Image Quality Assessment Based on Low Order Moment Features

Leida LI  Hancheng ZHU  Gaobo YANG  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E97-A   No.2   pp.538-542
Publication Date: 2014/02/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E97.A.538
Print ISSN: 0916-8508
Type of Manuscript: Special Section LETTER (Special Section on Image Media Quality)
Category: 
Keyword: 
image quality assessment,  full-reference,  orthogonal moment,  

Full Text: PDF>>
Buy this Article




Summary: 
This letter presents a new image quality metric using low order discrete orthogonal moments. The moment features are extracted in a block manner and the relative moment differences (RMD) are computed. A new exponential function based on RMD is proposed to generate the quality score. The performance of the proposed method is evaluated on public databases. Experimental results and comparisons demonstrate the efficiency of the proposed method.