Automatic detection of multiple oriented blood vessels in retinal images英文文献资料.docVIP

J. Biomedical Science and Engineering, 2010, 3, 101-107 JBiSE doi:10.4236/jbise.2010.31015 Published Online January 2010 (http://www.SciRP.org/journal/jbise/). Automatic detection of multiple oriented blood vessels in retinal images P. C. Siddalingaswamy , K. Gopalakrishna Prabhu 1 2 1 2 Department of Computer Science Engineering, Manipal Institute of Technology, Manipal, India; Department of Biomedical Engineering, Manipal Institute of Technology, Manipal, India. Email: pcs.swamy@ Received 9 September 2009; revised 16 October 2009; accepted 19 October 2009. ABSTRACT be examined by ophthalmologists. Manual diagnosis is usually performed by analyzing the images from a pa- tient, as not all images show signs of diabetic retinopathy, it increases the time and decreases the efficiency of ophthalmologists. Therefore, an automatic segmentation of the vasculature could save workload of the ophthal- mologists and may assist in characterizing the detected lesions and to identify false positives [2]. Another im- portant application of automatic retinal vessel segmenta- tion is in the registration of retinal images of the same patient taken over period of time [3]. The registered im- ages are useful in monitoring the progression of disease and to observe the effect of treatment. Different techniques of segmentation of retinal images have been investigated so far. They are filter based meth- ods, vessel tracking methods, classifier based methods and morphological methods. The techniques utilize the prior knowledge such as, contrast that exists between the blood vessels and surrounding background, origin of vasculature from the same point that is the optic disc and connectivity of the vessels. Filter based methods [4,5] and [6] employ a two dimensional linear structural element that has a Gaus- sian cross-profile section to identify the blood vessels,