|Table of Contents|

Automatic Fundus Images Registration and Mosaic Based on Speeded up Robust Features


Research Field:
Publishing date:


Automatic Fundus Images Registration and Mosaic Based on Speeded up Robust Features
WANG Yu-liangLIAO Wen-heSHEN Jian-xin
College of Mechanical & Electrical Engineering,Nanjing University of Aeronautics and Astronautics, Nanjing 210016,China
speeded up robust features image registration image fusion image mosaic fundus images
In order to overcome the characteristics of low contrast,non-uniform illumination,limited field of view(FOV),and the geometric distortion between different FOVs of the fundus images,an automatic fundus image registration and mosaic algorithm based on speeded up robust features(SURF) is presented.Fundus images are enhanced by homomorphism filtering,and the SURF features in effective FOVs are extracted and described using vector to determine the matching feature point pairs between images.Outlier point pairs are rejected using RANSAC algorithm employing a perspective model,and transformation matrixes are computed according to the matching point pairs of surrounding FOV images to the central in turn,image registration and image fusion are implemented to get fundus panoramic image finally.The automatic registration and mosaic results of multiple FOV images obtained by fundus camera show that the algorithm is robust,the stability with registration accuracy reaches pixel level and the high-precision automatic fundus image mosaic can be achieved.


[1] Brown L G. A survey of image registration techniques [J]. ACM Computing Surveys, 1992, 24( 4) : 325-376.
[2] Zitová B,Flusser J. Image registration methods: A survey [J]. Image and Vision Computing,2003,21( 11) : 977-1000.
[3] Can A,Stewart C V,Roysam B, et al. A feature-based, robust,hierarchical algorithm for registering pairs of images of the curved human retina [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24( 3) : 347-364.
[4] Ryan N,Heneghan C,De Chazal P. Registration of digital retinal images using landmark correspondence by expectation maximization[J]. Image and Vision Computing, 2004, 22( 11) : 883-898.
[5] 李忠新,茅耀斌,王执铨. 基于角点匹配的鲁棒图像镶嵌方法[J]. 南京理工大学学报,2007,31 ( 3) : 359-363.
[6] Yang Gehua,Stewart C V,Sofka M,et al. Registration of challenging image pairs: Initialization,estimation, and decision [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29 ( 11 ) : 1973-1989.
[7] Lee S,Reinhardt J M,Cattin P C, et al. Objective and expert- independent validation of retinal image registration algorithms by a projective imaging distortion model [J]. Medical Image Analysis, 2010, 14( 4) : 539-549.
[8] 王玉亮,沈建新,廖文和. 基于SIFT 特征的眼底图像自动拼接[J]. 中国图象图形学报,2011,16( 4) : 654-659.
[9] Bay H,Tuytelaars T,Van Gool L. SURF: Speeded up robust features [A]. Computer Vision-ECCV 2006,9 th European Conference on Computer Vision[C]. Berlin, Germany: Springer Verlag, 2006: 404-417.
[10] Friedman J H,Bentley J L,Finkel R A. An algorithm for finding best matches in logarithmic expected time [J]. ACM Transactions on Mathematical Software, 1977,3 ( 3) : 209-226.
[11] Lowe D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60( 2) : 91-110.
[12] Fishchler M A,Bolles R C. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography [J]. Communi-cations of ACM, 1981, 24( 6) : 381-395.


Last Update: 2012-10-12