A-RANSAC: Adaptive random sample consensus method in multimodal retinal image registration. (August 2018)

• Record Type: Journal Article
• Authors: Hossein-Nejad, Zahra; Nasri, Mehdi
• Is Part Of: Biomedical signal processing and control. Volume 45(2018)
• Page Start: 325
• Page End: 338
• Publication Date: 2018-08
• Subjects: Angiographic imaging -- Image registration -- Retinal images -- SIFT -- RANSAC; 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.2018.06.002
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: The paper proposes an adaptive RANSAC method which optimizes Root Mean Square and removed matches simultaneously. SAR-SIFT method is used for feature extraction and used as image descriptor. The performance of the proposed method is evaluated with classical evaluation criteria, in addition to the new criteria of SITMMR and SITMMC. The method applied on multimodal retinal images including standard and real clinical databases, and its superiority is shown in experiments. Abstract: In this paper, an adaptive Random Sample Consensus (A-RANSAC) method is proposed for multimodal retinal image registration. In this method, the features of two various images from images taken with different modalities such as FA (Fluorescein angiography) and RF (Red free) are extracted using a modified version of Scale Invariant Feature Transform method (SIFT) called SAR-SIFT which is originally used for Synthetic Aperture Radar images. Then, the matching performance between these images is enhanced using the proposed A-RANSAC. In the A-RANSAC method, the threshold value is chosen so that the Root Mean Square Error (RMSE) and the number of removed matches are optimized simultaneously. The efficiency of the proposed method has been investigated in other modes such as high resolution and low-quality retinal image registration in addition to multimodal registration. The simulation results on several retinal image datasets show that the proposed method improves the precision matching by 9.89% and rate of success by 25% on the average compared to the SAR-SIFT method.