Peer Reviewed

1

DOI

10.17077/omia.1005

Conference Location

Boston, MA, USA

Publication Date

September 2014

Abstract

Registration of multi-modal retinal images is very significant to integrate information gained from different modalities for a reliable diagnosis of retinal diseases by ophthalmologists. However, accurate image registration is a challenging, we propose an algorithm for registration of summed-voxel projection images (SVPIs) with color fundus photographs (CFPs) based on local patch matching. SVPIs are evenly split into 16 local image blocks for extracting matching point pairs by searching local maximization of the similarity function. These matching point pairs are used for a coarse registration and then a search region of feature matching points is redefined for a more accurate registration. The performance of our registration algorithm is tested on a series of datasets including 3 normal eyes and 20 eyes with age-related macular degeneration. The experiment demonstrates that the proposed method can achieve accurate registration results (the average of root mean square error is 128μm).

Rights

Copyright © 2014, Sijie Niu, Qiang Chen, Honglie Shen, Luis de Sisternes, and Daniel L. Rubin.

Included in

Ophthalmology Commons

Share

COinS
 
Sep 14th, 12:00 AM Sep 14th, 12:00 AM

Registration of SD-OCT en-face images with color fundus photographs based on local patch matching

Boston, MA, USA

Registration of multi-modal retinal images is very significant to integrate information gained from different modalities for a reliable diagnosis of retinal diseases by ophthalmologists. However, accurate image registration is a challenging, we propose an algorithm for registration of summed-voxel projection images (SVPIs) with color fundus photographs (CFPs) based on local patch matching. SVPIs are evenly split into 16 local image blocks for extracting matching point pairs by searching local maximization of the similarity function. These matching point pairs are used for a coarse registration and then a search region of feature matching points is redefined for a more accurate registration. The performance of our registration algorithm is tested on a series of datasets including 3 normal eyes and 20 eyes with age-related macular degeneration. The experiment demonstrates that the proposed method can achieve accurate registration results (the average of root mean square error is 128μm).