DETECTION OF VISUAL IMPAIRMENTS USING BACK PROPAGATION NEURAL NETWORKS
Journal Title: International Journal of Computer Science & Engineering Technology - Year 2013, Vol 4, Issue 3
Abstract
Proliferative diabetic retinopathy is the more serious conditions as it involves the proliferative growth of abnormal new vessels on the retina. New vessels characteristic appearance like narrower calibre and more tortuous. This paper presents a method for detecting new vessels on the optic disc based on the SVM classifier. First, vessels like candidate segments are extracted using green component, because in the colour retinal images the blood vessels appear most contrasted in the green channel compared to red and blue channels in RGB image. Second, candidate new vessel segments re detected using a method of morphological watershed transform. Third, fifteen feature parameter are calculated for each segment. Based on these feature, each segment is classified as normal or abnormal vessels using SVM classifier. The system was trained with normal and abnormal retinal images.
Authors and Affiliations
Anwar Basha. H , S. Udhayakumar , E. Sujatha
Keywords
Related Articles
- EP ID EP156579
- DOI -
- Views 121
- Downloads 0
Virtual Education - the progression by Driving Forces and Technical Challenge issues in Access Control
Enabling technologies have led to the transformation from Traditional Education systems to a new methodology of virtual education incorporating: Electronic collections, Virtual reference services, Virtual libraries and o...
Analyze the impact of Transmission rate on the Performance of AODV and DSR Protocols in MANETs under Responsive and Non-responsive Traffic.
The massive boom in the wireless technology has led to heavy utilization. Due to the heavy utilization and shared nature of resources causes QoS problems in ad hoc networks. Providing QoS is a severe problem in mobile ad...
Regression model approach to predict missing values in the Excel sheet databases
The most important stage of data mining is pre-processing, where we prepare the data for mining. Real-world data tends to be incomplete, noisy, and inconsistent and an important task when pre-processing the data is to fi...
Analysis of Degenerated Tissue in Temporal Lobe of Human Brain using image segmentation Techniques
Degenerated Tissue in temporal lobe may cause diminished speech and memory difficulty. The principal of our Research work is automatic detection of degenerated tissues due to any disease in the temporal lobe. Fully autom...
Enhanced Energy Conserving Improved and Balanced LEACH for Heterogeneous Wireless Sensor Networks
Wireless sensor networks consists of thousands of tiny, low cost, low power and multifunctional sensor nodes where each sensor node has very low battery life. Main goal is to conserve the transmitted energy from various...