancement method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111460339.6A CN114418906A (en) 2021-12-02 2021-12-02 Image contrast enhancement method and system

Publications (1)

Publication Number Publication Date
CN114418906A true CN114418906A (en) 2022-04-29

Family

ID=81266311

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111460339.6A Pending CN114418906A (en) 2021-12-02 2021-12-02 Image contrast enhancement method and system

Country Status (1)

Country Link
CN (1) CN114418906A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117541654A (en) * 2024-01-09 2024-02-09 广东泰一高新技术发展有限公司 Detail enhancement method for high-resolution remote sensing image

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117541654A (en) * 2024-01-09 2024-02-09 广东泰一高新技术发展有限公司 Detail enhancement method for high-resolution remote sensing image

Similar Documents

Publication Publication Date Title
CN111583123A (en) Wavelet transform-based image enhancement algorithm for fusing high-frequency and low-frequency information
CN104574293B (en) Multiple dimensioned Retinex image sharpenings algorithm based on bounded computing
Wang et al. Fusion-based underwater image enhancement by wavelet decomposition
CN111210395B (en) Retinex underwater image enhancement method based on gray value mapping
CN108961172B (en) Gamma correction-based image contrast enhancement method
CN110232668B (en) Multi-scale image enhancement method
CN113837974B (en) NSST domain power equipment infrared image enhancement method based on improved BEEPS filtering algorithm
CN107203980B (en) Underwater target detection image enhancement method of self-adaptive multi-scale dark channel prior
CN114331873A (en) Non-uniform illumination color image correction method based on region division
CN114092353A (en) Infrared image enhancement method based on weighted guided filtering
CN107451986B (en) Single infrared image enhancement method based on fusion technology
CN116188339A (en) Retinex and image fusion-based scotopic vision image enhancement method
CN114418906A (en) Image contrast enhancement method and system
CN109064413B (en) Image contrast enhancement method and image acquisition medical equipment adopting same
WO2020107308A1 (en) Low-light-level image rapid enhancement method and apparatus based on retinex
CN113344810A (en) Image enhancement method based on dynamic data distribution
CN110992287B (en) Method for clarifying non-uniform illumination video
CN117391987A (en) Dim light image processing method based on multi-stage joint enhancement mechanism
CN110706180B (en) Method, system, equipment and medium for improving visual quality of extremely dark image
CN114998173B (en) Space environment high dynamic range imaging method based on local area brightness adjustment
CN114359083B (en) High-dynamic thermal infrared image self-adaptive preprocessing method for interference environment
CN113269681B (en) Underwater real-time image enhancement method based on multi-algorithm fusion
CN114331896A (en) Image enhancement method and system based on image decomposition and spectral transformation
CN115018717A (en) Improved Retinex-Net low-illumination and dark vision image enhancement method
Raju et al. Modified self—Adaptive Plateau Histogram Equalization with mean threshold for brightness preserving and 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