Performance Validation and Analysis for Multi-Method Fusion Based Image Quality Metrics in A New Image Database

被引:0
|
作者
Ma, Xiaoyu [1 ]
Jiang, Xiuhua [1 ]
Pan, Da [1 ]
机构
[1] Commun Univ China, Commun & Informat Technol Sch, Beijing 10024, Peoples R China
关键词
full reference image quality assessment; image database; multi-method fusion; INFORMATION; SIMILARITY;
D O I
暂无
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
Considering that there is no single full reference image quality assessment method that could give the best performance in all situations, some multi-method fusion metrics were proposed. Machine learning techniques are often involved in such multi-method fusion metrics so that its output would be more consistent with human visual perceptions. On the other hand, the robustness and generalization ability of these multi-method fusion metrics are questioned because of the scarce of images with mean opinion scores. In order to comprehensively validate whether or not the generalization ability of such multi-method fusion IQA metrics are satisfying, we construct a new image database which contains up to 60 reference images. The newly built image database is then used to test the generalization ability of different multi-method fusion IQA metrics. Cross database validation experiment indicates that in our new image database, the performances of all the multi-method fusion IQA metrics have no statistical significant different with some single-method IQA metrics such as FSIM and MAD. In the end, a thorough analysis is given to explain why the performance of multi-method fusion IQA framework drop significantly in cross database validation.
引用
收藏
页码:147 / 161
页数:15
相关论文
共 50 条
  • [41] New Image Quality Approach Based on Decision Fusion
    Liu, Mingna
    Yang, Xin
    FIFTH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY, VOL 4, PROCEEDINGS, 2008, : 10 - 14
  • [42] Multi-focus Image Performance Evaluation Method Based on the Extraction and Combination of Multiple Metrics
    Li, Weitong
    Cheng, Yu
    Sun, Yuehui
    Xu, Shaoqiu
    2017 13TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY (CIS), 2017, : 130 - 134
  • [43] Assessing the Performance of Image Quality Assessment Metrics
    Alotaibi, Theyab
    Bourennani, Farid
    Khan, Ishtiaq Rasool
    IEEE MMSP 2021: 2021 IEEE 23RD INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP), 2021,
  • [44] A review of image fusion: Methods, applications and performance metrics
    Singh, Simrandeep
    Singh, Harbinder
    Bueno, Gloria
    Deniz, Oscar
    Singh, Sartajvir
    Monga, Himanshu
    Hrisheekesha, P. N.
    Pedraza, Anibal
    DIGITAL SIGNAL PROCESSING, 2023, 137
  • [45] QUALITY ESTIMATION BASED MULTI-FOCUS IMAGE FUSION
    Guan, Jingwei
    Cham, Wai-kuen
    2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 1987 - 1991
  • [46] A new method for multi-view range image fusion
    Zhang, ZH
    Peng, X
    Shi, WQ
    Hu, XT
    OPTICAL MEASUREMENT AND NONDESTRUCTIVE TESTING: TECHNIQUES AND APPLICATIONS, 2000, 4221 : 115 - 119
  • [47] Single Image Defogging Method Based on Image Patch Decomposition and Multi-Exposure Image Fusion
    Liu, Qiuzhuo
    Luo, Yaqin
    Li, Ke
    Li, Wenfeng
    Chai, Yi
    Ding, Hao
    Jiang, Xinghong
    FRONTIERS IN NEUROROBOTICS, 2021, 15
  • [48] A new spatial projection image fusion method based on Gaussian image cube
    Shao, Zhenfeng
    Liu, Jun
    Li, Deren
    Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University, 2010, 35 (10): : 1207 - 1211
  • [49] Fusion of panchromatic image and multi-spectral image based on SVR and Bayesian method
    Liang, D. (dliang@ahu.edu.cn), 1600, Zhejiang University (47):
  • [50] An image fusion method of multi-scale image based on HMM and genetic algorithms
    Jiang, Zetao
    Wu, Donghui
    Journal of Computational Information Systems, 2015, 11 (12): : 4367 - 4374