Blind Assessment of Wavelet-Compressed Images Based On Subband Statistics of Natural Scenes

2014 ◽  
Vol 6 (1) ◽  
pp. 26-43
Author(s):  
Yingchun Guo ◽  
Gang Yan ◽  
Cuihong Xue ◽  
Yang Yu
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Correlation Coefficient ◽  
Image Quality Assessment ◽  
Pearson Correlation ◽  
Correlation Coefficients ◽  
Subjective Assessment ◽  
Reference Image ◽  
Natural Scenes ◽  
Compressed Images

This paper presents a no-reference image quality assessment metric that makes use of the wavelet subband statistics to evaluate the levels of distortions of wavelet-compressed images. The work is based on the fact that for distorted images the correlation coefficients of the adjacent scale subbands change proportionally with respect to the distortion of a compressed image. Subband similarity is used in this work to measure the correlations of the adjacent scale subbands of the same wavelet orientations. The higher the image quality is (i.e., less distortion), the greater the cosine similarity coefficient will be. Statistical analysis is applied to analyze the performance of the metric by evaluating the relationship between the human subjective assessment scores and the subband cosine similarities. Experimental results show that the proposed blind method for the quality assessment of wavelet-compressed images has sufficient prediction accuracy (high Pearson Correlation Coefficient, PCCs), sufficient prediction monotonicity (high Spearman Correlation Coefficient SCCs) and sufficient prediction consistency (low outlier ratios) and less running time. It is simple to calculate, has a clear physical meaning, and has a stable performance for the four image databases on which the method was tested.

Blind Assessment of Wavelet-Compressed Images Based on Subband Statistics of Natural Scenes

2018 ◽  
pp. 1322-1337
Author(s):  
Yingchun Guo ◽  
Gang Yan ◽  
Cuihong Xue ◽  
Yang Yu
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Correlation Coefficient ◽  
Image Quality Assessment ◽  
Pearson Correlation ◽  
Correlation Coefficients ◽  
Subjective Assessment ◽  
Natural Scenes ◽  
Assessment Scores ◽  
Compressed Images

This paper presents a no-reference image quality assessment metric that makes use of the wavelet subband statistics to evaluate the levels of distortions of wavelet-compressed images. The work is based on the fact that for distorted images the correlation coefficients of the adjacent scale subbands change proportionally with respect to the distortion of a compressed image. Subband similarity is used in this work to measure the correlations of the adjacent scale subbands of the same wavelet orientations. The higher the image quality is (i.e., less distortion), the greater the cosine similarity coefficient will be. Statistical analysis is applied to analyze the performance of the metric by evaluating the relationship between the human subjective assessment scores and the subband cosine similarities. Experimental results show that the proposed blind method for the quality assessment of wavelet-compressed images has sufficient prediction accuracy (high Pearson Correlation Coefficient, PCCs), sufficient prediction monotonicity (high Spearman Correlation Coefficient SCCs) and sufficient prediction consistency (low outlier ratios) and less running time. It is simple to calculate, has a clear physical meaning, and has a stable performance for the four image databases on which the method was tested.

scholarly journals Digital image contrast assessment based on the Weibull distribution parameters

2021 ◽  
pp. 4-13
Author(s):  
Y. I. Golub ◽  
F. V. Starovoitov
Keyword(s):  
Image Quality ◽  
Weibull Distribution ◽  
Quality Assessment ◽  
Image Quality Assessment ◽  
Numerical Estimate ◽  
Rank Correlation ◽  
Subjective Assessment ◽  
Reference Image ◽  
Local Contrast ◽  
Two Parameters

The goal of the studies described in the paper is to find a quantitative assessment that maximally correlates with the subjective assessment of the contrast image quality in the absence of reference image. As a result of the literature analysis, 16 functions were selected that are used for no-refernce image quality assessment: BEGH, BISH, BREN, CMO, CURV, FUS, HELM, EBCM, KURT, LAPD, LAPL, LAPM, LOCC, LOEN, SHAR, WAVS. They all use the arithmetical mean of the local contrast quality. As an alternative to averaging local estimates (since the mean is one of two parameters of the normal distribution), it is proposed to use one of two parameters of the Weibull distribution of the same data – scale or shape.For the experiments, digital images with nonlinear contrast distortion from the available CCID2014 database were used. It contains 15 original images with a size of 768x512 pixels and 655 versions with modified contrast. This database of images contains the average visual quality assessment (Mean Opinion Score, briefly MOS) of each image. Spearman’s rank correlation coefficient was used to determine the correspondence between the visual MOS scores and the studied quantitative measures.As a result of the research, a new quality assessment measure of contrast images in the absence of references is presented. To obtain the estimate, local quality values are calculated by the BREN measure, their set is described by the Weibull distribution, and the scale parameter of the distribution serves as the best numerical estimate of the quality of contrast images. This conclusion is confirmed experimentally, and the proposed measure correlates better than other variants with the subjective assessments of experts.

A No-Reference Image Quality Comprehensive Assessment Method

2020 ◽  
pp. 2154011
Author(s):  
Yuan-Yuan Fan ◽  
Ying-Jun Sang
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Correlation Coefficient ◽  
Image Quality Assessment ◽  
Rank Order ◽  
Comprehensive Assessment ◽  
Assessment Model ◽  
Reference Image ◽  
Human Visual Perception ◽  
Function Model

On the basis of the research status of image quality comprehensive assessment, a no-reference image quality comprehensive assessment function model is proposed in this paper. First, the image quality is classified as contrast, sharpness, and signal-to-noise ratio (SNR), and the interrelation of each assessment index is researched and analyzed; second, the weights in the comprehensive assessment model are studied when only contrast, sharpness, and SNR are changed. Finally, on the basis of studying each kind of distortion separately, and considering the different types of image distortion, we studied how to determine the weights of each index in the comprehensive image quality assessment. The results show that the no-reference image quality comprehensive assessment function model proposed in this paper can better fit human visual perception, and it has a good correlation with Difference Mean Opinion Score (DMOS). Correlation Coefficient (CC) reached 0.8331, Spearman Rank Order Correlation Coefficient (SROCC) reached 0.8206, Mean Absolute Error (MAE) was only 0.0920, Root Mean Square Error (RMSE) was only 0.1122, Outlier Ratio (OR) was only 0.0365. The method proposed in this paper can be applied to photoelectric measurement equipment television system and give an accurate and reliable quality assessment to no reference television images.

scholarly journals Blind Image Quality Assessment Using a CNN and Edge Distortion

2021 ◽  
Vol 35 (4) ◽  
pp. 315-324
Author(s):  
Rajesh Babu Movva ◽  
Raja Kumar Kontham
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Image Quality Assessment ◽  
Subjective Assessment ◽  
Image Features ◽  
Reference Image ◽  
Linear Transformations ◽  
Blind Image Quality Assessment ◽  
Kernel Approach ◽  
Blind Image

The present paper introduces a Convolutional Neural Network (CNN) for the assessment of image quality without a reference image, which comes under the category of Blind Image Quality Assessment models. Edge distortions in the image are characterized as input feature vectors. This approach is in justification of the fact that subjective assessment focusses on image features that emanate from the edges and the boundaries present in the image. The earlier methods were found to use complex transformations on the image to extract the features before training or as a part of the training. The present work uses Prewitt kernel approach to extract the horizontal and vertical edge maps of the training images. These maps are then input to a simple CNN for extracting higher level features using non-linear transformations. The resultant features are mapped to image quality score by regression. The network uses Spatial Pyramid Pooling (SPP) layer to accommodate input images of varying sizes. The present proposed model was tested on popular datasets used in the domain of Image Quality Assessment (IQA). The experimental results have shown that the model competes with the earlier proposed models with simplicity of feature extraction and involvement of minimal complexity.

scholarly journals Contrast-distorted image quality assessment based on curvelet domain features

2021 ◽  
Vol 11 (3) ◽  
pp. 2595
Author(s):  
Ismail Taha Ahmed ◽  
Chen Soong Der ◽  
Baraa Tareq Hammad ◽  
Norziana Jamil
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Image Quality Assessment ◽  
Pearson Correlation ◽  
Poor Performance ◽  
Spatial Domain ◽  
Reference Image ◽  
Quality Metric ◽  
Image Quality Metric ◽  
Fold Cross Validation

Contrast is one of the most popular forms of distortion. Recently, the existing image quality assessment algorithms (IQAs) works focusing on distorted images by compression, noise and blurring. Reduced-reference image quality metric for contrast-changed images (RIQMC) and no reference-image quality assessment (NR-IQA) for contrast-distorted images (NR-IQA-CDI) have been created for CDI. NR-IQA-CDI showed poor performance in two out of three image databases, where the pearson correlation coefficient (PLCC) were only 0.5739 and 0.7623 in TID2013 and CSIQ database, respectively. Spatial domain features are the basis of NR-IQA-CDI architecture. Therefore, in this paper, the spatial domain features are complementary with curvelet domain features, in order to take advantage of the potent properties of the curvelet in extracting information from images such as multiscale and multidirectional. The experimental outcome rely on K-fold cross validation (K ranged 2-10) and statistical test showed that the performance of NR-IQA-CDI rely on curvelet domain features (NR-IQA-CDI-CvT) significantly surpasses those which are rely on five spatial domain features.

Sign in / Sign up

Export Citation Format

Share Document