An improved edge detection using morphological Laplacian of Gaussian operator

Generally medical images are of low contrast. They need to be enhanced for computer diagnosis as well as for observation and analysis by a doctor. Edge detection is one of the basic yet important processes of image segmentation that leads to detection of different organs in a medical image. Presently a number of edge detection algorithms are available, but they do not always give satisfactory results. In this paper, a new algorithm is proposed which is based on the study of mathematical morphology and Laplacian of Gaussian. The proposed algorithm combines the advantages of both techniques for better detection of edge and good image contrast. We also present a study of different gradient based operators and mathematical morphology used for edge detection. The results of the proposed algorithm are compared with those of other methods showing the improvement in the result of proposed algorithm.