No-reference noisy image quality assessment incorporating features of entropy, gradient, and kurtosis

作     者：Heng YAO Ben MA Mian ZOU Dong XU Jincao YAO Heng YAO;Ben MA;Mian ZOU;Dong XU;Jincao YAO

作者机构：School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China School of Mechanical EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China Cancer Hospital of the University of Chinese Academy of Sciences(Zhejiang Cancer Hospital)Hangzhou 310000China Institute of Basic Medicine and CancerChinese Academy of SciencesHangzhou 310000China 

出 版 物：《Frontiers of Information Technology & Electronic Engineering》 (信息与电子工程前沿（英文版）)

年 卷 期：2021年第22卷第12期

页      面：1565-1582页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 081002[工学-信号与信息处理] 

基　　金：Project supported by the National Natural Science Foundation of China(No.61702332) the Zhejiang Provincial Natural Science Foundation of China(Nos.LZY21F030001 and LSD19H180001) 

主　　题：Noisy image quality assessment Noise estimation Kurtosis Human visual system Support vector regression 

摘      要：Noise is the most common type of image distortion affecting human visual *** this paper,we propose a no-reference image quality assessment(IQA)method for noisy images incorporating the features of entropy,gradient,and ***,image noise estimation is conducted in the discrete cosine transform domain based on skewness *** the principal component analysis domain,kurtosis feature is obtained by statistically counting the significant differences between images with and without *** addition,both the consistency between the entropy and kurtosis features and the subjective scores are improved by combining them with the gradient *** vector regression is applied to map all extracted features into an integrated scoring *** proposed method is evaluated in three mainstream databases(i.e.,LIVE,TID2013,and CSIQ),and the results demonstrate the superiority of the proposed method according to the Pearson linear correlation coefficient which is the most significant indicator in IQA.