MEDICAL IMAGES SEGMENTATION USING ACTIVE CONTOUR OPTIMIZED WITH SGD: A REVIEW
Parul Saxena, Roopali Soni, M. Tech · 2013
This paper is a review of image segmentation is to partition an image into non-overlapping regions based on intensity or textural information. The active contour is one of the most successful variational models in image segmentation. It consists of evolving a contour in images toward the boundaries of objects. After reviewing, we have proposed an approach which is used in image segmentation using level set and is then optimized using Stochastic GD. So, this paper pro- poses a modification of Stochastic Gradient Descent Method (SGD), called Modified SGD. This Modified Stochastic Gradient Descent Method is often used to solve the optimization problem since they are very easy to implement. Before starting image segmentation using Level Set, Noise removal techniques are also applied on the input images provided by the users. The proposed methods are very simple modification of the basic methods and are directly compatible with any type of level set implementation. In this survey, some techniques have been reviewed that helps in the further research.