Abstract
In this study, we have introduced an accurate retinal images registration method using affine moment invariants (AMI’s) which are the shape descriptors. First, some closed-boundary regions are extracted in both reference and sensed images. Then, AMI’s are computed for each of those regions. The centers of gravity of three pairs of regions which have the minimum of distances are selected as the control points. The region matching is performed by the distance measurements of AMI’s. The evaluation of region matching is performed by comparing the angles of three triangles which are built on these three-point pairs in reference and sensed images. The parameters of affine transform can be computed using these three pairs of control points. The proposed algorithm is applied on the valid DRIVE database. In general (for the case, each sensed image is produced by rotating, scaling, and translating the reference image with different angles, scale factors, and translation factors), the success rate and accuracy is 95 and 96 %, respectively.
Similar content being viewed by others
References
Hajnal VJ, Hill DLG, Hawkes DJ: Medical Image Registration. CRC LLC, Boca Raton, 2001
Pohl C, Van Genderen JL: Multisensor image fusion in remote sensing: concepts, methods and application. Int J Remote Sens 19:823–854, 1998
Daneshvar S, Ghassemian H: MRI and PET image fusion by combining IHS and retina-inspired models. Inform Fusion 11:114–123, 2010
Patton N, Aslam TM, MacGillivray T, Deary JI, Dhillon B, Eikelboom RH, Yogesan K, Constable IJ: Retinal image analysis: concepts, applications and potential. Prog Retin Eye Res 25:99–127, 2006
Walter T, Massin P, Erginay A, Ordonez R, Jeulin C, Klein JC: Automatic detection of microaneurysms in color fundus images. Med Image Anal 11:555–566, 2007
Yan M, Huang K: A region based algorithm for vessel detection in retinal images. Med Image Comput Comput Assist Interv 1:645–653, 2006
Zhu YM: Mutual information-based registration of temporal and stereo retinal images using constrained optimization. Comput Meth Prog Bio 86:210–215, 2007
Cideciyan AV: Registration of ocular fundus images: an algorithm using cross-correlation of triple invariant image descriptors. IEEE Eng Med Biol 14:52–58, 1995
Cao H: A novel automated approach of multimodality retinal image registration and fusion. A PhD Dissertation, 2008
Chanwimaluang T: Advanced retinal imaging: feature extraction, 2-D registration, and 3-D reconstruction. A PhD Dissertation, 2006
Zitov B, Flusser J, Sroubek F: Image registration: a survey and recent advances. IEEE ICIP, 2005
Li H, Chutatape O: Automated feature extraction in colorretinal images by a model based approach. IEEE T Biomed Eng 51:246–254, 2004
Sinthanayothin C, Boyce JF, Cook HL, Williamson TH: Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images. Br J Ophthalmol 83:902–910, 1999
Foracchia M, Grisan E, Rugger A: Detection of optic disc in retinal images by means of a geometrical model of vessel structure. IEEE T Biomed Eng 23:1189–1195, 2004
Barrett SF, Naess E, Molvik T: Employing the Hough transform to locate the optic disk. Biomed Sci Instrum 37:81–86, 2001
Ibanez MV, Simo A: Bayesian detection of the fovea in eye fundus angiographies. Pattern Recogn Lett 20:229–240, 1999
Hunter A, Lowell J, Steel D, Basu A, Ryder R: Non-linear filtering for vascular segmentation and detection of venous beading. Technical Report University of Durham, 2003
Delibasi KK, Kechriniotis AI, Tsonos C, Assimakis N: Automatic model-based tracing algorithm for vessel segmentation and diameter estimation. Comput Meth Prog Bio 100:108–122, 2010
Gregson PH, Shen Z, Scott RC, Kozousek V: Automated grading of venous beading. Comput Biomed Res 28:291–304, 1995
Akita K, Kuga H: A computer method of understanding ocular fundus images. Pattern Recogn 16:431–443, 1982
Chanwimaluang T, Fransen SR: Hybrid retinal image registration. IEEE T Inf Technol B 10:129–142, 2006
KoláĜ R, Harabiš V: Automatic rigid registration and analysis of colour fundus image in patients with diabetic retinopathy. IFMBE Proceedings 25/11:251–254, 2009
Suk T, Flusser J: Pattern recognition by affine moment invariants. Pattern Recogn 26:167–174, 1993
Suk T, Flusser J: A moment based approach to registration of images with affine geometric distortion. IEEE T Geosci Remote 32:382–387, 1994
Maitra S: Moment invariants. Proc IEEE 67:679–699, 1979
Flusser J, Suk T: Classification of objects by affine moment invariants. UTIA CSAV, Prague, Research Report No. 1736, 1991
Flusse J, Suk T: The independence of the affine moment invariants. Int Workshop on Information Optics, 2006
Rizon M, Yazid H, Saad P, Shakaff AY, Rahman Saad A, Sugisaka M, Szali Y, Rozailan M, Karthigayan M: Object detection using circular Hough transform. Am J Appl Sci 2:1606–1609, 2005
Carlson F: Lecture 10-Hough circle transform
Laliberté F, Gagnon L, Sheng Y: Registration and fusion of retinal images—an evaluation study. IEEE Trans Med Imag 22:661–673, 2003
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Gharabaghi, S., Daneshvar, S. & Sedaaghi, M.H. Retinal Image Registration Using Geometrical Features. J Digit Imaging 26, 248–258 (2013). https://doi.org/10.1007/s10278-012-9501-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10278-012-9501-7