CN111583123A - Wavelet transform-based image enhancement algorithm for fusing high-frequency and low-frequency information - Google Patents
Wavelet transform-based image enhancement algorithm for fusing high-frequency and low-frequency information Download PDFInfo
- Publication number
- CN111583123A CN111583123A CN201910118889.6A CN201910118889A CN111583123A CN 111583123 A CN111583123 A CN 111583123A CN 201910118889 A CN201910118889 A CN 201910118889A CN 111583123 A CN111583123 A CN 111583123A
- Authority
- CN
- China
- Prior art keywords
- image
- frequency
- low
- wavelet
- low frequency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000001914 filtration Methods 0.000 claims abstract description 20
- 230000009466 transformation Effects 0.000 claims abstract description 13
- 238000006243 chemical reaction Methods 0.000 claims abstract description 8
- 238000005286 illumination Methods 0.000 claims abstract description 3
- 230000004044 response Effects 0.000 claims abstract description 3
- 238000012545 processing Methods 0.000 claims description 24
- 238000005516 engineering process Methods 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 3
- 101100496169 Arabidopsis thaliana CLH1 gene Proteins 0.000 claims description 2
- 101100274572 Arabidopsis thaliana CLH2 gene Proteins 0.000 claims description 2
- 101100274575 Caenorhabditis elegans clh-3 gene Proteins 0.000 claims description 2
- 230000035945 sensitivity Effects 0.000 claims description 2
- 238000005452 bending Methods 0.000 claims 1
- 230000008602 contraction Effects 0.000 claims 1
- 239000003814 drug Substances 0.000 abstract 1
- 230000006870 function Effects 0.000 description 17
- 230000008569 process Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000013139 quantization Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an image enhancement algorithm based on wavelet transform and fusing high-frequency and low-frequency information, which is mainly used for solving the problem of uneven illumination in the fields of medicine, photography and security, and comprehensively utilizes an image enhancement method, and sequentially comprises the following steps: step S1, inputting the color picture into a computer and converting the color picture into a gray scale picture, performing 2-layer wavelet decomposition of two-dimensional signals on the gray scale picture, and converting the image from a spatial domain into a frequency domain; step S2, extracting low-frequency components of the image, and improving high-frequency response in the low-frequency components by adopting homomorphic filtering; step S3, converting the filtered low-frequency image into a space domain to perform gray scale conversion to enhance the contrast and brightness of the image; and step S4, reconstructing an image according to the enhanced low-frequency component and high-frequency component coefficients, and carrying out threshold denoising on the reconstructed image based on wavelet transformation to finally obtain the enhanced image. By utilizing the technical scheme of the invention, the low-frequency information of the image, namely the overall brightness of the image, is effectively enhanced, and simultaneously, the noise interference in the high-frequency information is inhibited.
Description
Technical Field
The invention designs an image enhancement algorithm based on wavelet transformation and fusing high-frequency and low-frequency information, in particular to an image enhancement algorithm based on wavelet transformation and fusing threshold denoising, homomorphic filtering and gray level transformation.
Background
In the field of digital image processing, image enhancement technology is an important means for improving the visual effect of an image for a specific scene. Image enhancement can be based on the specific characteristics of the image and the problem of influencing the visual perception, and measures aiming at enhancing certain characteristics and quality of the image are taken aiming at specific application purposes. The problems mainly solved by image enhancement include: 1. the contrast ratio of the whole image and the local image is improved; 2. the image is enhanced, and noise interference is avoided; 3. enhancing the visual effect of the graphics. Since the image quality is comprehensively affected by various factors, no general algorithm exists at present.
Traditional image enhancement algorithms are mainly divided into two main categories: frequency domain enhancement and spatial domain enhancement. The image enhancement technology based on the airspace directly processes the image pixels and changes the distribution and the change rule of the gray value of the image, thereby realizing the image enhancement of the gray value level of the pixels. The image enhancement technology based on the frequency domain adopts reversible image transformation, converts an image defined in an original space into the frequency domain, enhances the image in the frequency domain space and then converts the image into the original space.
With the wide application of image enhancement technology in different application fields such as medical field, security field and photography field, researchers have proposed many different image enhancement algorithms, wherein the most widely applied algorithms mainly include wavelet transform algorithm, histogram equalization algorithm, partial differential equation algorithm, Retinex algorithm and the like. The method cannot simultaneously optimize evaluation indexes, so that the most suitable image enhancement algorithm needs to be selected according to specific requirements.
Disclosure of Invention
The invention aims to realize the suppression of high-frequency noise while enhancing low-frequency image information by adopting homomorphic filtering and gray level transformation algorithms based on a wavelet transformation technology, thereby obtaining better visual effect.
In order to achieve the above technical problem, the present invention can be realized by the following research schemes:
the invention discloses an image enhancement algorithm fusing high-frequency and low-frequency information, which sequentially comprises the following steps:
step S1, inputting the color picture into a computer and converting the color picture into a gray scale picture, performing 2-layer wavelet decomposition of two-dimensional signals on the gray scale picture, and converting the image from a spatial domain into a frequency domain;
step S2, extracting low-frequency components of the image, and improving high-frequency response in the low-frequency components by adopting homomorphic filtering;
step S3, converting the filtered low-frequency image into a space domain to perform gray scale conversion to enhance the contrast and brightness of the image;
and step S4, reconstructing an image according to the enhanced low-frequency component and high-frequency component coefficients, and carrying out threshold denoising on the reconstructed image based on wavelet transformation to finally obtain the enhanced image.
In the image enhancement method, the image is transformed from a spatial domain into a frequency domain by performing wavelet transform on the image, then the low-frequency component of the image is extracted, and the original image is wavelet decomposed into a low-frequency signal CL1 and three high-frequency signals CH1, CH2 and CH3 in actual processing, and then a signal CLL with relatively low frequency and three signals CLH1, CLH2 and CLH3 with relatively high frequency are decomposed from the low-frequency component. Wavelet decomposition is performed on the image using the wavedec2 function in the MATLAB wavelet toolkit, calling the format [ c, s ] ═ wavedec2(X, N, 'sym 4'). Where X denotes the original image signal, N denotes the N-level decomposition of the signal, sym4 is a mother function for wavelet transform, c is the decomposition coefficient of each level, and s is the decomposition coefficient length, i.e., magnitude, of each level.
In the image enhancement method, a homomorphic filter function is constructed through the following formula, homomorphic filtering is carried out on low-frequency components after wavelet decomposition of the image, and reflected light components of the image are improved, so that high-frequency components such as brightness, detail, edge information and the like of the image are improved, and the quality of the image is improved:
f(x,y)＝i(x,y)r(x,y)；
z(x,y)＝lni(x,y)+lnr(x,y)；
F(u,v)＝I(u,v)+R(u,v)；
S(u,v)＝H(u,v)F(u,v)＝H(u,v)I(u,v)+H(u,v)R(u,v)；
g(x,y)＝es(x,y)；
wherein the homomorphic filter function is H (u,v)，rHrepresents the high frequency gain, rLRepresenting the low frequency gain, D (u, v) represents the point (u, v) to the filter center (u, v)0,v0) C is a constant for controlling the sharpening sensitivity of the filter function, c ∈ [0,1]M, n are dynamic parameters, D0The cut-off frequency is indicated. The function of the image is F (x, y) represented by the product of the incident component I (x, y) and the reflected component R (x, y), z (x, y) is the logarithm of both sides of F (x, y), F (u, v) is the frequency domain expression of the image obtained by performing fast fourier transform on the image function z (x, y), I (u, v) is the fourier transform of lni (x, y), and R (u, v) is the fourier transform of lnr (x, y). S (u, v) is to be processed with F (u, v) homomorphic filtering, g (x, y) is to be processed with inverse Fourier transform (FFT)-1) And (4) taking logarithm of S (x, y) after returning to the space domain to obtain a final filtered image, and programming a homomorphic filtering transfer function H (u, v) by MATLAB in actual processing to realize the step.
In the image enhancement method, the low-frequency image which is converted into a space domain after filtering is subjected to nonlinear gray scale conversion through the following formula, so that the contrast and the brightness of the image are enhanced:
S＝crγ；
where the scale factor is a constant c representing the degree of curvature of the curve and r is the image pixel. When the gamma value is equal to 1, linear gray scale conversion is carried out, and when the gamma value is greater than 1, the stretching amplitude to the low-brightness area is greater than the moving amplitude to the high-brightness area, so that the method can be used for processing and enhancing the image after overexposure; the opposite is true when the gamma value is less than 1, which can be used to process images at low illumination levels. In the actual processing, the method is realized by calling an Imadjust function in an MATLAB tool box, wherein the calling format is b ═ Imadjust (a, [ ], [ ], gamma), wherein a is an image to be processed, [ ] is a gray scale range needing processing, b is the processed image, and the parameter gamma specifies the shape of a curve.
In the image enhancement method of the present invention, the image reconstructed according to the enhanced low frequency component and high frequency component coefficient is subjected to threshold denoising processing on the high frequency component by the following method to obtain an enhanced image:
selecting a proper threshold value by adopting VisuShrink, and adopting a global unified threshold value
Where σ is the standard deviation of the noise signal and N is the length of the signal. Coefficients above the threshold are processed using a shrinkage coefficient method, also known as soft thresholding. In the actual processing, the method is realized by calling a wdencmp function in an MATLAB toolbox, wherein the calling format is XC ═ wdencmp (' gbl ', im4, ' sym4', N, THR, SORH, KEEPAPP), wherein XC is a denoised signal, gbl (abbreviation of global) indicates that each layer is processed by using the same threshold, im4 is an image to be processed, sym4' is a used wavelet function, N is selected to be 3 to indicate the layer number of wavelet decomposition, THR is selected to be 3 to be a threshold vector, SORH is selected to be's ', a soft threshold is selected, and when a parameter KEEPAPP is 1, the low-frequency coefficient is not subjected to threshold quantization processing.
Compared with the traditional method, the algorithm of the invention has the advantages that:
by comprehensively utilizing the image enhancement method for fusing high-frequency and low-frequency information, the low-frequency information of the image, namely the overall brightness of the image, is effectively enhanced, and meanwhile, the noise interference in the high-frequency information is inhibited.
Drawings
FIG. 1 is a diagram of an input original image and its histogram of gray scale, and an image and its histogram of gray scale that has undergone homomorphic filtering and gray scale transformation based on wavelet transformation;
FIG. 2 is a low frequency coefficient reconstructed image and its grayscale histogram and a homomorphically filtered image of low frequency components and its grayscale histogram;
FIG. 3 is a spectral image before homomorphic filtering and a spectral image after filtering;
FIG. 4 is a gray scale transformed image of a low frequency component filtered image and a gray scale histogram thereof;
FIG. 5 is an image of an enhanced image after threshold denoising and its grayscale histogram;
fig. 6 is a general flowchart of the algorithm.
Detailed Description
The invention is described in further detail below with reference to the following figures and detailed description:
the simulation verification experiment of the invention is carried out based on an MATLAB software platform, so the following operation is realized based on MATLAB software programming.
As shown in fig. 6, the image enhancement algorithm based on wavelet transform and fusing high and low frequency information specifically includes the following steps:
step S1, load the color image into MATLAB and convert it to a grayscale image. The method comprises the steps of performing 2-layer wavelet decomposition on an image to obtain low-frequency components and high-frequency components of the image, performing wavelet decomposition on the image by adopting a wavedec2 function in an MATLAB wavelet toolbox, and calling a wavelet 2(X, N, 'sym 4') with the format of [ c, s ] ═ wavedec2, wherein X represents an original image signal, N represents N-layer decomposition on the signal, sym4 is a mother function for performing wavelet transformation, c is decomposition coefficients of each layer, and s is the length, namely the size, of each decomposition coefficient.
And step S2, extracting low-frequency components of the image, carrying out homomorphic filtering on the low-frequency components, and writing a homomorphic filtering transfer function H (u, v) by MATLAB in actual processing to realize the step.
And step S3, image reconstruction is carried out according to the filtered low-frequency component coefficient, the image is converted from a frequency domain to a space domain, nonlinear gray scale conversion enhancement is carried out on the image, the method is realized by calling Imadjust function in an MATLAB tool box in actual processing, the calling format is b ═ Imadjust (a, [ ], [ ], gamma), wherein a is the image to be processed, [ ] is the gray scale range needing processing, b is the processed image, the parameter gamma specifies the shape of a curve, the image after gray scale conversion is converted to the frequency domain to extract the low-frequency coefficient of the image, and the low-frequency component of the image in the second step is replaced.
Step S4, reconstructing an image according to the obtained low-frequency component and high-frequency component, performing soft threshold denoising based on wavelet transformation on the reconstructed image, and in actual processing, calling wdencmp functions in an MATLAB toolbox to realize the soft threshold denoising, wherein the calling format is XC ═ wdencmp (' gbl ', im4, ' sym4', N, THR, SORH, KEEPAPP), the denoised signals of XC and gbl (abbreviation of global) indicate that each layer adopts the same threshold to process, im4 indicates an image to be processed, sym4' is the used wavelet function, N selects 3 to indicate the number of layers of wavelet decomposition, THR selects 3 to be a threshold vector, SORH takes ' S ' to indicate that a soft threshold is selected, and when the value of a parameter KEEPAPP is 1, the low-frequency coefficient is not subjected to threshold quantization processing, and finally obtaining the final enhanced image.
Claims (5)
1. An image enhancement algorithm based on wavelet transform and fusing high and low frequency information mainly comprises the technologies of wavelet transform, homomorphic filtering, gray level transform, threshold denoising and the like, and is characterized in that the image high and low frequency information is processed, and the method comprises the following steps:
step S1, firstly, inputting the color picture into a computer and converting the color picture into a gray scale image, and performing 2-layer wavelet decomposition of two-dimensional signals on the gray scale image;
step S2, extracting low-frequency components of the image, and improving high-frequency response in the low-frequency components by adopting homomorphic filtering;
step S3, converting the filtered low-frequency image into a space domain to perform gray scale conversion to enhance the contrast and brightness of the image;
and step S4, reconstructing an image according to the enhanced low-frequency component and high-frequency component coefficients, and finally performing threshold denoising on the reconstructed image based on wavelet transformation to obtain an enhanced image.
2. The wavelet transform-based image enhancement algorithm fusing high and low frequency information according to claim 1, wherein said step S1 is performed by performing wavelet transform on the image, converting the image from spatial domain to frequency domain, then extracting low frequency components of the image, performing wavelet decomposition on the original image in actual processing into a low frequency signal CL1 and three high frequency signals CH1, CH2, CH3, and then performing wavelet decomposition on the image from the low frequency component into a relatively low frequency signal CLL and three relatively high frequency signals CLH1, CLH2, CLH3, performing wavelet decomposition on the image by using wavedec2 function in matwavelet toolbox, calling the format [ c, S ] ' wavedec2(X, N, ' sym4 '), wherein X represents the original image signal, N represents performing N-layer decomposition on the signal, sym4 is a mother function for performing wavelet transform, c is decomposition coefficients for each layer, and S is decomposition coefficient length for each layer, i.e. the size.
3. The wavelet transform-based image enhancement algorithm fusing high and low frequency information according to claim 1, wherein in step S2, a homomorphic filter function is constructed through the following formula, so as to implement homomorphic filtering on the low frequency component after wavelet decomposition of the image, and enhance the reflected light component of the image, thereby enhancing the high frequency components such as brightness, detail and edge information of the image, and improving the quality of the image:
f(x,y)＝i(x,y)r(x,y)；
z(x,y)＝lni(x,y)+lnr(x,y)；
F(u,v)＝I(u,v)+R(u,v)；
S(u,v)＝H(u,v)F(u,v)＝H(u,v)I(u,v)+H(u,v)R(u,v)；
g(x,y)＝es(x,y)；
wherein the homomorphic filter function is H (u, v), rHRepresents the high frequency gain, rLRepresenting the low frequency gain, D (u, v) represents the point (u, v) to the filter center (u, v)0,v0) C is a constant for controlling the sharpening sensitivity of the filter function, c ∈ [0,1]M, n are dynamic parameters, D0The cutoff frequency is represented, the function of the image is F (x, y) represented by the product of the incident component I (x, y) and the reflected component R (x, y), z (x, y) is the logarithm of both sides of F (x, y), F (u, v) is the frequency domain expression of the image obtained by performing the fast fourier transform on the image function z (x, y), I (u, v) is the fourier transform of lni (x, y), R (u, v) is the fourier transform of lnr (x, y), S (u, v) is the homomorphic filtering processing on F (u, v), g (x, y) is the homomorphic filtering processing on F (u, v), and g (x, y) is the product of the inverse fourier transform (FFT) on g (x, y)-1) And (4) taking logarithm of S (x, y) after returning to the space domain to obtain a final filtered image, and programming a homomorphic filtering transfer function H (u, v) by MATLAB in actual processing to realize the step.
4. The wavelet transform-based image enhancement algorithm fusing high and low frequency information according to claim 1, wherein in step S3, the low frequency image transformed to the spatial domain after filtering is subjected to the non-linear gray scale transform by the following formula to enhance the image contrast and brightness:
S＝crγ；
the scale factor is a constant c which represents the bending degree of the curve, r is an image pixel, linear gray scale conversion is performed when the gamma value is equal to 1, and the stretching amplitude to the low-brightness area is larger than the moving amplitude to the high-brightness area when the gamma value is larger than 1, so that the method can be used for processing and enhancing the overexposed image; when the gamma value is less than 1, the opposite can be used for processing the image under the enhanced low illumination, and the processing is realized by calling an Imadjust function in an MATLAB tool box in an actual processing mode, wherein the calling format is b ═ Imadjust (a, [ ], [ ], gamma), wherein a is the image to be processed, [ ] is the gray scale range needing to be processed, b is the processed image, and the parameter gamma specifies the shape of the curve.
5. The wavelet transform-based image enhancement algorithm fusing high and low frequency information as claimed in claim 1, wherein said step S4 is implemented by performing threshold denoising processing on the high frequency component of the image reconstructed from the enhanced low frequency component and the high frequency component coefficient by the following method to obtain the enhanced image:
selecting a proper threshold value by adopting VisuShrink, and adopting a global unified threshold value
Where σ is the standard deviation of the noise signal, N is the length of the signal, coefficients above a threshold are processed by a contraction coefficient method, also called soft thresholding, which is implemented in the actual processing by calling wdencmp function in MATLAB toolbox, with the format XC ═ wdencmp ('gbl', im4, 'sym4', N, THR, SORH, keepap), where XC denoised signal, gbl (abbreviation for global) indicates that each layer is processed with the same threshold, im4 indicates the image to be processed, 'sym4' is the wavelet function used, N selects 3, indicates the number of layers of the wavelet decomposition, THR selects 3 as the threshold vector, SORH takes's', indicates that the soft threshold is selected, and when the parameter keeppap takes a value of 1, indicates that the low frequency coefficient is not thresholded.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910118889.6A CN111583123A (en) | 2019-02-17 | 2019-02-17 | Wavelet transform-based image enhancement algorithm for fusing high-frequency and low-frequency information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910118889.6A CN111583123A (en) | 2019-02-17 | 2019-02-17 | Wavelet transform-based image enhancement algorithm for fusing high-frequency and low-frequency information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111583123A true CN111583123A (en) | 2020-08-25 |
Family
ID=72122498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910118889.6A Pending CN111583123A (en) | 2019-02-17 | 2019-02-17 | Wavelet transform-based image enhancement algorithm for fusing high-frequency and low-frequency information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111583123A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112244862A (en) * | 2020-10-14 | 2021-01-22 | 哈尔滨理工大学 | Electrocardiosignal denoising algorithm based on RFDA wavelet threshold |
| CN112348771A (en) * | 2020-09-25 | 2021-02-09 | 深圳市运泰利自动化设备有限公司 | Imaging consistency evaluation method based on wavelet transformation |
| CN112434880A (en) * | 2020-12-10 | 2021-03-02 | 清研灵智信息咨询(北京)有限公司 | Patrol route planning and patrol personnel management system based on deep learning |
| CN112488961A (en) * | 2020-12-16 | 2021-03-12 | 四川长虹电器股份有限公司 | T parameter homomorphic filtering method based on logarithmic equation |
| CN112634687A (en) * | 2020-12-30 | 2021-04-09 | 重庆医科大学 | Digital education technology teaching information control method and system |
| CN112884689A (en) * | 2021-02-25 | 2021-06-01 | 景德镇陶瓷大学 | Highlight removing method for image on strong reflection surface |
| CN113015262A (en) * | 2021-02-25 | 2021-06-22 | 上海吉盛网络技术有限公司 | All-digital elevator multi-party call device |
| CN113160096A (en) * | 2021-05-27 | 2021-07-23 | 山东中医药大学 | Low-light image enhancement method based on retina model |
| CN113256532A (en) * | 2021-06-13 | 2021-08-13 | 石家庄职业技术学院 | Low-contrast character image enhancement method |
| CN113379640A (en) * | 2021-06-25 | 2021-09-10 | 哈尔滨工业大学 | Multistage filtering image denoising method fusing edge information |
| CN113656462A (en) * | 2021-08-18 | 2021-11-16 | 北京奥康达体育产业股份有限公司 | Wisdom sports park data analysis system based on thing networking |
| CN113807194A (en) * | 2021-08-24 | 2021-12-17 | 哈尔滨工程大学 | Enhanced power transmission line fault image identification method |
| CN114972074A (en) * | 2022-04-27 | 2022-08-30 | 广东鉴面智能科技有限公司 | Night vision image analysis system based on low-light-level environment |
| CN115294118A (en) * | 2022-10-08 | 2022-11-04 | 南通先端精密机械有限公司 | Marine metal plate welding defect identification method |
| WO2023005069A1 (en) * | 2021-07-27 | 2023-02-02 | 深圳市赛禾医疗技术有限公司 | Ultrasonic image processing method and apparatus, and electronic device |
| CN116894951A (en) * | 2023-09-11 | 2023-10-17 | 济宁市质量计量检验检测研究院(济宁半导体及显示产品质量监督检验中心、济宁市纤维质量监测中心) | Jewelry online monitoring method based on image processing |
| CN117152182A (en) * | 2023-10-31 | 2023-12-01 | 深圳市巨龙创视科技有限公司 | Ultralow-illumination network camera image processing method and device and electronic equipment |
| CN118097760A (en) * | 2024-04-28 | 2024-05-28 | 深圳市瑜威电子科技有限公司 | Face recognition control method, system, equipment and storage medium |
| CN118138902A (en) * | 2024-04-30 | 2024-06-04 | 华东交通大学 | Imaging method and system for removing specular reflection based on polarization characteristic and light field imaging |
-
2019
- 2019-02-17 CN CN201910118889.6A patent/CN111583123A/en active Pending
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112348771B (en) * | 2020-09-25 | 2022-04-15 | 深圳市运泰利自动化设备有限公司 | Imaging consistency evaluation method based on wavelet transformation |
| CN112348771A (en) * | 2020-09-25 | 2021-02-09 | 深圳市运泰利自动化设备有限公司 | Imaging consistency evaluation method based on wavelet transformation |
| CN112244862B (en) * | 2020-10-14 | 2024-05-14 | 哈尔滨理工大学 | Electrocardiogram signal denoising algorithm based on RFDA wavelet threshold |
| CN112244862A (en) * | 2020-10-14 | 2021-01-22 | 哈尔滨理工大学 | Electrocardiosignal denoising algorithm based on RFDA wavelet threshold |
| CN112434880A (en) * | 2020-12-10 | 2021-03-02 | 清研灵智信息咨询(北京)有限公司 | Patrol route planning and patrol personnel management system based on deep learning |
| CN112488961A (en) * | 2020-12-16 | 2021-03-12 | 四川长虹电器股份有限公司 | T parameter homomorphic filtering method based on logarithmic equation |
| CN112634687A (en) * | 2020-12-30 | 2021-04-09 | 重庆医科大学 | Digital education technology teaching information control method and system |
| CN113015262A (en) * | 2021-02-25 | 2021-06-22 | 上海吉盛网络技术有限公司 | All-digital elevator multi-party call device |
| CN113015262B (en) * | 2021-02-25 | 2023-04-28 | 上海吉盛网络技术有限公司 | All-digital elevator multiparty call device |
| CN112884689A (en) * | 2021-02-25 | 2021-06-01 | 景德镇陶瓷大学 | Highlight removing method for image on strong reflection surface |
| CN112884689B (en) * | 2021-02-25 | 2023-11-17 | 景德镇陶瓷大学 | Method for removing high light of strong reflection surface image |
| CN113160096A (en) * | 2021-05-27 | 2021-07-23 | 山东中医药大学 | Low-light image enhancement method based on retina model |
| CN113160096B (en) * | 2021-05-27 | 2023-12-08 | 山东中医药大学 | Low-light image enhancement method based on retina model |
| CN113256532A (en) * | 2021-06-13 | 2021-08-13 | 石家庄职业技术学院 | Low-contrast character image enhancement method |
| CN113379640A (en) * | 2021-06-25 | 2021-09-10 | 哈尔滨工业大学 | Multistage filtering image denoising method fusing edge information |
| WO2023005069A1 (en) * | 2021-07-27 | 2023-02-02 | 深圳市赛禾医疗技术有限公司 | Ultrasonic image processing method and apparatus, and electronic device |
| CN113656462A (en) * | 2021-08-18 | 2021-11-16 | 北京奥康达体育产业股份有限公司 | Wisdom sports park data analysis system based on thing networking |
| CN113807194A (en) * | 2021-08-24 | 2021-12-17 | 哈尔滨工程大学 | Enhanced power transmission line fault image identification method |
| CN113807194B (en) * | 2021-08-24 | 2023-10-10 | 哈尔滨工程大学 | Enhanced power transmission line fault image recognition method |
| CN114972074A (en) * | 2022-04-27 | 2022-08-30 | 广东鉴面智能科技有限公司 | Night vision image analysis system based on low-light-level environment |
| CN115294118A (en) * | 2022-10-08 | 2022-11-04 | 南通先端精密机械有限公司 | Marine metal plate welding defect identification method |
| CN116894951A (en) * | 2023-09-11 | 2023-10-17 | 济宁市质量计量检验检测研究院(济宁半导体及显示产品质量监督检验中心、济宁市纤维质量监测中心) | Jewelry online monitoring method based on image processing |
| CN116894951B (en) * | 2023-09-11 | 2023-12-08 | 济宁市质量计量检验检测研究院(济宁半导体及显示产品质量监督检验中心、济宁市纤维质量监测中心) | Jewelry online monitoring method based on image processing |
| CN117152182B (en) * | 2023-10-31 | 2024-02-20 | 深圳市巨龙创视科技有限公司 | Ultralow-illumination network camera image processing method and device and electronic equipment |
| CN117152182A (en) * | 2023-10-31 | 2023-12-01 | 深圳市巨龙创视科技有限公司 | Ultralow-illumination network camera image processing method and device and electronic equipment |
| CN118097760A (en) * | 2024-04-28 | 2024-05-28 | 深圳市瑜威电子科技有限公司 | Face recognition control method, system, equipment and storage medium |
| CN118138902A (en) * | 2024-04-30 | 2024-06-04 | 华东交通大学 | Imaging method and system for removing specular reflection based on polarization characteristic and light field imaging |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111583123A (en) | Wavelet transform-based image enhancement algorithm for fusing high-frequency and low-frequency information | |
| Liu et al. | Efficient single image dehazing and denoising: An efficient multi-scale correlated wavelet approach | |
| CN108090886B (en) | High dynamic range infrared image display and detail enhancement method | |
| CN107798661B (en) | Self-adaptive image enhancement method | |
| CN103034986A (en) | Night vision image enhancement method based on exposure fusion | |
| WO2007116543A1 (en) | Image processing method | |
| CN104574293A (en) | Multiscale Retinex image sharpening algorithm based on bounded operation | |
| CN107784638A (en) | A kind of Dongba ancient books image enchancing method of optimization | |
| CN110246088B (en) | Image brightness noise reduction method based on wavelet transformation and image noise reduction system thereof | |
| Mu et al. | Low and non-uniform illumination color image enhancement using weighted guided image filtering | |
| Dharejo et al. | A deep hybrid neural network for single image dehazing via wavelet transform | |
| Gopinathan et al. | Wavelet and FFT Based Image Denoising Using Non-Linear Filters. | |
| CN117252773A (en) | Image enhancement method and system based on self-adaptive color correction and guided filtering | |
| CN111815550A (en) | Infrared and visible light image fusion method based on gray level co-occurrence matrix | |
| CN107451986B (en) | Single infrared image enhancement method based on fusion technology | |
| CN114359083B (en) | High-dynamic thermal infrared image self-adaptive preprocessing method for interference environment | |
| CN104978720A (en) | Video image raindrop removal method and apparatus | |
| CN104616252A (en) | NSCT (Non Subsampled Contourlet Transform) and PCNN (Pulse Coupled Neural Network) based digital image enhancing method | |
| CN112822343B (en) | Night video oriented sharpening method and storage medium | |
| Kadhim et al. | Enhancement of Microscopy Images by Using a Hybrid Technique Based on Adaptive Histogram Equalisation and Fuzzy Logic. | |
| CN110992287B (en) | Method for clarifying non-uniform illumination video | |
| CN106803236A (en) | Asymmetric correction method based on fuzzy field singular value decomposition | |
| CN110175959B (en) | Typhoon cloud picture enhancement method | |
| CN115082296B (en) | Image generation method based on wavelet domain image generation frame | |
| CN116630198A (en) | Multi-scale fusion underwater image enhancement method combining self-adaptive gamma correction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200825 |
|
| WD01 | Invention patent application deemed withdrawn after publication |