Retinal image registration using log-polar transform and robust description of bifurcation points. (April 2021)

• Record Type: Journal Article
• Authors: Saha, Sajib; Rahaman, G.M. Atiqur; Islam, Tazul; Akter, Masuma; Frost, Shaun; Kanagasingam, Yogesan
• Is Part Of: Biomedical signal processing and control. Volume 66(2021)
• Publication Date: 2021-04
• Subjects: Image registration -- Color fundus photographs -- Local feature descriptor -- Log-polar transform -- Retinal image registration; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102424
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A novel descriptor named Combined Local Haar of Bifurcation points (CLHB) is proposed in retinal imaging context. An innovative retinal image registration method, which is better than the state-of-the-art methods, is proposed. Extensive experiments on public and private datasets are conducted. The proposed method is found 2∼3% more accurate than the best performing method in the context. Abstract: Registration of retinal image is a crucial and fundamental step in several medical diagnoses. In this paper we propose an innovative method for retinal image registration. The method applies log-polar transform to approximate the difference in scale and orientation among images. A novel descriptor named Combined Local Haar of Bifurcation points (CLHB) is proposed for robust description and precise matching of retinal bifurcation and cross-over points. Experiments are performed on retinal image registration datasets collected from private and public sources and consisting of a total of 484 fundus photographs (i.e. 242 pairs). The proposed method has been compared with the state-of-the-art Generalized Dual-Bootstrap Iterative Closest Point (GDP ICP), Hernandez-Matas et al., Saha et al., and Chen et al.'s methods and has been found to outperform them with a clear margin. On the publicly available FIRE dataset, our proposed method is found 2% more accurate than the best performing Saha et al.'s method. On the private dataset the method is found to be about 3% more accurate than the best performing method.