Next Article in Journal
Nutritional and Health Potential of Probiotics: A Review
Previous Article in Journal
Analysis of Heat and Mass Transfer Features of Hybrid Casson Nanofluid Flow with the Magnetic Dipole Past a Stretched Cylinder
Previous Article in Special Issue
Robustness of PET Radiomics Features: Impact of Co-Registration with MRI
Article

Fundus Image Registration Technique Based on Local Feature of Retinal Vessels

1
Department of Computer System and Technology, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur 50603, Malaysia
2
Department of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur 50603, Malaysia
3
Regenerative Medicine Cluster/Imaging Unit, Advanced Medical & Dental Institute, Universiti Sains Malaysia, Kepala Batas 13200, Malaysia
*
Authors to whom correspondence should be addressed.
Academic Editors: Alessandro Stefano, Albert Comelli and Federica Vernuccio
Appl. Sci. 2021, 11(23), 11201; https://doi.org/10.3390/app112311201
Received: 30 September 2021 / Revised: 18 November 2021 / Accepted: 19 November 2021 / Published: 25 November 2021
Feature-based retinal fundus image registration (RIR) technique aligns fundus images according to geometrical transformations estimated between feature point correspondences. To ensure accurate registration, the feature points extracted must be from the retinal vessels and throughout the image. However, noises in the fundus image may resemble retinal vessels in local patches. Therefore, this paper introduces a feature extraction method based on a local feature of retinal vessels (CURVE) that incorporates retinal vessels and noises characteristics to accurately extract feature points on retinal vessels and throughout the fundus image. The CURVE performance is tested on CHASE, DRIVE, HRF and STARE datasets and compared with six feature extraction methods used in the existing feature-based RIR techniques. From the experiment, the feature extraction accuracy of CURVE (86.021%) significantly outperformed the existing feature extraction methods (p ≤ 0.001*). Then, CURVE is paired with a scale-invariant feature transform (SIFT) descriptor to test its registration capability on the fundus image registration (FIRE) dataset. Overall, CURVE-SIFT successfully registered 44.030% of the image pairs while the existing feature-based RIR techniques (GDB-ICP, Harris-PIIFD, Ghassabi’s-SIFT, H-M 16, H-M 17 and D-Saddle-HOG) only registered less than 27.612% of the image pairs. The one-way ANOVA analysis showed that CURVE-SIFT significantly outperformed GDB-ICP (p = 0.007*), Harris-PIIFD, Ghassabi’s-SIFT, H-M 16, H-M 17 and D-Saddle-HOG (p ≤ 0.001*). View Full-Text
Keywords: image registration; fundus image; feature extraction image registration; fundus image; feature extraction
Show Figures

Figure 1

MDPI and ACS Style

Ramli, R.; Hasikin, K.; Idris, M.Y.I.; A. Karim, N.K.; Wahab, A.W.A. Fundus Image Registration Technique Based on Local Feature of Retinal Vessels. Appl. Sci. 2021, 11, 11201. https://doi.org/10.3390/app112311201

AMA Style

Ramli R, Hasikin K, Idris MYI, A. Karim NK, Wahab AWA. Fundus Image Registration Technique Based on Local Feature of Retinal Vessels. Applied Sciences. 2021; 11(23):11201. https://doi.org/10.3390/app112311201

Chicago/Turabian Style

Ramli, Roziana, Khairunnisa Hasikin, Mohd Y.I. Idris, Noor K. A. Karim, and Ainuddin W.A. Wahab 2021. "Fundus Image Registration Technique Based on Local Feature of Retinal Vessels" Applied Sciences 11, no. 23: 11201. https://doi.org/10.3390/app112311201

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop