CN112419300A - Underwater image quality evaluation method and system - Google Patents
Underwater image quality evaluation method and system Download PDFInfo
- Publication number
- CN112419300A CN112419300A CN202011411080.1A CN202011411080A CN112419300A CN 112419300 A CN112419300 A CN 112419300A CN 202011411080 A CN202011411080 A CN 202011411080A CN 112419300 A CN112419300 A CN 112419300A
- Authority
- CN
- China
- Prior art keywords
- image
- underwater
- quality
- underwater image
- estimating
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000013441 quality evaluation Methods 0.000 title claims description 13
- 238000013507 mapping Methods 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000009827 uniform distribution Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 238000003384 imaging method Methods 0.000 abstract description 11
- 238000012545 processing Methods 0.000 description 6
- 238000001303 quality assessment method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000019771 cognition Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000031700 light absorption Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- 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
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a system for evaluating the quality of an underwater image, wherein the method comprises the following steps: s1, extracting the brightness and chroma characteristics of the underwater image, and estimating the brightness and chroma of the input picture; s2, extracting the ambiguity characteristics of the underwater picture, and estimating the ambiguity degree of the input picture; s3, extracting the contrast characteristic of the underwater picture, and estimating the contrast of the input picture; and S4, learning a mapping model of the image characteristics extracted in the steps S1-S3 to the image quality on the training set by using a support vector regression method, and predicting the quality of the underwater image. The method does not need to refer to the original image, can obtain higher prediction performance at the same time, has high running speed, and meets the application requirement of underwater imaging.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a system for evaluating the quality of an underwater image.
Background
Underwater imaging plays an important role in underwater operations, marine exploration, cultural relic protection and the like. However, due to the complex underwater imaging environment, the absorption of light into water, and other factors, the underwater imaging quality is low, and the application requirements cannot be met, so that a special underwater image processing technology needs to be researched, the underwater imaging quality is improved, and the underwater imaging system can better serve important tasks such as underwater operation. The invention provides a quality evaluation method for underwater images, which can reliably judge the quality of underwater imaging, is used for monitoring the quality of underwater imaging in real time and improves the processing efficiency of the underwater images.
Mean Square Error (MSE) and peak to noise ratio (PSNR) are currently widely adopted quality evaluation criteria. In recent years, triggered by some classical psychological cognition paradigms, many researchers have proposed some cognition-based image quality evaluation methods. The structural similarity method (SSIM) proposed in the article "Image quality assessment from Image visibility to structural similarity", published by Wang, Z et al in IEEE Trans. Image Process, Vol.13, No. 4, pp.600 to 612, estimates the quality of an Image from its structural information. The Multi-scale structure similarity method (MS-SSIM) proposed by Wang, Z et al in the paper "Multi-scale structure similarity for image quality assessment" published by IEEE aid Conference on Signals, Systems and Computer, volume 2, pages 1398 to 1402, extends the SSIM method to multiple scales, achieving better prediction performance. Li, Q. et al, in the paper "Reduced-Reference Image Quality Assessment Using partition Normal Image reconstruction" published by IEEE Journal of Selected Topics in Signal Processing, volume 3, pages 2, 202 to 211, wavelet decomposition of images, and then Normalization Processing for each subband, extracting distribution parameters of coefficients as features to estimate the Quality of the images. Gao, x. et al, in the paper "Image Quality Assessment Based on Multiscale geometry Analysis" published in IEEE trans Image Process, volume 18, phase 7, page 1409 to page 1423, perform Multiscale decomposition on images, then weight the decomposition coefficients with a human eye contrast sensitivity function, then penalize the coefficients with a Just Noticeable Difference (JND) model, and finally extract histogram features to predict Image Quality. The method of Blind Image Quality Indexes (BIQI) was proposed by Liu, H.et al, IEEE transactions systems video technology, vol 21, page 971 to page 982, respectively. The method comprises two steps, firstly, images are classified according to distortion types by using Distorted Image Statistics (DIS), and then quality evaluation is carried out according to different distortion types. Zhai, g. et al, in a paper "a psychological Quality measurement in Free-Energy Principle" published in IEEE trans. image Process, volume 21, page 1, page 41 to page 52, simulate a model of generation inside the brain using an AR model, AR-represent an image, and extract statistical information representing the Quality of the image. An underwater image quality evaluation method based on CIELab space chromaticity, contrast and saturation measurement is proposed by Yang, M et al in the paper "An underserver color image quality evaluation method" published in IEEE Trans. image processing, volume 24, No. 12, pages 6062 to 6071. Panetta, K et al, in the paper "Human-Visual-System-embedded image quality measures" published in IEEE Journal of organic Engineering, Vol.41, pp.3 to 551, inspired by the Human Visual System (HVS), evaluated the imaging quality of underwater images from three aspects of chroma, sharpness and contrast.
Disclosure of Invention
The invention aims to make up for the defects of the prior art and provides a method and a system for evaluating the quality of an underwater image.
The invention is realized by the following technical scheme:
a method of quality assessment of an underwater image, the method comprising the steps of:
s1, extracting the brightness and chroma characteristics of the underwater image, and estimating the brightness and chroma of the input picture;
s2, extracting the blur degree characteristics of the underwater image, and estimating the blur degree of the input picture;
s3, extracting the contrast characteristic of the underwater image, and estimating the contrast of the input picture;
s4, learning a mapping model of the image features extracted by the steps S1-S3 to the image quality on the training set by using a support vector regression method for predicting the image quality.
In the step S1, the underwater image is decomposed into three channels, red, green and blue, the mean value of the red channel is extracted as the chromaticity characteristic of the image, and the chromaticity of the image is estimated; and converting the underwater image into a gray image, extracting the mean value of the gray image as the brightness characteristic of the image, and estimating the brightness of the image.
In step S2, the grayscale image corresponding to the underwater image is decomposed into three layers of wavelet sub-bands, the total energy of the wavelet coefficients is calculated and used as the blur characteristic of the underwater image, and the blur of the underwater image is estimated.
In step S3, first, the KL distance between the histogram of gray scale of the underwater image and the uniform distribution is calculated, then the JS distance between the histogram of gray scale and the uniform distribution is further calculated, and the contrast of the underwater image is estimated by using the JS distance as a contrast feature.
In step S4, a group of underwater images is used as a training set, luminance, chrominance, blur and contrast characteristics are extracted for each image, then subjective scores corresponding to the extracted characteristics and the underwater images are input into a support vector regression model, a mapping model from image characteristics to image quality is learned, and the quality of the underwater images is predicted by using the model.
A quality evaluation system of underwater images comprises an image feature extraction module and a mapping model learning module, wherein image features of the underwater images are extracted through the image feature extraction module to obtain image feature values of the underwater images, the mapping model learning module utilizes a group of underwater images as a training set, utilizes a support vector regression model to learn a mapping model from the image features to image quality, and utilizes the model to predict the quality of the underwater images.
The image characteristics of the underwater image comprise brightness characteristics, chrominance characteristics, fuzzy degree characteristics and contrast characteristics of the image.
The invention has the advantages that:
the invention provides a method and a system for evaluating the quality of an underwater image, which are used for extracting features closely related to the quality of the underwater image, representing the quality of the image and utilizing a support vector regression model to learn the mapping from the image features to the image quality so as to judge the quality of the underwater image.
Drawings
FIG. 1 is a schematic diagram of an embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the spirit of the invention. All falling within the scope of the present invention.
The underwater imaging environment is complex, the method and the device represent the factors influencing the image quality by representing the main factors influencing the underwater image quality, including brightness, chroma, contrast and ambiguity, respectively carrying out modeling expression, extracting digital features to represent the factors influencing the image quality, and then learning the mapping relation from the image features to the image quality by utilizing a support vector regression model.
Fig. 1 is a schematic diagram of an embodiment of the underwater image quality evaluation method of the present invention. As shown in fig. 1, an embodiment of the present invention provides a method for evaluating quality of an underwater image, where the method includes: s1, extracting the brightness and chroma characteristics of the underwater image, and estimating the brightness and chroma of the input picture; s2, extracting the blur degree characteristics of the underwater image, and estimating the blur degree of the input picture; s3, extracting the contrast characteristic of the underwater image, and estimating the contrast of the input picture; s4, a model of mapping the image features extracted by steps S1-S3 to image quality is learned on the training set using support vector regression method for predicting the image quality. The method comprises the steps of representing the change of image quality by extracting features related to the underwater image quality, including brightness, chroma, fuzziness and contrast features, and utilizing a support vector regression model to learn the mapping relation from the image features to the image quality so as to judge the quality of the underwater image. The method does not need to refer to an original image, can obtain higher prediction performance, has high running speed and meets the application requirement of underwater imaging.
In an embodiment, the specific implementation process and the detailed details of the quality evaluation method for the underwater image are as follows: firstly, decomposing an input underwater image into three channels of red, green and blue, which are respectively represented as R, G and B: then extracting the mean value of the red channel as the chroma characteristic of the underwater image:
wherein r represents the chromaticity characteristic, and N is the pixel number of the image; then, the underwater image is converted into a gray image:
wherein the content of the first and second substances,representing a gray level image corresponding to the underwater image, and then extracting the mean value of the gray level image as the brightness characteristic of the underwater image:
where b represents a luminance characteristic.
Then, carrying out wavelet decomposition on the gray level image corresponding to the underwater image to obtain three-layer sub-band wavelet coefficients, and recording the three-layer sub-band wavelet coefficients as { LH }l,HLl,HHl1,2,3, calculating the energy of the wavelet coefficient of each layer by the following calculation method:
whereinXY denotes one of the subbands LH, HL or HH,representing sub-bands XYLThe energy of the wavelet coefficients is contained,representing sub-bands XYLIncluding the number of wavelet coefficients, is included,representing the wavelet coefficients at location (i, j). Then, calculating the energy of the wavelet coefficient of each layer, wherein the calculation method comprises the following steps:
wherein E islRepresenting the total energy, λ, of the wavelet coefficients of the layer l1、λ2And λ3The values are 0.1, 0.1 and 0.8 respectively as parameters. Then adding the energy of the wavelet coefficients of the three layers, and calculating the total energy of the wavelet coefficients of the whole underwater image, wherein the total energy is expressed as:
wherein E isTTotal energy of wavelet coefficients, ω, representing the entire image1、ω2And ω3Values for parameters are 4/7, 2/7 and 1/7, respectively. By using ETThe degree of blur of an image is estimated as a degree of blur characteristic of the image.
Finally, calculating the distance between the underwater image histogram and the uniform distribution to extract the image contrast characteristic; specifically, calculating the difference between the underwater image histogram and the uniformly distributed Kullback-Leibler, and expressing the difference as follows:
DKL(m||n)=-∫m(x)logn(x)dx+∫m(x)logm(x)dx
where m and n represent the histogram and uniform distribution of the underwater image, respectively, and then the Jensen-Shannon difference between m and n is calculated, expressed as:
wherein:
by using DJS(m, n) as a contrast characteristic of the underwater image, the contrast of the image is estimated.
Training an underwater image quality prediction model, extracting the above characteristics of each image by using a group of underwater images as a training set, inputting the extracted characteristics and the corresponding subjective quality scores into a support vector regression model, training a quality prediction model, and predicting the quality of other underwater images by using the model.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes and modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention.
Claims (10)
1. A quality evaluation method of underwater images is characterized in that: the method comprises the following steps:
s1, extracting the brightness and chroma characteristics of the underwater image, and estimating the brightness and chroma of the input picture;
s2, extracting the blur degree characteristics of the underwater image, and estimating the blur degree of the input picture;
s3, extracting the contrast characteristic of the underwater image, and estimating the contrast of the input picture;
s4, learning a mapping model from image characteristics to image quality by using a support vector regression model on the training set to predict the quality of the underwater image, wherein the image characteristics comprise the brightness, the chroma, the fuzzy degree and the contrast of the input image obtained in the steps S1-S3.
2. The method for evaluating the quality of an underwater image according to claim 1, characterized in that: the extracting of the luminance and chrominance characteristics of the underwater image and the estimating of the luminance and chrominance of the input picture in step S1 are specifically as follows:
decomposing the underwater image into three channels of red, green and blue, extracting the mean value of the red channel as the chromaticity characteristic of the underwater image, and estimating the chromaticity of the underwater image; and converting the underwater image into a gray image, extracting the mean value of the gray image as the brightness characteristic of the underwater image, and estimating the brightness of the underwater image.
3. The method for evaluating the quality of an underwater image according to claim 2, characterized in that: the step S1 specifically includes: the underwater image is decomposed into three channels of red, green and blue, which are respectively represented as R, G, B, and then the average value of the red channel is extracted as the chrominance characteristic of the underwater image:
wherein r represents the chromaticity characteristic, and N is the pixel number of the image; then, the underwater image is converted into a gray image:
wherein the content of the first and second substances,representing a gray level image corresponding to the underwater image, and then extracting the mean value of the gray level image as the brightness characteristic of the underwater image:
where b represents a luminance characteristic.
4. The method for evaluating the quality of an underwater image according to claim 1, characterized in that: step S2, extracting the blur degree characteristics of the underwater image, and estimating the blur degree of the input picture, the specific method is as follows: and performing wavelet decomposition on the gray level image corresponding to the underwater image to decompose the gray level image into three layers of wavelet sub-bands, calculating the total energy of wavelet coefficients and using the total energy as the blurring characteristic of the underwater image to estimate the blurring degree of the underwater image.
5. The method for evaluating the quality of the underwater image according to claim 4, wherein: the step S2 specifically includes: firstly, carrying out wavelet decomposition on a gray level image corresponding to an underwater image to obtain three-layer sub-band wavelet coefficients, and recording the three-layer sub-band wavelet coefficients as { LH }l,HLl,HHl1,2,3, and then calculating the energy of each layer of wavelet coefficients, wherein the calculation method comprises the following steps:
wherein XY represents one of the sub-bands LH, HL or HH,representing sub-bands XYlThe energy of the wavelet coefficients is contained,representing sub-bands XYlIncluding the number of wavelet coefficients, is included,representing the wavelet coefficients at location (i, j), the energy of each layer of wavelet coefficients is:
wherein E islRepresenting the total energy, λ, of the wavelet coefficients of the layer l1、λ2And λ3Is a parameter; then adding the energy of the wavelet coefficients of the three layers, and calculating the total energy of the wavelet coefficients of the whole underwater image, wherein the total energy is expressed as:
wherein E isTTotal energy of wavelet coefficients, ω, representing the entire image1、ω2And ω3Is a parameter; total energy E of wavelet coefficient of whole imageTAnd estimating the blurring degree of the underwater image as the blurring characteristic of the underwater image.
6. The method for evaluating the quality of an underwater image according to claim 1, characterized in that: step S3, extracting the contrast characteristics of the underwater image, and estimating the contrast of the input picture, the specific method is as follows: firstly, calculating the difference between a gray level histogram of an underwater image and a uniformly distributed Kullback-Leibler, then calculating the difference between the gray level histogram and a uniformly distributed Jensen-Shannon, and estimating the contrast of the underwater image by using the Jensen-Shannon difference as a contrast characteristic.
7. The method for evaluating the quality of the underwater image according to claim 6, wherein: the step S3 specifically includes: calculating the difference between the gray level histogram of the underwater image and the Kullback-Leibler of uniform distribution, and expressing as follows:
DKL(m||n)=-∫m(x)logn(x)dx+∫m(x)logm(x)dx
wherein m and n respectively represent a gray histogram and a uniform distribution of the underwater image, and then a Jensen-Shannon difference between m and n is calculated and represented as:
wherein:
using the Jensen-Shannon difference D between m and nJS(m, n) estimating the contrast of the underwater image as the contrast characteristic of the underwater image.
8. The method for evaluating the quality of the underwater image according to claim 6, wherein: in step S4, a support vector regression model is used to learn a mapping model from image features to image quality on the training set to predict the quality of the underwater image, and the specific method is as follows: a group of underwater images are used as a training set, the brightness, the chroma, the fuzzy degree and the contrast characteristic of each underwater image are extracted, then the extracted characteristics and the subjective scores corresponding to the underwater images are input into a support vector regression model, a mapping model of the image characteristics to the image quality is learned, and the quality of the underwater images is predicted by using the mapping model.
9. A quality evaluation system of underwater images is characterized in that: the underwater image prediction method comprises an image feature extraction module and a mapping model learning module, wherein the image feature extraction module is used for extracting the image features of underwater images to obtain the image feature values of the underwater images, the mapping model learning module uses a group of underwater images as a training set, a mapping model from the image features to the image quality is learned by using a support vector regression model, and the model is used for predicting the quality of the underwater images.
10. The system for evaluating the quality of an underwater image according to claim 9, wherein: the image characteristics of the underwater image comprise brightness characteristics, chrominance characteristics, fuzzy degree characteristics and contrast characteristics of the image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011411080.1A CN112419300A (en) | 2020-12-04 | 2020-12-04 | Underwater image quality evaluation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011411080.1A CN112419300A (en) | 2020-12-04 | 2020-12-04 | Underwater image quality evaluation method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112419300A true CN112419300A (en) | 2021-02-26 |
Family
ID=74830373
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011411080.1A Pending CN112419300A (en) | 2020-12-04 | 2020-12-04 | Underwater image quality evaluation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112419300A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109345520A (en) * | 2018-09-20 | 2019-02-15 | 江苏商贸职业学院 | A kind of quality evaluating method of image definition |
CN109584242A (en) * | 2018-11-24 | 2019-04-05 | 天津大学 | Maximum entropy and KL divergence are without reference contrast distorted image quality evaluating method |
CN109829905A (en) * | 2019-01-30 | 2019-05-31 | 中国矿业大学 | It is a kind of face beautification perceived quality without reference evaluation method |
CN109871852A (en) * | 2019-01-05 | 2019-06-11 | 天津大学 | A kind of no reference tone mapping graph image quality evaluation method |
CN110046673A (en) * | 2019-04-25 | 2019-07-23 | 上海大学 | No reference tone mapping graph image quality evaluation method based on multi-feature fusion |
CN111354048A (en) * | 2020-02-24 | 2020-06-30 | 清华大学深圳国际研究生院 | Quality evaluation method and device for camera-oriented acquired pictures |
-
2020
- 2020-12-04 CN CN202011411080.1A patent/CN112419300A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109345520A (en) * | 2018-09-20 | 2019-02-15 | 江苏商贸职业学院 | A kind of quality evaluating method of image definition |
CN109584242A (en) * | 2018-11-24 | 2019-04-05 | 天津大学 | Maximum entropy and KL divergence are without reference contrast distorted image quality evaluating method |
CN109871852A (en) * | 2019-01-05 | 2019-06-11 | 天津大学 | A kind of no reference tone mapping graph image quality evaluation method |
CN109829905A (en) * | 2019-01-30 | 2019-05-31 | 中国矿业大学 | It is a kind of face beautification perceived quality without reference evaluation method |
CN110046673A (en) * | 2019-04-25 | 2019-07-23 | 上海大学 | No reference tone mapping graph image quality evaluation method based on multi-feature fusion |
CN111354048A (en) * | 2020-02-24 | 2020-06-30 | 清华大学深圳国际研究生院 | Quality evaluation method and device for camera-oriented acquired pictures |
Non-Patent Citations (3)
Title |
---|
PHONG V. VU等: ""A Fast Wavelet-Based Algorithm for Global and Local Image Sharpness Estimation"" * |
VITTORIA BRUNI等: ""Evaluation of degraded images using adaptive Jensen-Shannon divergence"" * |
乔子昂等: ""颜色通道下的无参考图像质量评价"" * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | An experimental-based review of image enhancement and image restoration methods for underwater imaging | |
Gu et al. | No-reference quality assessment of screen content pictures | |
CN111489303A (en) | Maritime affairs image enhancement method under low-illumination environment | |
CN108052980B (en) | Image-based air quality grade detection method | |
CN111080541B (en) | Color image denoising method based on bit layering and attention fusion mechanism | |
CN107274365A (en) | A kind of mine image intensification method based on unsharp masking and NSCT algorithms | |
CN109978854B (en) | Screen content image quality evaluation method based on edge and structural features | |
CN111161360B (en) | Image defogging method of end-to-end network based on Retinex theory | |
WO2022095253A1 (en) | Method for removing cloud and haze on basis of depth channel sensing | |
CN109389569B (en) | Monitoring video real-time defogging method based on improved DehazeNet | |
CN103607589B (en) | JND threshold value computational methods based on hierarchy selection visual attention mechanism | |
CN116596792B (en) | Inland river foggy scene recovery method, system and equipment for intelligent ship | |
CN115170410A (en) | Image enhancement method and device integrating wavelet transformation and attention mechanism | |
CN114757854B (en) | Night vision image quality improving method, device and equipment based on multispectral analysis | |
CN113284061A (en) | Underwater image enhancement method based on gradient network | |
CN112102186A (en) | Real-time enhancement method for underwater video image | |
CN111242870A (en) | Low-light image enhancement method based on deep learning knowledge distillation technology | |
CN110910347A (en) | Image segmentation-based tone mapping image no-reference quality evaluation method | |
CN117495718A (en) | Multi-scale self-adaptive remote sensing image defogging method | |
CN117391920A (en) | High-capacity steganography method and system based on RGB channel differential plane | |
CN110415816B (en) | Skin disease clinical image multi-classification method based on transfer learning | |
CN112508847A (en) | Image quality evaluation method based on depth feature and structure weighted LBP feature | |
CN111127386B (en) | Image quality evaluation method based on deep learning | |
CN112419300A (en) | Underwater image quality evaluation method and system | |
Guo et al. | Marg-unet: a single image dehazing network based on multimodal attention residual group |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210226 |