CN112950629A - No-reference panoramic image quality evaluation method and system - Google Patents
No-reference panoramic image quality evaluation method and system Download PDFInfo
- Publication number
- CN112950629A CN112950629A CN202110359001.5A CN202110359001A CN112950629A CN 112950629 A CN112950629 A CN 112950629A CN 202110359001 A CN202110359001 A CN 202110359001A CN 112950629 A CN112950629 A CN 112950629A
- Authority
- CN
- China
- Prior art keywords
- panoramic image
- difference
- markov
- model
- module
- 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 56
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 22
- 230000008569 process Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000009826 distribution Methods 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 10
- 230000007704 transition Effects 0.000 description 7
- 238000002474 experimental method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000007430 reference method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000001303 quality assessment method Methods 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
- G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
-
- 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)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a system for evaluating the quality of a non-reference panoramic image, wherein the method comprises the following steps: calculating a difference image of adjacent pixels to obtain a difference image; setting a threshold value T of the differential image, wherein the values of the differential image which are greater than T or less than-T are set as T or-T; calculating a Markov process on each difference graph to obtain a Markov probability model; and inputting the probability distribution of the Markov probability model into the regression model as a characteristic for training and predicting to obtain the final quality score of the panoramic image. The system comprises: the device comprises a difference image obtaining module, a threshold setting module, a Markov probability model obtaining module and a model training and predicting module. The method combines the statistical characteristics of the panoramic image, and has better accuracy compared with other quality evaluation methods without reference images.
Description
Technical Field
The invention relates to the technical field of panoramic image quality evaluation, in particular to a method and a system for evaluating the quality of a non-reference panoramic image.
Background
Panoramic images, one of the most important forms of Virtual Reality (VR) media content, can provide a viewer with a 360 degree viewing angle. However, unlike conventional images, panoramic images have a very high resolution, which makes them difficult to transmit, compress, or store. During the acquisition, stitching and transmission process, the quality of the panoramic image may be compromised, seriously affecting the quality of experience of the viewer.
The panoramic video evaluation is classified into subjective quality evaluation and objective quality evaluation, as in the planar video evaluation. Subjective quality evaluation refers to that people subjectively score video quality, and is generally used for manufacturing a database and judging the quality of an objective algorithm; objective methods use mathematical models to assess video quality, automatically without human involvement.
Objective algorithms can be divided into three types: full reference, half reference and no reference. The full-reference method requires all information of the original video, the half-reference method requires some information of the original video, and the no-reference method can obtain the quality of the video without analyzing the original information.
In the prior art, some methods are based on PSNR (peak signal-to-noise ratio). However, the PSNR-based method does not consider visual characteristics of human eyes, and thus, ssim (structural similarity) -based methods have been proposed later. These methods are all full reference algorithms, however, in the actual evaluation process, it is difficult to obtain a reference image without distortion. Therefore, a no-reference evaluation method based on learning has been proposed thereafter. However, in these methods, the statistical characteristics of the panoramic image are not taken into consideration, but the statistical characteristics of the panoramic image change under different distortion degrees, and the perceptual quality of the image can be calculated based on the statistical characteristics of the panoramic image. Therefore, how to model the statistical characteristics of the panoramic image and how to accurately predict the image quality is a problem which needs to be further solved at present.
Disclosure of Invention
The invention provides a method and a system for evaluating the quality of a non-reference panoramic image aiming at the problems in the prior art, combines the statistical characteristics of the panoramic image, and has better accuracy compared with other non-reference image quality evaluations.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention provides a no-reference panoramic image quality evaluation method, which comprises the following steps:
s11: calculating a difference image of adjacent pixels to obtain a difference image;
s12: setting a threshold value T of the differential image, wherein the values of the differential image which are greater than T or less than-T are set as T or-T;
s13: calculating a Markov process on each difference graph to obtain a Markov probability model;
s14: and inputting the probability distribution of the Markov probability model into a regression model as a characteristic for training and predicting to obtain the final quality score of the panoramic image.
Preferably, the S11 further includes: calculating difference images of adjacent pixels in eight directions to obtain difference images;
wherein, eight directions are respectively: up, down, left, right, left up, left down, right up, right down.
Preferably, the S13 further includes: calculating a first order Markov process and a second order Markov process on each of the difference maps;
further, the features of the symmetric directions in the markov probability model are combined.
Preferably, the regression model in S14 is further an SVR, and it selects RBF as the kernel function.
The invention also provides a no-reference panoramic image quality evaluation system, which comprises: the device comprises a difference graph obtaining module, a threshold setting module, a Markov probability model obtaining module and a model training and predicting module; wherein the content of the first and second substances,
the difference image obtaining module is used for calculating difference images of adjacent pixels to obtain a difference image;
the threshold setting module is used for setting a threshold T of the differential image, and the values of the differential image which are greater than T or less than-T are all set as T or-T;
the Markov probability module obtaining module is used for calculating a Markov process on each differential graph to obtain a Markov probability model;
and the model training set prediction module is used for inputting the probability distribution of the Markov probability model into a regression model as a feature for training and predicting to obtain the final quality score of the panoramic image.
Preferably, the difference image obtaining module is further configured to calculate difference images of adjacent pixels in eight directions to obtain a difference image;
wherein, eight directions are respectively: up, down, left, right, left up, left down, right up, right down.
Preferably, the Markov probability module obtaining module is further configured to compute a first order Markov process and a second order Markov process on each of the difference plots;
further, the features of the symmetric directions in the markov probability model are combined.
Preferably, the regression model in the model training set prediction module is further an SVR, and it selects RBF as a kernel function.
The invention also provides a no-reference panoramic image quality rating device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor is used for executing the no-reference panoramic image quality rating method when executing the program.
The present invention also provides a computer-readable storage medium having stored thereon a computer program for executing the method for rating the quality of a non-reference panoramic image when executed by a processor.
Compared with the prior art, the embodiment of the invention has at least one of the following advantages:
(1) the method and the system for evaluating the quality of the non-reference panoramic image calculate the pixel value transition probability of the panoramic image, then construct a Markov probability model for the transition probability, combine the statistical characteristics of the panoramic image, and have the following performances: the Spearman rank-order correlation coefficient (SROCC), the Pearson Linear Correlation Coefficient (PLCC) and the Root Mean Square Error (RMSE) are superior to other existing technologies;
(2) the method and the system for evaluating the quality of the non-reference panoramic image, provided by the invention, train and predict the model by constructing the Markov probability model, are simple to calculate and do not relate to frequency conversion and convolution operation.
Drawings
Embodiments of the invention are further described below with reference to the accompanying drawings:
fig. 1 is a flowchart of a method for evaluating quality of a non-reference panoramic image according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating the relationship between MOS and prediction score for each test picture according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a no-reference panoramic image quality evaluation system according to an embodiment of the present invention.
Description of reference numerals: the method comprises a 1-difference graph obtaining module, a 2-threshold setting module, a 3-Markov probability model obtaining module and a 4-model training and predicting module.
Detailed Description
The following examples are given for the detailed implementation and specific operation of the present invention, but the scope of the present invention is not limited to the following examples.
Fig. 1 is a flowchart illustrating a method for evaluating quality of a non-reference panoramic image according to an embodiment of the present invention.
Referring to fig. 1, the method for evaluating quality of a non-reference panoramic image of the present embodiment includes:
s11: calculating a difference image of adjacent pixels to obtain a difference image;
for a panoramic image of size m × n, the difference image D is calculated by the following formula
Wherein Ii,jRepresents the pixel value of the ith row and the jth column in the image, i belongs to {1,j∈{1,...,n-1}。
S12: setting a threshold value T of the differential image, wherein the values of the differential image which are greater than T or less than-T are set as T or-T;
map D is transformed as follows
S13: calculating a Markov process on each difference graph to obtain a Markov probability model;
s14: and inputting the probability distribution of the Markov probability model into the regression model as a characteristic for training and predicting to obtain the final quality score of the panoramic image.
According to the embodiment of the invention, the pixel value transition probability of the panoramic image is calculated, and then the Markov probability model is constructed for the transition probability, so that the statistical characteristics of the panoramic image are combined, and the accuracy is better compared with other non-reference image quality evaluation.
In the preferred embodiment, the calculation of the adjacent pixel difference image in S11 includes eight directions of adjacent pixel difference images, where the eight directions are: up, down, left, right, left up, left down, right up, right down, all directions can be noted as arrow symbols { ↓, ±, →,}. The calculation in the following is exemplified by the difference in the right direction, and the other directions are calculated in a similar manner.
In a preferred embodiment, S13 further includes: calculating a first-order Markov process and a second-order Markov process on each difference graph to obtain a second-order Markov model, wherein a transition probability formula is as follows by taking a right direction as an example:
further, in order to further reduce the dimensionality of the features, the features in the symmetric directions in the markov probability model are combined according to the following formula:
wherein, k is (2T +1)3In one embodiment, T is 3, 2k is 686, i.e., feature dimension is 686.
In a preferred embodiment, the regression model in S14 is further svr (support vector regression), and it selects rbf (radial basis function) as the kernel function.
Score=SVR_model{I} (5)
Experiments were performed on the CVIQD dataset below to evaluate the model proposed by the present invention. The experimental environment of the experiment is a win10 system and a matlab2018a experimental platform. The evaluation indexes of the experiment are SROCC (specific rank-order correlation coefficient), PLCC (Pearson linear correlation coefficient), RMSE (root mean squared error). The higher the SRCC and PLCC, the lower the RMSE, indicating better model performance. The data set has 544 panoramic images, containing 16 scenes. We randomly divided 12 scenes as a training set, leaving 4 scenes as a test set. And repeating 1000 times of training-testing experiments, and taking the median of the obtained results as the final experiment result. Before calculating PLCC and RMSE for different objective quality assessment methods, the predicted quality scores need to be mapped into a common scale using a five-parameter logistic nonlinear fitting function, as follows:
wherein { betaiI | (1, 2.·, 5): is 5 parameters to be fitted, x represents an original score calculated by an objective quality evaluation algorithm, and g (x) represents a quality score obtained by nonlinear mapping of x.
Table 1 shows the comparison of the algorithm of the present invention with other full-reference/no-reference quality evaluation algorithms, from a single distortion type and all distortion types, respectively. Various indexes of the algorithm provided by the user are superior to those of the existing algorithm, and in addition, the performance of the algorithm is slightly reduced for the HEVC distortion type.
TABLE 1 quality evaluation algorithm Performance comparison
As shown in fig. 2, the MOS of each test picture is related to the prediction score, and it can be seen that the fitting degree is good.
The experiment shows that the method can well extract the statistical characteristics of the panoramic image, thereby predicting the human perception quality score.
Fig. 3 is a schematic diagram of a no-reference panoramic image quality evaluation system according to an embodiment of the present invention.
Referring to fig. 3, the no-reference panoramic image quality evaluation system of the present embodiment includes: the device comprises a difference diagram obtaining module 1, a threshold setting module 2, a Markov probability model obtaining module 3 and a model training and predicting module 4. The difference image obtaining module 1 is used for calculating difference images of adjacent pixels to obtain a difference image. The threshold setting module 2 is configured to set a threshold T of the difference map, and values of the difference map that are greater than T or smaller than-T are both set to T or-T. The Markov probability module obtaining module 3 is used for calculating a Markov process on each differential graph to obtain a Markov probability model. And the model training set prediction module 4 is used for inputting the probability distribution of the Markov probability model into the regression model as a characteristic for training and predicting to obtain the final quality score of the panoramic image. In the embodiment, the pixel value transition probability of the panoramic image is calculated, and then the Markov probability model is constructed for the transition probability, so that the statistical characteristics of the panoramic image are combined, and the performance of the model is due to other existing technologies.
In a preferred embodiment, the difference image obtaining module is further configured to calculate difference images of adjacent pixels in eight directions to obtain a difference image; wherein, eight directions are respectively: up, down, left, right, left up, left down, right up, right down.
In a preferred embodiment, the Markov probability module obtaining module is further configured to compute a first order Markov process and a second order Markov process on each of the difference maps; further, the features of the symmetric directions in the markov probability model are combined.
In a preferred embodiment, the regression model in the model training set prediction module is further an SVR, and it selects RBF as the kernel function.
Based on the above embodiments, in another embodiment, the present invention further provides a no-reference panoramic image quality rating apparatus, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to perform the no-reference panoramic image quality rating method in any one of the above embodiments.
Based on the above-mentioned embodiments, in another embodiment, the present invention further provides a computer-readable storage medium having stored thereon a computer program, which when executed by a processor, is configured to perform the no-reference panoramic image quality rating method in any of the above-mentioned embodiments.
The quality evaluation system for the non-reference panoramic image provided by the embodiment of the invention trains and predicts the model by constructing the Markov probability model, has simple calculation and does not relate to frequency conversion and convolution operation.
It should be noted that, the steps in the method provided by the present invention may be implemented by using corresponding modules, devices, units, and the like in the system, and those skilled in the art may implement the composition of the system by referring to the technical solution of the method, that is, the embodiment in the method may be understood as a preferred example for constructing the system, and will not be described herein again.
Those skilled in the art will appreciate that, in addition to implementing the system and its various devices provided by the present invention in purely computer readable program code means, the method steps can be fully programmed to implement the same functions by implementing the system and its various devices in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system and various devices thereof provided by the present invention can be regarded as a hardware component, and the devices included in the system and various devices thereof for realizing various functions can also be regarded as structures in the hardware component; means for performing the functions may also be regarded as structures within both software modules and hardware components for performing the methods.
The foregoing disclosure of the preferred embodiments of the present invention has been made in an effort to provide a better understanding of the principles of the invention and its practical application, and is not intended to limit the invention to the specific embodiments disclosed herein. Any modifications and variations within the scope of the description, which may occur to those skilled in the art, are intended to be within the scope of the invention.
Claims (10)
1. A no-reference panoramic image quality evaluation method is characterized by comprising the following steps:
s11: calculating a difference image of adjacent pixels to obtain a difference image;
s12: setting a threshold value T of the differential image, wherein the values of the differential image which are greater than T or less than-T are set as T or-T;
s13: calculating a Markov process on each difference graph to obtain a Markov probability model;
s14: and inputting the probability distribution of the Markov probability model into a regression model as a characteristic for training and predicting to obtain the final quality score of the panoramic image.
2. The no-reference panoramic image quality evaluation method according to claim 1, wherein the S11 includes: calculating difference images of adjacent pixels in eight directions to obtain difference images;
wherein, eight directions are respectively: up, down, left, right, left up, left down, right up, right down.
3. The no-reference panoramic image quality evaluation method according to claim 1, wherein the S13 includes: calculating a first order Markov process and a second order Markov process on each of the difference maps;
further, the features of the symmetric directions in the markov probability model are combined.
4. The no-reference panoramic image quality evaluation method of claim 1, wherein the regression model in S14 is SVR, and it selects RBF as a kernel function.
5. A no-reference panoramic image quality rating system, comprising: the device comprises a difference graph obtaining module, a threshold setting module, a Markov probability model obtaining module and a model training and predicting module; wherein the content of the first and second substances,
the difference image obtaining module is used for calculating difference images of adjacent pixels to obtain a difference image;
the threshold setting module is used for setting a threshold T of the differential image, and the values of the differential image which are greater than T or less than-T are all set as T or-T;
the Markov probability module obtaining module is used for calculating a Markov process on each differential graph to obtain a Markov probability model;
and the model training set prediction module is used for inputting the probability distribution of the Markov probability model into a regression model as a feature for training and predicting to obtain the final quality score of the panoramic image.
6. The no-reference panoramic image quality rating system of claim 5, wherein the difference map obtaining module calculates difference images of adjacent pixels in eight directions to obtain a difference map;
wherein, eight directions are respectively: up, down, left, right, left up, left down, right up, right down.
7. The non-reference panoramic image quality rating system of claim 5, wherein the Markov probability module obtains module calculates a first order Markov process and a second order Markov process on each of the difference maps;
further, the features of the symmetric directions in the markov probability model are combined.
8. The no-reference panoramic image quality rating system of claim 5, wherein the regression model in the model training set prediction module is an SVR and it selects an RBF as a kernel function.
9. A non-reference panoramic image quality rating apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor is adapted to perform the method of any of claims 1 to 4 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110359001.5A CN112950629A (en) | 2021-04-02 | 2021-04-02 | No-reference panoramic image quality evaluation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110359001.5A CN112950629A (en) | 2021-04-02 | 2021-04-02 | No-reference panoramic image quality evaluation method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112950629A true CN112950629A (en) | 2021-06-11 |
Family
ID=76232157
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110359001.5A Pending CN112950629A (en) | 2021-04-02 | 2021-04-02 | No-reference panoramic image quality evaluation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112950629A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113643262A (en) * | 2021-08-18 | 2021-11-12 | 上海大学 | No-reference panoramic image quality evaluation method, system, equipment and medium |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014131128A (en) * | 2012-12-28 | 2014-07-10 | Samsung R&D Institute Japan Co Ltd | Image quality estimation device, image quality estimation method, and image quality estimation program |
US20150093016A1 (en) * | 2013-09-29 | 2015-04-02 | Ningbo University | Digital watermarking based method for objectively evaluating quality of stereo image |
CN104766299A (en) * | 2014-12-26 | 2015-07-08 | 国家电网公司 | Image quality assessment method based on probabilistic graphical model |
CN105208374A (en) * | 2015-08-24 | 2015-12-30 | 宁波大学 | Non-reference image quality objective evaluation method based on deep learning |
US20170013191A1 (en) * | 2015-07-08 | 2017-01-12 | Intel Corporation | No-reference image and video quality evaluation |
CN107371016A (en) * | 2017-07-25 | 2017-11-21 | 天津大学 | Based on asymmetric distortion without with reference to 3D stereo image quality evaluation methods |
CN109740592A (en) * | 2018-12-04 | 2019-05-10 | 上海大学 | Based on the picture quality of memory without ginseng appraisal procedure |
CN110084782A (en) * | 2019-03-27 | 2019-08-02 | 西安电子科技大学 | Full reference image quality appraisement method based on saliency detection |
CN110766658A (en) * | 2019-09-23 | 2020-02-07 | 华中科技大学 | Non-reference laser interference image quality evaluation method |
CN111127298A (en) * | 2019-06-12 | 2020-05-08 | 上海大学 | Panoramic image blind quality assessment method |
-
2021
- 2021-04-02 CN CN202110359001.5A patent/CN112950629A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014131128A (en) * | 2012-12-28 | 2014-07-10 | Samsung R&D Institute Japan Co Ltd | Image quality estimation device, image quality estimation method, and image quality estimation program |
US20150093016A1 (en) * | 2013-09-29 | 2015-04-02 | Ningbo University | Digital watermarking based method for objectively evaluating quality of stereo image |
CN104766299A (en) * | 2014-12-26 | 2015-07-08 | 国家电网公司 | Image quality assessment method based on probabilistic graphical model |
US20170013191A1 (en) * | 2015-07-08 | 2017-01-12 | Intel Corporation | No-reference image and video quality evaluation |
CN105208374A (en) * | 2015-08-24 | 2015-12-30 | 宁波大学 | Non-reference image quality objective evaluation method based on deep learning |
CN107371016A (en) * | 2017-07-25 | 2017-11-21 | 天津大学 | Based on asymmetric distortion without with reference to 3D stereo image quality evaluation methods |
CN109740592A (en) * | 2018-12-04 | 2019-05-10 | 上海大学 | Based on the picture quality of memory without ginseng appraisal procedure |
CN110084782A (en) * | 2019-03-27 | 2019-08-02 | 西安电子科技大学 | Full reference image quality appraisement method based on saliency detection |
CN111127298A (en) * | 2019-06-12 | 2020-05-08 | 上海大学 | Panoramic image blind quality assessment method |
CN110766658A (en) * | 2019-09-23 | 2020-02-07 | 华中科技大学 | Non-reference laser interference image quality evaluation method |
Non-Patent Citations (4)
Title |
---|
DOHYOUNG LEE ET AL.: ""Toward a No-Reference Image Quality Assessment Using Statistics of Perceptual Color Descriptors"", 《IEEE TRANSACTIONS ON IMAGE PROCESSING》 * |
PAVAN CHENNAGIRI MADHUSUDANA ET AL.: ""Subjective and Objective Quality Assessment of Stitched Images for Virtual Reality"", 《IEEE TRANSACTIONS ON IMAGE PROCESSING》 * |
TOMAS PEVNY ET AL.: ""Steganalysis by Subtractive Pixel Adjacency Matrix"", 《IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY》 * |
袁文翀: ""数字隐写图像的特征提取及信息检测方法"", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113643262A (en) * | 2021-08-18 | 2021-11-12 | 上海大学 | No-reference panoramic image quality evaluation method, system, equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109379550B (en) | Convolutional neural network-based video frame rate up-conversion method and system | |
AU2020203139B2 (en) | Techniques for robustly predicting perceptual video quality | |
Yang et al. | Subjective quality assessment of screen content images | |
Fu et al. | Blind image quality assessment for multiply distorted images via convolutional neural networks | |
CN111127298B (en) | Panoramic image blind quality assessment method | |
CN107945151B (en) | Repositioning image quality evaluation method based on similarity transformation | |
CN108513132B (en) | Video quality evaluation method and device | |
CN112950579A (en) | Image quality evaluation method and device and electronic equipment | |
CN112950629A (en) | No-reference panoramic image quality evaluation method and system | |
CN116843684B (en) | End-to-end panoramic image quality evaluation method based on dynamic visual content | |
Liu et al. | Spatio-temporal interactive laws feature correlation method to video quality assessment | |
CN104103065A (en) | No-reference fuzzy image quality evaluation method based on singular value decomposition | |
CN113298779A (en) | Video redirection quality objective evaluation method based on reverse reconstruction grid | |
Narwaria et al. | Scalable image quality assessment based on structural vectors | |
CN113222902B (en) | No-reference image quality evaluation method and system | |
Yang et al. | Blind VQA on 360° Video via Progressively Learning From Pixels, Frames, and Video | |
Li et al. | No‐reference image quality assessment based on multiscale feature representation | |
CN114445342A (en) | Haze degree evaluation method and device, electronic equipment and storage medium | |
CN111539909B (en) | Image quality evaluation method, system and terminal for similar scene image group | |
CN113643262A (en) | No-reference panoramic image quality evaluation method, system, equipment and medium | |
Yu et al. | Predicting encoded picture quality in two steps is a better way | |
Shi et al. | Using Analytic Hierarchy Process to Assess Network Video Quality | |
CN112734733B (en) | Non-reference image quality monitoring method based on channel recombination and feature fusion | |
Corchs et al. | Quality Assessment of JPEG-distorted Face Images: Influence of Affective Content. | |
Zhang et al. | Image quality assessment using author topic model |
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: 20210611 |