scholarly journals Multivariate Statistical Approach to Image Quality Tasks

2018 ◽  
Vol 4 (10) ◽  
pp. 117
Author(s):  
Praful Gupta ◽  
Christos Bampis ◽  
Jack Glover ◽  
Nicholas Paulter ◽  
Alan Bovik
Keyword(s):  
Image Quality ◽  
Image Quality Assessment ◽  
Multivariate Model ◽  
Reference Image ◽  
Natural Image ◽  
Local Contrast ◽  
Natural Scene Statistics ◽  
Distorted Image ◽  
Multiple Imaging ◽  
Contrast Normalization

Many existing natural scene statistics-based no reference image quality assessment (NR IQA) algorithms employ univariate parametric distributions to capture the statistical inconsistencies of bandpass distorted image coefficients. Here, we propose a multivariate model of natural image coefficients expressed in the bandpass spatial domain that has the potential to capture higher order correlations that may be induced by the presence of distortions. We analyze how the parameters of the multivariate model are affected by different distortion types, and we show their ability to capture distortion-sensitive image quality information. We also demonstrate the violation of Gaussianity assumptions that occur when locally estimating the energies of distorted image coefficients. Thus, we propose a generalized Gaussian-based local contrast estimator as a way to implement non-linear local gain control, which facilitates the accurate modeling of both pristine and distorted images. We integrate the novel approach of generalized contrast normalization with multivariate modeling of bandpass image coefficients into a holistic NR IQA model, which we refer to as multivariate generalized contrast normalization (MVGCN). We demonstrate the improved performance of MVGCN on quality-relevant tasks on multiple imaging modalities, including visible light image quality prediction and task success prediction on distorted X-ray images.

No-reference image quality assessment with center-surround based natural scene statistics

2017 ◽  
Vol 77 (16) ◽  
pp. 20731-20751 ◽  
Author(s):  
Jun Wu ◽  
Zhaoqiang Xia ◽  
Huifang Li ◽  
Kezheng Sun ◽  
Ke Gu ◽  
...  
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Image Quality Assessment ◽  
Reference Image ◽  
Natural Scene ◽  
Natural Scene Statistics

scholarly journals Total Variation Based Perceptual Image Quality Assessment Modeling

2014 ◽  
Vol 2014 ◽  
pp. 1-10
Author(s):  
Yadong Wu ◽  
Hongying Zhang ◽  
Ran Duan
Keyword(s):  
Image Quality ◽  
Visual System ◽  
Quality Assessment ◽  
Total Variation ◽  
Human Visual System ◽  
Image Quality Assessment ◽  
Reference Image ◽  
Distorted Image ◽  
Perceptual Image Quality ◽  
Tv Model

Visual quality measure is one of the fundamental and important issues to numerous applications of image and video processing. In this paper, based on the assumption that human visual system is sensitive to image structures (edges) and image local luminance (light stimulation), we propose a new perceptual image quality assessment (PIQA) measure based on total variation (TV) model (TVPIQA) in spatial domain. The proposed measure compares TVs between a distorted image and its reference image to represent the loss of image structural information. Because of the good performance of TV model in describing edges, the proposed TVPIQA measure can illustrate image structure information very well. In addition, the energy of enclosed regions in a difference image between the reference image and its distorted image is used to measure the missing luminance information which is sensitive to human visual system. Finally, we validate the performance of TVPIQA measure with Cornell-A57, IVC, TID2008, and CSIQ databases and show that TVPIQA measure outperforms recent state-of-the-art image quality assessment measures.

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.

scholarly journals NO-REFERENCE IMAGE QUALITY ASSESSMENT FOR ZY3 IMAGERY IN URBAN AREAS USING STATISTICAL MODEL

2016 ◽  
Vol XLI-B3 ◽  
pp. 949-954 ◽  
Author(s):  
Y. Zhang ◽  
W.H. Cui ◽  
F. Yang ◽  
Z.C. Wu
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Urban Areas ◽  
Satellite Images ◽  
Image Quality Assessment ◽  
Reference Image ◽  
Atmospheric Conditions ◽  
Natural Scene Statistics ◽  
The Impact

More and more high-spatial resolution satellite images are produced with the improvement of satellite technology. However, the quality of images is not always satisfactory for application. Due to the impact of complicated atmospheric conditions and complex radiation transmission process in imaging process the images often suffer deterioration. In order to assess the quality of remote sensing images over urban areas, we proposed a general purpose image quality assessment methods based on feature extraction and machine learning. We use two types of features in multi scales. One is from the shape of histogram the other is from the natural scene statistics based on Generalized Gaussian distribution (GGD). A 20-D feature vector for each scale is extracted and is assumed to capture the RS image quality degradation characteristics. We use SVM to learn to predict image quality scores from these features. In order to do the evaluation, we construct a median scale dataset for training and testing with subjects taking part in to give the human opinions of degraded images. We use ZY3 satellite images over Wuhan area (a city in China) to conduct experiments. Experimental results show the correlation of the predicted scores and the subjective perceptions.

A New Image Distortion Measure Based on Natural Scene Statistics Modeling

2012 ◽  
Vol 2 (1) ◽  
pp. 1-15
Author(s):  
Abdelkaher Ait Abdelouahad ◽  
Mohammed El Hassouni ◽  
Hocine Cherifi ◽  
Driss Aboutajdine
Keyword(s):  
Quality Assessment ◽  
Image Quality Assessment ◽  
Reference Image ◽  
Support Vector ◽  
Natural Scene ◽  
Natural Scene Statistics ◽  
Intrinsic Mode Functions ◽  
Distorted Image ◽  
Leibler Divergence ◽  
Gaussian Density

In the field of Image Quality Assessment (IQA), this paper examines a Reduced Reference (RRIQA) measure based on the bi-dimensional empirical mode decomposition. The proposed measure belongs to Natural Scene Statistics (NSS) modeling approaches. First, the reference image is decomposed into Intrinsic Mode Functions (IMF); the authors then use the Generalized Gaussian Density (GGD) to model IMF coefficients distribution. At the receiver side, the same number of IMF is computed on the distorted image, and then the quality assessment is done by fitting error between the IMF coefficients histogram of the distorted image and the GGD estimate of IMF coefficients of the reference image, using the Kullback Leibler Divergence (KLD). In addition, the authors propose a new Support Vector Machine-based classification approach to evaluate the performances of the proposed measure instead of the logistic function-based regression. Experiments were conducted on the LIVE dataset.

AN IMAGE QUALITY METRIC BASED ON BIOLOGICALLY INSPIRED FEATURE MODEL

2011 ◽  
Vol 11 (02) ◽  
pp. 265-279 ◽  
Author(s):  
CHENG DENG ◽  
JIE LI ◽  
YIFAN ZHANG ◽  
DONGYU HUANG ◽  
LINGLING AN
Keyword(s):  
Image Quality ◽  
Image Quality Assessment ◽  
Similarity Index ◽  
Saliency Map ◽  
Feature Weighting ◽  
Feature Model ◽  
Perceptual Quality ◽  
Reference Image ◽  
Biologically Inspired ◽  
Distorted Image

Objective image quality assessment (IQA) metrics have been widely applied to imaging systems to preserve and enhance the perceptual quality of images being processed and transmitted. In this paper, we present a novel IQA metric based on biologically inspired feature model (BIFM) and structural similarity index (SSIM). The SSIM index map is first generated through the well-known IQA metric SSIM between the reference image and the distorted image. Then, saliency map of the distorted image is extracted via BIF to define the most salient image locations. Finally, according to the saliency map, a feature weighting model is employed to define the different weights for the different samples in the SSIM index map. Experimental results confirm that the proposed IQA metric improves the performance over PSNR and SSIM under various distortion types in terms of different evaluation criteria.

Sign in / Sign up

Export Citation Format

Share Document