Gaussian Process-based Feature-Enriched Blind Image Quality Assessment

被引：0
|
作者：
Khalid H. [1 ]
Ali D.M. [1 ]
Ahmed N. [2 ]
机构：
[1] Department of Electrical Engineering, University of Engineering and Technology, Postal Code: 54890, Lahore
[2] Department of Computer Engineering, University of Engineering and Technology, Postal Code: 54890, Lahore
来源：
Journal of Visual Communication and Image Representation | 2021年 / 77卷
关键词：
Blind image quality assessment (BIQA); Feature selection; Gaussian process regression; Image quality assessment (IQA); Natural scene statistics; No-reference (NR);
D O I：
10.1016/j.jvcir.2021.103092
中图分类号：
学科分类号：
摘要：
The objective of blind-image quality assessment (BIQA) research is the prediction of perceptual quality of images, without reference information. The human's perceptual assessment of quality of an image is the backbone of BIQA research. Therefore, human-provided, mean opinion score (perceptual quality) has been analyzed in detail, and it has been observed to follow the Gaussian distribution and thus can be ideally modeled by the same. In this paper, we have proposed an integrated two-stage Gaussian process-based hybrid-feature selection algorithm for the BIQA problem. Moreover, a new consolidated feature set (obtained from the proposed algorithm), consisting of momentous Natural Scene Statistics (NSS)-based features is used in combination with the Gaussian process regression algorithm for the design of a new blind-image quality evaluator, referred to as GPR-BIQA. The proposed evaluator is tested on eight IQA legacy databases, and it is found that the proposed evaluator proficiently correlate with the human opinion, and outperformed a substantial number of existing approaches. © 2021 Elsevier Inc.
引用
收藏
相关论文
共 50 条
  • [21] A Feature-Enriched Deep Convolutional Neural Network for JPEG Image Compression Artifacts Reduction and Its Applications
    Chen, Honggang
    He, Xiaohai
    Yang, Hong
    Qing, Linbo
    Teng, Qizhi
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (01) : 430 - 444
  • [22] Gaussian Process-Based Refinement of Dispersion Corrections
    Proppe, Jonny
    Gugler, Stefan
    Reiher, Markus
    JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2019, 15 (11) : 6046 - 6060
  • [23] Optimization Employing Gaussian Process-Based Surrogates
    Preuss, R.
    von Toussaint, U.
    BAYESIAN INFERENCE AND MAXIMUM ENTROPY METHODS IN SCIENCE AND ENGINEERING, MAXENT 37, 2018, 239 : 275 - 284
  • [24] Gaussian Process-Based Inferential Control System
    Abusnina, Ali
    Kudenko, Daniel
    Roth, Rolf
    INTERNATIONAL JOINT CONFERENCE SOCO'14-CISIS'14-ICEUTE'14, 2014, 299 : 115 - 124
  • [25] Advanced drone-based weed detection using feature-enriched deep learning approach
    Rehman, Mobeen Ur
    Eesaar, Hassan
    Abbas, Zeeshan
    Seneviratne, Lakmal
    Hussain, Irfan
    Chong, Kil To
    KNOWLEDGE-BASED SYSTEMS, 2024, 305
  • [26] HOMOGENEITY BASED BLIND NOISY IMAGE QUALITY ASSESSMENT
    Huang, Xiaotong
    Chen, Li
    Tian, Jing
    Zhang, Xiaolong
    Fu, Xiaowei
    2013 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC 2013), 2013, : 2963 - 2967
  • [27] A no-reference image quality assessment model based on neighborhood component analysis and Gaussian process
    Rajevenceltha, J.
    Gaidhane, Vilas H.
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2024, 98
  • [28] Blind Image Quality Assessment Based on Perceptual Comparison
    Li, Aobo
    Wu, Jinjian
    Liu, Yongxu
    Li, Leida
    Dong, Weisheng
    Shi, Guangming
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 9671 - 9682
  • [29] A New Blind Image Quality Assessment Based on Pairwise
    Jiang, Jianbin
    Zhou, Yue
    He, Liming
    NEURAL INFORMATION PROCESSING, ICONIP 2016, PT IV, 2016, 9950 : 609 - 617
  • [30] Blind Image Quality Assessment Based on Mutual Information
    Liu, Bao
    Liu, Li-Xiong
    Dong, Hong-Ping
    Lin, Yong-Gang
    ELECTRONICS, COMMUNICATIONS AND NETWORKS V, 2016, 382 : 127 - 136
12345