Share Email Print

Proceedings Paper

Adaptive feature enhancement of retinal vascular images using wavelet-based multiresolution analysis
Author(s): Lei Xu; Xiaoxiang Zheng; Yajun Yu; Hengyi Zhang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The goal of this research is to put forward a high efficient method that can generate clinically useful images with improved visualization of retinal vascular image features. Methods: (1) Multiresolution decomposition of an original retinal image into subband images via 2D wavelet transformation (WT). (2) At S equals 21, the LLMMSE estimate algorithm that is applicable for nonstationary image model is used in wavelet domain to reduce noise. At s equals 22, soft thresholding wavelet shrinkage technique is used in wavelet domain to reduce noise. At s >= 23, semisoft wavelet shrinkage technique is applied in wavelet domain to further reduce noise. (3) Opening of a gray-scale Adaf subband image by a gray-scale circular structuring element can generate a background image. Enhancement is achieved by using this opened image as a unsharp mask and then applying morphological spatial filtering technique to enhance vessel contrast. (4) Reconstruction of retinal image from modified subband images via inverse 2-DWT. Experimental results show that the proposed approach is able to adaptively enhance subtle vascular features, suppress noise and improve global visualization of retinal vascular images.

Paper Details

Date Published: 25 September 1998
PDF: 5 pages
Proc. SPIE 3545, International Symposium on Multispectral Image Processing (ISMIP'98), (25 September 1998); doi: 10.1117/12.323584
Show Author Affiliations
Lei Xu, Zhejiang Univ. (China)
Xiaoxiang Zheng, Zhejiang Univ. (China)
Yajun Yu, Zhejiang Univ. (China)
Hengyi Zhang, Zhejiang Univ. (China)

Published in SPIE Proceedings Vol. 3545:
International Symposium on Multispectral Image Processing (ISMIP'98)
Ji Zhou; Anil K. Jain; Tianxu Zhang; Yaoting Zhu; Mingyue Ding; Jianguo Liu, Editor(s)

© SPIE. Terms of Use
Back to Top