SVM Algorithm for the Robotic Detection of Retinal Hemorrhage in Fundus Images

Abstract

Many important eye diseases as well as systemic diseases manifest themselves in the retina. Diabetic retinopathy is a vascular disease of the retina which affects patients with diabetes mellitus. A number of other anatomical structures contribute to the process of vision, this paper focuses on retinal imaging and image analysis. Fundus photographs are partitioned into a number of splats covering the entire image. Each splat contains pixels with similar color and close spatial location. A set of distinct features is extracted within each splat. By learning properties of splats formed from blood vessels, a classifier was trained so that it can distinguish blood splats from non-blood splats. Once the blood splats, i.e. vasculature and hemorrhages, are separated from the background, the connected vasculature was removed and the remaining objects considered hemorrhage candidates. The proposed method SVM algorithm determines the origination of the blood vessel network. Finally the segmented image is classified so as to yield normal and abnormal set using Support vector machine.

Authors and Affiliations

Dr. K. Sakthivel, G. Keerthana

Keywords

Related Articles

Survey on Privacy Policy Specification System for User Uploaded Images Over Popular Content Sharing Sites

The regular use of social networking websites and application encompasses the collection and retention of personal and very often sensitive information about users. This information needs to remain private and each soci...

DICOM Image Enhancement of Mammogram Breast Cancer

Mammogram breast cancer images have the ability to help oncologist in detecting disease caused by cells normal growth. Developing algorithms and software to analyze these images may also help oncologist in their daily w...

A Review on QoS Aware Routing Protocols for Wireless Sensor Networks

Wireless Sensors Network is used to monitor agriculture field, traffic signal management & Health Monitoring, Pollution control, Military applications etc. with limited energy resources. Various energy efficient routing...

Matlab Implementation of Face Recognition Using Local Binary Variance Pattern

Face images can be seen as a composition of micro-patterns which can be well described by LBP (Local Binary Pattern). We exploited this observation on human face database for efficient representation in face recognition...

Efficiency Enhancement in a Pre-Bunched Cerenkov Free Electron Laser

An electron beam passing through a slow wave structure is unstable to an electromagnetic perturbation whose phase velocity equals the velocity of the beam. This phenomenon of cerenkov emission is the basis of all slow w...

Download PDF file
  • EP ID EP21810
  • DOI -
  • Views 195
  • Downloads 4

How To Cite

Dr. K. Sakthivel, G. Keerthana (2016). SVM Algorithm for the Robotic Detection of Retinal Hemorrhage in Fundus Images. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 4(3), -. https://europub.co.uk/articles/-A-21810