Deep Multi-Scale Features Learning for Distorted Image Quality Assessment

被引:24
|
作者
Zhou, Wei [1 ]
Chen, Zhibo [1 ]
机构
[1] Univ Sci & Technol China, CAS Key Lab Technol Geospatial Informat Proc & Ap, Hefei 230027, Peoples R China
关键词
Image quality assessment; deep neural network; multi-scale features; human vision; end-to-end prediction; SIMILARITY;
D O I
10.1109/ISCAS51556.2021.9401285
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Image quality assessment (IQA) aims to estimate human perception based image visual quality. Although existing deep neural networks (DNNs) have shown significant effectiveness for tackling the IQA problem, it still needs to improve the DNN-based quality assessment models by exploiting efficient multi-scale features. In this paper, motivated by the human visual system (HVS) combining multi-scale features for perception, we propose to use pyramid features learning to build a DNN with hierarchical multi-scale features for distorted image quality prediction. Our model is based on both residual maps and distorted images in luminance domain, where the proposed network contains spatial pyramid pooling and feature pyramid from the network structure. Our proposed network is optimized in a deep end-to-end supervision manner. To validate the effectiveness of the proposed method, extensive experiments are conducted on four widely-used image quality assessment databases, demonstrating the superiority of our algorithm.
引用
收藏
页数:5
相关论文
共 50 条
  • [1] No-Reference Image Quality Assessment with Multi-Scale Orderless Pooling of Deep Features
    Varga, Domonkos
    [J]. JOURNAL OF IMAGING, 2021, 7 (07)
  • [2] A Multi-Scale Learning Local Phase and Amplitude Blind Image Quality Assessment for Multiply Distorted Images
    Li, Chaofeng
    Zhang, Yu
    Wu, Xiaojun
    Zheng, Yuhui
    [J]. IEEE ACCESS, 2018, 6 : 64577 - 64586
  • [3] Innovative Approaches in Image Quality Assessment: A Deep Learning-Enabled Multi Level and Multi-Scale Perspective
    Sun, Hai
    [J]. TRAITEMENT DU SIGNAL, 2023, 40 (06) : 2661 - 2670
  • [4] JOINT LEARNING OF DEEP MULTI-SCALE FEATURES AND DIVERSIFIED METRICS FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    Gong, Zhiqiang
    Zhong, Ping
    Yu, Yang
    Shan, Jiaxin
    Hu, Weidong
    [J]. 2017 IEEE 27TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, 2017,
  • [5] Learning Multi-Scale Deep Image Prior for High-Quality Unsupervised Image Denoising
    Jiang, Hao
    Zhang, Qing
    Nie, Yongwei
    Zhu, Lei
    Zheng, Wei-Shi
    [J]. COMPUTER GRAPHICS FORUM, 2022, 41 (07) : 323 - 334
  • [6] A multi-scale approach for pasta quality features assessment
    Diantom, Agoura
    Curti, Elena
    Carini, Eleonora
    Boukid, Fatma
    Mattarozzi, Monica
    Vodovotz, Yael
    Careri, Maria
    Vittadini, Elena
    [J]. LWT-FOOD SCIENCE AND TECHNOLOGY, 2019, 101 : 285 - 292
  • [7] Deep multi-scale attentional features for medical image segmentation
    Poudel, Sahadev
    Lee, Sang-Woong
    [J]. APPLIED SOFT COMPUTING, 2021, 109
  • [8] Adaptive Deep Learning Network With Multi-Scale and Multi-Dimensional Features for Underwater Image Enhancement
    Qiao, Nianzu
    Dong, Lu
    Sun, Changyin
    [J]. IEEE TRANSACTIONS ON BROADCASTING, 2023, 69 (02) : 482 - 494
  • [9] Multi-scale structural similarity for image quality assessment
    Wang, Z
    Simoncelli, EP
    Bovik, AC
    [J]. CONFERENCE RECORD OF THE THIRTY-SEVENTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, VOLS 1 AND 2, 2003, : 1398 - 1402
  • [10] Multi-scale Transformer with Decoder for Image Quality Assessment
    Zhang, Shuai
    Liu, Yutao
    [J]. ARTIFICIAL INTELLIGENCE, CICAI 2023, PT I, 2024, 14473 : 220 - 231