An analysis of CANNY and LAPLACIAN of GAUSSIAN image filters in regard to evaluating retinal image

This paper deals with the analysis of performance of Canny and Laplacian of Gaussian filter in edge detection of retinal images. Edge detection is one of the methods in image segmentation in Image Processing. Classical methods of edge detection involve convolving the image with an operator (a 2D filter), which is constructed to be geometry of the operator which determines a characteristic direction in which it is most sensitive to edges. It is important to have efficient edge detection technique. In this paper, comparative analysis of the aforesaid filters is done and found that Canny edge operator performs better than Laplacian of Gaussian filter in most of the varieties of retinal images under various conditions. Here in this paper, we pertain only with human retinal images under diverse conditions. We have shown healthy retina, retina blood vessels, disease affected retina, optic disc etc.