TY - GEN
T1 - A novel no-reference image quality assessment metric based on statistical independence
AU - Chu, Ying
AU - Mou, Xuanqin
AU - Hong, Wei
AU - Ji, Zhen
PY - 2012
Y1 - 2012
N2 - No-reference image quality assessment (NR IQA) has wide applicability to many problems. This paper focuses on the mechanism of divisive normalization transform (DNT) which simulates the behavior of visual cortex neurons to extract the independent components of natural images, analyzes the difference between the statistics of neighboring DNT coefficients of the images of a variety of distortion, and proposes a novel solution for NR IQA metric design. We demonstrate that measuring the statistical independence between neighboring DNT coefficients could provide features useful for quality assessment. The performance of the proposed method is quite satisfactory when it was tested on the popular LIVE, CSIQ and TID2008 databases. The experimental results are fairly competitive with the existing NR IQA metrics.
AB - No-reference image quality assessment (NR IQA) has wide applicability to many problems. This paper focuses on the mechanism of divisive normalization transform (DNT) which simulates the behavior of visual cortex neurons to extract the independent components of natural images, analyzes the difference between the statistics of neighboring DNT coefficients of the images of a variety of distortion, and proposes a novel solution for NR IQA metric design. We demonstrate that measuring the statistical independence between neighboring DNT coefficients could provide features useful for quality assessment. The performance of the proposed method is quite satisfactory when it was tested on the popular LIVE, CSIQ and TID2008 databases. The experimental results are fairly competitive with the existing NR IQA metrics.
KW - Image quality assessment
KW - divisive normalization transform
KW - no-reference
KW - statistical independence
KW - support vector regression
UR - https://www.scopus.com/pages/publications/84874059214
U2 - 10.1109/VCIP.2012.6410790
DO - 10.1109/VCIP.2012.6410790
M3 - 会议稿件
AN - SCOPUS:84874059214
SN - 9781467344050
T3 - 2012 IEEE Visual Communications and Image Processing, VCIP 2012
BT - 2012 IEEE Visual Communications and Image Processing, VCIP 2012
T2 - 2012 IEEE Visual Communications and Image Processing, VCIP 2012
Y2 - 27 November 2012 through 30 November 2012
ER -