Open AccessLocal descriptor for retinal fundus image registration
Author(s) -
Ramli Roziana,
Idris Mohd Yamani Idna,
Hasikin Khairunnisa,
Karim Noor Khairiah A.,
Wahab Ainuddin Wahid Abdul,
Ahmedy Ismail,
Ahmedy Fatimah,
Arof Hamzah
Publication year - 2020
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/iet-cvi.2019.0623
Subject(s) - scale invariant feature transform , artificial intelligence , image registration , pattern recognition (psychology) , feature extraction , computer vision , feature (linguistics) , histogram , computer science , mathematics , rotation (mathematics) , invariant (physics) , image (mathematics) , linguistics , philosophy , mathematical physics
A feature‐based retinal image registration (RIR) technique aligns multiple fundus images and composed of pre‐processing, feature point extraction, feature descriptor, matching and geometrical transformation. Challenges in RIR include difference in scaling, intensity and rotation between images. The scale and intensity differences can be minimised with consistent imaging setup and image enhancement during the pre‐processing, respectively. The rotation can be addressed with feature descriptor method that robust to varying rotation. Therefore, a feature descriptor method is proposed based on statistical properties (FiSP) to describe the circular region surrounding the feature point. From the experiments on public Fundus Image Registration dataset, FiSP established 99.227% average correct matches for rotations between 0° and 180°. Then, FiSP is paired with Harris corner, scale‐invariant feature transform (SIFT), speeded‐up robust feature (SURF), Ghassabi's and D‐Saddle feature point extraction methods to assess its registration performance and compare with the existing feature‐based RIR techniques, namely generalised dual‐bootstrap iterative closet point (GDB‐ICP), Harris‐partial intensity invariant feature descriptor (PIIFD), Ghassabi's–SIFT, H‐M 16, H‐M 17 and D‐Saddle–histogram of oriented gradients (HOG). The combination of SIFT–FiSP registered 64.179% of the image pairs and significantly outperformed other techniques with mean difference between 25.373 and 60.448% ( p = <0.001*).