Retinal vessel centerline extraction using multiscale matched filter and sparse representation-based classifier

Authors:
Bob Zhang;Qin Li;Lei Zhang;Jane You;Fakhri Karray
Affiliations:
Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada;Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong;Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong;Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong;Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada
Venue:
ICMB'10 Proceedings of the Second international conference on Medical Biometrics
Year:
2010

Citing 5
Cited 1

Adaptive Local Thresholding by Verification-Based Multithreshold Probing with Application to Vessel Detection in Retinal Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
An improved matched filter for blood vessel detection of digital retinal images

Computers in Biology and Medicine
Robust Face Recognition via Sparse Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Detection of blood vessels in ophthalmoscope images using MF/ant (matched filter/ant colony) algorithm

Computer Methods and Programs in Biomedicine
Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation

IEEE Transactions on Image Processing

MFCA: matched filters with cellular automata for retinal vessel detection

MICAI'11 Proceedings of the 10th Mexican international conference on Advances in Artificial Intelligence - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Retina located in the back of the eye contains useful information in the diagnosis of certain diseases. By locating a blood vessel's width, color, reflectivity, tortuosity and abnormal branching, one can deduce the existence of these diseases. In order for this to be achieved, blood vessels first need to be extracted from its background in fundus image. In this paper we propose a new method to extract vessels based on Multiscale Production of Matched Filter (MPMF) and Sparse Representation-based Classifier (SRC). First, we locate vessel centerline candidates using multi-scale Gaussian filtering, scale production, double thresholding and centerline detection. Then, the candidates which are centerline pixels are classified with SRC. Particularly, two dictionary elements of vessel and non-vessel are used in the SRC process. Experimental results on two public databases show that the proposed method is good at distinguishing vessel from non-vessel objects and extracting the centerlines of small vessels.