CN106296600B - A kind of contrast enhancement process decomposed based on wavelet image - Google Patents
A kind of contrast enhancement process decomposed based on wavelet image Download PDFInfo
- Publication number
- CN106296600B CN106296600B CN201610625542.7A CN201610625542A CN106296600B CN 106296600 B CN106296600 B CN 106296600B CN 201610625542 A CN201610625542 A CN 201610625542A CN 106296600 B CN106296600 B CN 106296600B
- Authority
- CN
- China
- Prior art keywords
- image
- wavelet
- frequency information
- information
- low
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000002708 enhancing effect Effects 0.000 claims abstract description 27
- 230000009466 transformation Effects 0.000 claims abstract description 24
- 238000000926 separation method Methods 0.000 claims abstract description 6
- 230000003287 optical effect Effects 0.000 claims description 10
- 230000010365 information processing Effects 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000003321 amplification Effects 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000005315 distribution function Methods 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 2
- 238000005242 forging Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 5
- 238000005259 measurement Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 239000004744 fabric Substances 0.000 description 2
- 239000004615 ingredient Substances 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000003746 surface roughness Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- 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
A kind of contrast enhancement process decomposed based on wavelet image of the present invention belongs to image procossing and Computer Vision Detection field, is related to a kind of contrast enhancement process decomposed based on wavelet image.This method carries out high and low frequency information separation by wavelet transformation to the image of striation brightness irregularities first, then noise remove is carried out by wavelet transformation multi-scale thresholds denoising method to high frequency section information, and for low frequency part use of information limitation contrast self-adapting histogram equilibrium method degree of comparing enhancing, finally enhanced image is obtained using inverse wavelet transform.This method is respectively processed the high and low frequency information of image, largely eliminates noise, enhance the intensity of signal, effectively improve the consistent uniformity of striation using wavelet transformation and limitation contrast self-adapting histogram equilibrium method.
Description
Technical field
The invention belongs to image procossing and Computer Vision Detection field, it is related to a kind of decomposing based on wavelet image
Contrast enhancement process.
Background technique
Machine vision technique is a kind of important method of forging's block dimension measurement at present, and is assisted by projecting on forging surface
Laser striation simultaneously carries out accurate extract so that the mode for realizing that size accurately measures is widely adopted.However, due to forging shape
Different, the factors such as site environment interference cause the optical strip image directly acquired local luminance unevenness easily occur, striation are caused to mention
Take error to increase, in addition can not complete extraction, seriously affect the precision of final forging's block dimension measurement.Therefore, striation spy is being carried out
Sign carries out certain processing to image before extracting, enhance the contrast of laser optical strip image, and improving striation characteristic has very
Important meaning.The medium human hair of Fu Zhi bright " a kind of method for enhancing picture contrast ", patent publication No.: CN 104700365A,
Critical visible bias property of the invention based on human eye vision designs critical visual deviation enhancing function and gradient companding function,
Enhancing image is rebuild from enhanced gradient fields.This method is extracted for improving visual effect function well, but for computer
The precision of characteristics of image does not improve preferably." method for enhancing picture contrast " of Wen Yiqian et al. invention, patent publication No.:
CN105184754A, grayscale of the invention by calculating separately same row adjacent rows and with a line between the pixel of adjacent two column
Absolute value of the difference calculates separately the first, second grayscale value weight according to the absolute value, then passes through the first, second grayscale value weight
Accumulation calculating and normalized are carried out, it is final to obtain enhancing grayscale table, and then the grayscale value of each pixel is divided again
Match, improve the contrast of image, optimizes display effect.This method is cumbersome, and is equally only applicable to improve visual display effect
Fruit.
Summary of the invention
The technical problem to be solved by the present invention is to overcome the deficiencies of existing technologies, invent a kind of based on wavelet image
The contrast enhancement process of decomposition.Specifically refer to based on being denoised to image high-frequency information after wavelet decomposition, low-frequency information into
The image processing method of row contrast enhancing.Using small wave converting method and limitation contrast self-adapting histogram equilibrium method pair
Image high and low frequency information is handled respectively, realizes the enhancing of optical strip image contrast, is improved the consistent uniformity of striation, is improved image
Quality.
The technical solution adopted by the present invention is that a kind of contrast enhancement process decomposed based on wavelet image, feature
It is that this method carries out high and low frequency information separation by wavelet transformation to the image of striation brightness irregularities first, then to high frequency
Partial information carries out noise remove by wavelet transformation multi-scale thresholds denoising method, and low frequency part use of information is limited
The enhancing of contrast self-adapting histogram equilibrium method degree of comparing, finally obtains enhanced image using inverse wavelet transform；
Specific step is as follows for method:
Step 1: optical strip image high and low frequency information is separated using wavelet transformation
Image to be reinforced is read in using MATLAB, small echo is carried out to image using the dwt2 function in wavelet transformation tool box
Transformation；Wherein, Selection of Wavelet Basis Harr function, so that image information is decomposed into high frequency section and low frequency part, then to height
Frequency information is respectively processed, and high-frequency information is denoised, the enhancing of low-frequency information degree of comparing；
Step 2: high-frequency information processing
Pixel shared by striation information is less in laser optical strip image, and grey level distribution is sparse, and pixel shared by background is more, ash
It is densely distributed to spend grade, and includes a large amount of picture noise in image, in order to combine the reservation of signal section information and make an uproar
Sound ingredient effectively removes, and using wavelet transformation multi-scale thresholds Denoising Algorithm, determines the high-frequency information noise that different scale decomposes
Threshold value；Since this method needs to carry out signal enhancing to low-frequency information, hard-threshold denoising is selected, low frequency signal is not changed
Wavelet coefficient avoids enhancing subsequent low-frequency information contrast interfering；Treated high-frequency signal wavelet coefficient are as follows:
Wherein, w (m, n) is high-frequency signal wavelet coefficient after original image separation, and T is threshold value；
For different decomposition scale j, the threshold value T of high frequency coefficientjAre as follows:
Wherein, K is correction factor, LjFor the length of wavelet coefficient, σn 2For noise variance, σxFor subband wavelet coefficient standard
Difference；
Original image high-frequency signal wavelet coefficient can be modified by above formula, to realize image denoising.
Step 3: low-frequency information processing
Lead to asking for image detail information loss in order to avoid image is carried out gray level merging by conventional histogram equalization
Topic, using limitation contrast self-adapting histogram equilibrium method to each zonule on the basis of adaptive histogram equalization
Contrast clipping is all used, to effectively reduce the amplification of noise；In histogram equalization, mapping curve D and iterated integral
The proportional relationship of cloth function CDF:
Wherein, M is highest gray value, and N is number of pixels, and i is gray level, i ∈ [0,255].Again because of Cumulative Distribution Function
CDF is the integral of grey level histogram Hist, i.e.,
CDF (i)=∫ Hist (i) di (4)
By above formula it is found that the slope of limitation CDF is equivalent to the amplitude of limitation Hist；
Therefore, using limitation contrast self-adapting histogram equilibrium method need to the histogram counted in sub-block into
Row is cut, and makes its amplitude lower than some upper limit, and this part clipped value is evenly distributed in entire gray scale interval, to guarantee
The histogram gross area is constant, finally in order to avoid the blocky effect of image, the value of each pixel by sub-block around it mapping
Functional value carries out bilinear interpolation acquisition；
Step 4: inverse wavelet transform obtains enhancing image
Revised high and low frequency information is subjected to small echo contravariant using the idwt2 function in MATLAB wavelet transformation tool box
Get enhanced final image in return.The clarity distribution curve for detecting striation compares the consistent uniformity of striation, examines the party
Method is to the improvement degree for avoiding local overexposure or excessively dark problem.
The beneficial effects of the invention are as follows wavelet transformation and limitation contrast self-adapting histogram equilibrium method is utilized, to image
High and low frequency information be respectively processed, to largely eliminate noise, enhance the intensity of signal, be effectively improved
The consistent uniformity of striation lays a good foundation for subsequent accurate extraction optical losses.
Detailed description of the invention
Fig. 1 a) be the histogram counted in each sub-block of original image, Fig. 1 b) it is to carry out histogram according to certain threshold value
Histogram after cutting redistribution.
Fig. 2 is that contrast enhances front and back striation clarity change curve, curve before 1- enhances, curve after 2- enhancing.
Specific embodiment
Below with reference to technical solution and the attached drawing specific embodiment that the present invention will be described in detail.
Fig. 1 a) be the histogram counted in each sub-block of original image, Fig. 1 b) it is to carry out histogram according to certain threshold value
Histogram after cutting redistribution.The part that amplitude in original image is higher than given threshold is cut, and is equally evenly distributed to figure
As in entire gray scale interval, guaranteeing that the gross area is constant.Herein due to the addition of cutting part, image distribution can be made integrally to move up one
Fraction causes top beyond threshold value at original cutting, as shown in above figure (b).But due to influencing very little, it can ignore
Disregard.
In forging measurement due to object under test surface between video camera at a distance from, determinand surface roughness and surface
Curvature difference and noise jamming etc. lead to, further influence spy uneven in same projection surface's laser striation brightness of image
The problem of sign extraction and measurement accuracy.Especially when laser striation is incident upon forged shaft surface, it may appear that radial in forging
Laser striation middle is brighter, and in two sides then than darker situation, it is biggish it is bright it is dark it is poor lead to not to obtain feature it is complete
Laser optical strip image.This method is using wavelet transformation and limitation contrast self-adapting histogram equilibrium method, to the height of image
Low-frequency information is respectively processed, to largely eliminate noise, while the intensity of signal is enhanced, first to light
The image of brightness irregularities carries out high and low frequency information separation by wavelet transformation, then passes through small echo change to high frequency section information
It changes multi-scale thresholds denoising method and carries out noise remove, and contrast self-adapting histogram is limited for low frequency part use of information
The enhancing of equalization methods degree of comparing, finally obtains enhanced image using inverse wavelet transform.Specific step is as follows:
Step 1: wavelet transformation separates optical strip image high and low frequency information
Image to be reinforced is read in using MATLAB, small echo is carried out to image using the dwt2 function in wavelet transformation tool box
It converts, wherein Selection of Wavelet Basis Harr function, so that image information is decomposed into high frequency section and low frequency part, then to low-and high-frequency
Information is respectively processed.High-frequency information is denoised, the enhancing of low-frequency information degree of comparing.
Step 2: high-frequency information processing
Pixel shared by striation information is less in laser optical strip image, and grey level distribution is sparse, and pixel shared by background is more, ash
It is densely distributed to spend grade, and includes a large amount of picture noise in image, in order to combine the reservation of signal section information and make an uproar
Sound ingredient effectively removes, and the present invention uses wavelet transformation multi-scale thresholds Denoising Algorithm, determines the high frequency letter that different scale decomposes
Cease noise threshold.Since this method needs to carry out signal enhancing to low-frequency information, hard-threshold denoising is selected, high frequency is not changed
The wavelet coefficient of signal avoids enhancing subsequent low-frequency information contrast interfering.Utilize wavedec2 function in MATLAB
Two layers of decomposition are carried out to image, obtain four 915 × 657 matrixes, wherein first matrix is image low-frequency information coefficient,
Excess-three matrix is respectively image in high-frequency information matrix horizontal, in vertical and diagonal direction.According to formula (2) to difference
Threshold value under scale is calculated, and the threshold value for acquiring three matrixes of high frequency section is respectively 1.3322,2.4614 and 1.7066, then
High-frequency signal wavelet coefficient is handled using formula (1), to realize image denoising.
Step 3: low-frequency information processing
Lead to asking for image detail information loss in order to avoid image is carried out gray level merging by conventional histogram equalization
Topic, the present invention is on the basis of adaptive histogram equalization using limitation contrast self-adapting histogram equilibrium method to each
Zonule all uses contrast clipping, to effectively reduce the amplification of noise.By formula (3), (4) it is found that limitation CDF's is oblique
Rate is equivalent to the amplitude of limitation Hist.
Average, median and the mode for calculating low-frequency information part matrix in image are respectively 36.7857,12 and
11.5, as the threshold value of processing, using histeq function in MATLAB, not according to the selection of the size of the coefficient of low-frequency information matrix
Same threshold value carries out histogram equalization, cuts to the amplitude of the histogram counted in sub-block, and this part is cut out
It cuts value to be evenly distributed in entire gray scale interval, to guarantee that the histogram gross area is constant, principle is as shown in Figure 1.Finally it is
The blocky effect of image is avoided, the value of each pixel carries out bilinear interpolation by the mapping function value of sub-block around it and obtains
?.
Step 4: inverse wavelet transform obtains enhancing image
Revised high and low frequency information is subjected to small echo contravariant using the idwt2 function in MATLAB wavelet transformation tool box
Get enhanced final image in return.The clarity distribution curve for detecting striation compares the consistent uniformity of striation, examines the party
Method is to the improvement degree for avoiding local overexposure or excessively dark problem.Fig. 2 is that contrast enhances front and back striation clarity change curve, can
To find out, 1 clarity difference of curve is very big before enhancing, and distribution is very scattered, and striation uniformity consistency is bad, striation articulation curve point
Cloth range is wider, and maxima and minima differs greatly, therefore will lead to the overexposure problem and light of striation clarity upper section
Clarity is difficult to coordinate compared with the excessively dark problem of lower part, and striation clarity upper section obtains after this method is handled before enhancing
Apparent inhibition is arrived, the part clarity that curve 2 is easy overexposure after enhancing significantly reduces, and distribution is more smooth, and striation is consistent
Uniformity is effectively improved, and the striation uniformity is obviously improved.
The present invention is using wavelet transformation and limitation contrast self-adapting histogram equilibrium method, to the high and low frequency information of image
It is respectively processed, largely eliminates noise, enhance the intensity of signal, effectively improve the consistent uniform of striation
Property.
Claims (1)
1. a kind of contrast enhancement process decomposed based on wavelet image, characterized in that this method is first to striation brightness
Non-uniform image carries out high and low frequency information separation by wavelet transformation, then passes through the more rulers of wavelet transformation to high frequency section information
It spends Threshold Denoising Method and carries out noise remove, and contrast self-adapting histogram equilibrium side is limited for low frequency part use of information
The enhancing of method degree of comparing, finally obtains enhanced image using inverse wavelet transform；Specific step is as follows for method:
Step 1: wavelet transformation separates optical strip image high and low frequency information
Image to be reinforced is read in using MATLAB, small echo change is carried out to image using the dwt2 function in wavelet transformation tool box
It changes, wherein Selection of Wavelet Basis Harr function, so that image information is decomposed into high frequency section and low frequency part, then low-and high-frequency is believed
Breath is respectively processed；High-frequency information is denoised, the enhancing of low-frequency information degree of comparing；
Step 2: high-frequency information processing
Using wavelet transformation multi-scale thresholds Denoising Algorithm, the high-frequency information noise threshold that different scale decomposes is determined；This method needs
Signal enhancing is carried out to low-frequency information, therefore selects hard-threshold denoising, do not changed the wavelet coefficient of low frequency signal, avoided to rear
Continuous low-frequency information contrast enhancing interferes；Treated high-frequency signal wavelet coefficient are as follows:
Wherein, w (m, n) is high-frequency signal wavelet coefficient after original image separation, and T is threshold value；
For different decomposition scale j, the threshold value T of high frequency coefficientjAre as follows:
Wherein, K is correction factor, LjFor the length of wavelet coefficient, σn 2For noise variance, σxIt is poor for subband wavelet coefficient standard；
Original image high-frequency signal wavelet coefficient is modified by above formula, to realize image denoising；
Step 3: low-frequency information processing
In order to avoid image is carried out the problem of gray level merging causes image detail information to be lost by conventional histogram equalization,
Each zonule is made using limitation contrast self-adapting histogram equilibrium method on the basis of adaptive histogram equalization
With contrast clipping, reduce the amplification of noise；In histogram equalization, mapping curve D and cumulative distribution function CDF at than
Example relationship:
Wherein, M is highest gray value, and N is number of pixels, and i is gray level, i ∈ [0,255]；Again because Cumulative Distribution Function CDF is
The integral of grey level histogram Hist, i.e.,
CDF (i)=∫ Hist (i) di (4)
By above formula it is found that the slope of limitation CDF is equivalent to the amplitude of limitation Hist；
Therefore, it needs to cut out the histogram counted in sub-block using limitation contrast self-adapting histogram equilibrium method
It cuts, makes its amplitude lower than some upper limit, and this part clipped value is evenly distributed in entire gray scale interval, to guarantee histogram
The figure gross area is constant；Finally in order to avoid the blocky effect of image, the value of each pixel by sub-block around it mapping function
Value carries out bilinear interpolation acquisition；
Step 4: inverse wavelet transform obtains enhancing image
Revised high and low frequency information progress inverse wavelet transform is obtained using the idwt2 function in MATLAB wavelet transformation tool box
To enhanced final image；The clarity distribution curve for detecting striation compares the consistent uniformity of striation, examines this method pair
Avoid the improvement degree of local overexposure or excessively dark problem.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610625542.7A CN106296600B (en) | 2016-08-01 | 2016-08-01 | A kind of contrast enhancement process decomposed based on wavelet image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610625542.7A CN106296600B (en) | 2016-08-01 | 2016-08-01 | A kind of contrast enhancement process decomposed based on wavelet image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106296600A CN106296600A (en) | 2017-01-04 |
| CN106296600B true CN106296600B (en) | 2018-12-21 |
Family
ID=57664143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610625542.7A Active CN106296600B (en) | 2016-08-01 | 2016-08-01 | A kind of contrast enhancement process decomposed based on wavelet image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106296600B (en) |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109427047B (en) | 2017-08-28 | 2021-01-26 | 京东方科技集团股份有限公司 | Image processing method and device |
| CN107729905A (en) * | 2017-10-19 | 2018-02-23 | 珠海格力电器股份有限公司 | Image information processing method and device |
| CN108492261A (en) * | 2018-02-07 | 2018-09-04 | 厦门美图之家科技有限公司 | A kind of image enchancing method and computing device |
| CN108550160B (en) * | 2018-04-03 | 2020-04-07 | 大连理工大学 | Non-uniform light bar characteristic region extraction method based on light intensity template |
| CN108961179B (en) * | 2018-06-19 | 2022-10-18 | 上海中和软件有限公司 | Medical image post-processing system and using method thereof |
| CN109584190B (en) * | 2018-10-23 | 2023-09-22 | 江苏理工学院 | Contrast image enhancement method based on wavelet transformation low-frequency histogram limitation |
| CN110136084A (en) * | 2019-05-16 | 2019-08-16 | 哈尔滨工业大学（深圳） | Automatic CLAHE image enchancing method, device, system and storage medium based on wavelet transform |
| CN110751618B (en) * | 2019-06-05 | 2022-12-30 | 浙江大华技术股份有限公司 | Floater detection method and device and electronic equipment |
| CN110365914B (en) * | 2019-07-24 | 2020-03-20 | 中国人民解放军国防科技大学 | Image dynamic range widening method and system |
| CN110517199B (en) * | 2019-08-26 | 2022-03-08 | 电子科技大学 | Image rain removing method convenient for intelligent vehicle driving |
| CN111028185B (en) * | 2019-12-06 | 2023-01-24 | Oppo广东移动通信有限公司 | Histogram equalization method, device, equipment and storage medium |
| CN111501543B (en) * | 2020-04-22 | 2022-01-04 | 河南省交通规划设计研究院股份有限公司 | Bridge surface crack detection device |
| CN112492312B (en) * | 2020-11-19 | 2022-11-08 | 平安普惠企业管理有限公司 | Image compression recovery method, device, equipment and medium based on wavelet transform |
| CN112434880B (en) * | 2020-12-10 | 2022-03-15 | 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 |
| CN112991196B (en) * | 2021-02-02 | 2022-08-02 | 武汉科技大学 | Frequency domain denoising method for rotary kiln flame image |
| CN113610717B (en) * | 2021-07-16 | 2024-01-19 | 江苏师范大学 | Enhancement method for ultraviolet fluorescence image of skin disease |
| CN114549353B (en) * | 2022-02-22 | 2022-09-02 | 中科微影(浙江)医疗科技有限公司 | Denoising method and system for nuclear magnetic resonance image |
| CN115564705B (en) * | 2022-07-08 | 2023-07-07 | 优层智能科技(上海)有限公司 | Burr detection precision enhancement method and system for precision standard component |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101430759A (en) * | 2008-12-04 | 2009-05-13 | 上海大学 | Optimized recognition pretreatment method for human face |
| US7840066B1 (en) * | 2005-11-15 | 2010-11-23 | University Of Tennessee Research Foundation | Method of enhancing a digital image by gray-level grouping |
| CN102332155A (en) * | 2011-10-19 | 2012-01-25 | 江苏技术师范学院 | Image enhancement method |
-
2016
- 2016-08-01 CN CN201610625542.7A patent/CN106296600B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7840066B1 (en) * | 2005-11-15 | 2010-11-23 | University Of Tennessee Research Foundation | Method of enhancing a digital image by gray-level grouping |
| CN101430759A (en) * | 2008-12-04 | 2009-05-13 | 上海大学 | Optimized recognition pretreatment method for human face |
| CN102332155A (en) * | 2011-10-19 | 2012-01-25 | 江苏技术师范学院 | Image enhancement method |
Non-Patent Citations (4)
| Title |
|---|
| Combination of contrast limited adaptive histogram equalisation and discrete wavelet transform for image enhancement;Huang Lidong 等;《IET Image Processing》;20150917;第9卷(第10期);908-915 * |
| 一种红外图像对比度增强的小波变换法;张长江 等;《红外与毫米波学报》;20040425;第23卷(第2期);119-124 * |
| 低对比度胸片中管线检测方法;徐文涛 等;《电子科技》;20151215;第28卷(第12期);84-87 * |
| 基于一种新阈值函数的小波阈值去噪方法研究;王京港 等;《数字技术与应用》;20120915;43-45 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106296600A (en) | 2017-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106296600B (en) | A kind of contrast enhancement process decomposed based on wavelet image | |
| US11127122B2 (en) | Image enhancement method and system | |
| Wang et al. | Simple low-light image enhancement based on Weber–Fechner law in logarithmic space | |
| Sun et al. | Fast single image haze removal via local atmospheric light veil estimation | |
| CN103578084A (en) | Color image enhancement method based on bright channel filtering | |
| WO2020124873A1 (en) | Image processing method | |
| CN104574293A (en) | Multiscale Retinex image sharpening algorithm based on bounded operation | |
| CN101639936A (en) | X-ray image enhancing method and system thereof | |
| CN116030058A (en) | Quality evaluation method for surface roughness of polishing pad | |
| CN107749049B (en) | Vein distribution display method and device | |
| CN108550145A (en) | A kind of SAR image method for evaluating quality and device | |
| CN105976342B (en) | A kind of adaptive gray level image Pseudo Col ored Image method | |
| Zhang et al. | Single image dehazing based on fast wavelet transform with weighted image fusion | |
| CN116503426B (en) | Ultrasonic image segmentation method based on image processing | |
| Wang et al. | Retinex algorithm on changing scales for haze removal with depth map | |
| CN114219774B (en) | Image quality evaluation method, device, terminal and computer readable storage medium | |
| Luo et al. | An effective underwater image enhancement method based on CLAHE-HF | |
| CN114359083B (en) | High-dynamic thermal infrared image self-adaptive preprocessing method for interference environment | |
| Zhou et al. | Human visual system based automatic underwater image enhancement in NSCT domain | |
| Chang et al. | An image enhancement algorithm based on Gaussian weighted bilateral filtering and retinex theory | |
| CN112070741B (en) | Rice chalkiness degree detecting system based on image salient region extracting method | |
| CN110852977B (en) | Image enhancement method for fusing edge gray level histogram and human eye visual perception characteristics | |
| CN112085683A (en) | Depth map reliability detection method in significance detection | |
| CN112560808A (en) | In-vivo vein identification method and device based on gray information | |
| Han et al. | Image enhancement based on spatial multi-scale homomorphic filtering and local entropy guided image filtering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |