Author : Safdar Mahfooz Alam, Mukesh Kumar, A K Jaiswal and Rohini Saxena

Segmentation of images is a key step in the field of image processing. Watershed segmentation is very important tool for segmentation of images in the field of mathematical morphology. Watershed transform is basically marker controlled segmentation technique. Segmentation of images by watershed generally results in the over segmentation. In this paper we proposed a novel approach to watershed segmentation using laplacian filter for noise removal and enhancement of images. Result of proposed algorithm is compared and analyzed with the result of existing methods. Result of proposed method shows it could effectively reduce the over segmentation and achieve more accurate segmentation results than existing methods.

Keywords: segmentation, watershed, marker, gradient, mathematical morphology, reconstruction

Article published in International Journal of Current  Engineering  and Technology, Vol.4,No.3 (June- 2014)