Extracting the Edges of Optic Disc using Erosion,canny-Edge detection and Hough Transform

Extracting the edges of optic disc is an important step in developing diagnosis of various serious ophthalmic pathologies. In this paper a new methodology for segmenting the OD from digital retinal images has been presented. This methodology uses morphological operator of Erosion and canny edge detection tech¬niques followed by the Circular Hough Transform to obtain a circular OD boundary approximation. OD seg¬mentation is done by extracting sub-image, an OD pixel and its surrounding region (a surrounding region wide enough to include the whole OD) are selected. Then the OD boundary is extracted in parallel from both the red and green channels of this sub-image by means of morphological and edge detection techniques. In order to smooth out the distracters, the image is transformed to the frequency do¬main and filtered by the Gaussian low-pass filter. OD boundaries are approx¬imated by a circumference using the Circular Hough Transform.