Real distorted images quality assessment based on multi-layer visual perception mechanism and high-level semantics

被引:4
|
作者
Wang, Xiaohong [1 ]
Pang, Yunjie [1 ]
Ma, Xiangcai [2 ]
机构
[1] Univ Shanghai Sci & Technol, Shanghai 200093, Peoples R China
[2] Shanghai Publishing & Printing Coll, Shanghai 200093, Peoples R China
关键词
IQA; Real distorted; K-means; High-level semantics; NETWORKS;
D O I
10.1007/s11042-020-09222-9
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Most of the existing image quality assessment (IQA) methods are directed to artificially synthesized distorted images, in which the types and characteristics of distortion are different from those in the real world. In view of the fact that the existing non-reference IQA methods can not accurately evaluate the quality of the real distortion image, combined with the theoretical analysis of multi-layer visual perception mechanism, we propose a real image distortion IQA method based on image underlying features and high-level semantics. Considering non-linear hierarchical structure of human visual perception, firstly, k-means clustering algorithm is performed according to the underlying feature indexs of the image so that the used image database can be divided into several groups, which aims to improve the accuracy of predicted quality score. Secondly, the deep convolutional neural network (DCNN) is used to extract the first-grade high-level semantic features in each group. Then, second-grade high-level semantic features that can provide better representation of image features are obtained by performing multiple statistical functions on first-grade high-level semantics. Besides, we establish an effective high-capacity regressor with high-level semantics and subjective mean opinion scores (MOS) values of the human eyes. The experimental results show that the proposed model on the KonIQ-10 k image database can predict the quality score effectively and achieve a high consistency with the corresponding MOS value, which is helpful for the subsequent image enhancement.
引用
收藏
页码:25905 / 25920
页数:16
相关论文
共 39 条
  • [31] A high-precision method evaluating color quality of Sichuan Dark Tea based on colorimeter combined with multi-layer perceptron
    Zou Yao
    Ma Wanjun
    Tang Qian
    Xu Wei
    Tan Liqiang
    Han Deyang
    Tian Yun
    Yuan Yue
    JOURNAL OF FOOD PROCESS ENGINEERING, 2020, 43 (08)
  • [32] Remote sensory assessment of beer quality based on visual perception of foamability and biometrics compared to standard emotional responses from affective images
    Viejo, Claudia Gonzalez
    Fuentes, Sigfredo
    De Anda-Lobo, Irma C.
    Hernandez-Brenes, Carmen
    FOOD RESEARCH INTERNATIONAL, 2022, 156
  • [33] Single-frame super-resolution by a cortex based mechanism using high level visual features in natural images
    Kursun, O
    Favorov, O
    SIXTH IEEE WORKSHOP ON APPLICATIONS OF COMPUTER VISION, PROCEEDINGS, 2002, : 112 - 117
  • [34] A filament-level analysis on failure mechanism and ballistic limit of real-size multi-layer 2D woven fabrics under FSP impact
    Ma, Ying
    Dippolito, Mario
    Miao, Yuyang
    Wang, Youqi
    TEXTILE RESEARCH JOURNAL, 2021, 91 (23-24) : 2896 - 2910
  • [35] No-Reference Image Quality Assessment of Magnetic Resonance images with multi-level and multi-model representations based on fusion of deep architectures
    Stepien, Igor
    Oszust, Mariusz
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 123
  • [36] A Single Image High-Perception Super-Resolution Reconstruction Method Based on Multi-layer Feature Fusion Model with Adaptive Compression and Parameter Tuning
    Zhang, Rui
    Ren, Wenyu
    Pan, Lihu
    Bai, Xiaolu
    Li, Ji
    NEURAL PROCESSING LETTERS, 2024, 56 (04)
  • [37] Improve Oil Recovery Mechanism of Multi-Layer Cyclic Alternate Injection and Production for Mature Oilfield at Extra-High Water Cut Stage Using Visual Physical Simulation Experiment
    Zhao, Lun
    Wang, Jincai
    Fu, Libing
    Chen, Li
    Jia, Zhihao
    ENERGIES, 2023, 16 (03)
  • [38] Fusion of Low-Quality Visible and Infrared Images Based on Multi-Level Latent Low-Rank Representation Joint With Retinex Enhancement and Multi-Visual Weight Information
    Pan, Qiaoying
    Zhao, Liaoying
    Chen, Shuhan
    Li, Xiaorun
    IEEE ACCESS, 2022, 10 : 2140 - 2153
  • [39] Two-stage stochastic operation considering day-ahead and real-time scheduling of microgrids with high renewable energy sources and electric vehicles based on multi-layer energy management system
    Azarhooshang, Alireza
    Sedighizadeh, Davoud
    Sedighizadeh, Mostafa
    ELECTRIC POWER SYSTEMS RESEARCH, 2021, 201