An efficient approach for robust multimodal 3 retinal image registration based on UR - SIFT 4 features and PIIFD descriptors

11 Existing algorithms based on scale invariant feature transform (SIFT) and Harris corners such as edge-driven 12 dual-bootstrap iterative closest point and Harris-partial intensity invariant feature descriptor (PIIFD) respectivley have 13 been shown to be robust in registering multimodal retinal images. However, they fail to register color retinal 14 images with other modalities in the presence of large content or scale changes. Moreover, the approaches need 15 preprocessing operations such as image resizing to do well. This restricts the application of image registration for 16 further analysis such as change detection and image fusion. Motivated by the need for efficient registration of 17 multimodal retinal image pairs, this paper introduces a novel integrated approach which exploits features of 18 uniform robust scale invariant feature transform (UR-SIFT) and PIIFD. The approach is robust against low content 19 contrast of color images and large content, appearance, and scale changes between color and other retinal image 20 modalities like the fluorescein angiogram. Due to low efficiency of standard SIFT detector for multimodal images, 21 the UR-SIFT algorithm extracts high stable and distinctive features in the full distribution of location and scale in 22 images. Then, feature points are adequate and repeatable. Moreover, the PIIFD descriptor is symmetric to contrast, 23 which makes it suitable for robust multimodal image registration. After the UR-SIFT feature extraction and the PIIFD 24 descriptor generation in images, an initial cross-matching process is performed and followed by a mismatch 25 elimination algorithm. Our dataset consists of 120 pairs of multimodal retinal images. Experiment results show the 26 outperformance of the UR-SIFT-PIIFD over the Harris-PIIFD and similar algorithms in terms of efficiency and 27 positional accuracy.