Paper Info
Title
Wavelet weighted blood vessel distortion measure for retinal images.
Abstract
In this paper, a novel wavelet transform based blood vessel distortion measure (WBVDM) is proposed to assess the image quality of blood vessels in the processed retinal images. The wavelet analysis of retinal image shows that different wavelet subbands carry different information about the blood vessels. The WBVDM is defined as the sum of wavelet weighted root of the normalized mean square error of subbands expressed in percentage. The proposed WBVDM is compared with other wavelet based distortion measures such as wavelet mean square error(WMSE), Relative WMSE(Rel WMSE) and root of the normalized WMSE(RNWMSE). The results show that WBVDM performs better in capturing the blood vessel distortion. For distortion in clinically nonsignificant regions, the proposed WBVDM shows a low value of 1.1676 compared to a large mean square error value of 7.9909. The evaluation of correlation using Pearson linear correlation coefficient (PLCC) and Spearman rank order correlation coefficient (SROCC) shows a higher value for the correlation between WBVDM and subjective score. The experimental observations show that WBVDM is able to capture the distortion in blood vessels more effectively and responds weakly to the distortion inherent in the other retinal features.
Year
DOI
Venue
2010
10.1016/j.bspc.2010.06.005
Biomedical Signal Processing and Control
Keywords
Field
DocType
Retinal image,Blood vessel,Decomposition level,Subband distortion,WBVDM,MSSIM
Computer vision,Normalization (statistics),Pattern recognition,Image quality,Mean squared error,Correlation,Artificial intelligence,Retinal,Distortion,Mathematics,Wavelet transform,Wavelet
Journal
Volume
Issue
ISSN
5
4
1746-8094
Citations 
PageRank 
References 
7
0.59
8
Authors
3
Name
Order
Citations
PageRank
S.R. Nirmala1101.99
S. Dandapat226128.51
P. K. Bora35710.33