AUTO-SEGMENTATION USING MEAN-SHIFT ALGORITHM AND ENTROPY ANALYSIS

Abstract

The development in the segmentation of object from the images and video has reached to the great height .Image segmentation has been widely used to split image into smaller parts so that useful information can be derived from them. This subject has drawn a lot of attention because of its useful applications and also because it gives a wide range of ideas that are still be explored more. Segmentation is the process of splitting the image into smaller regions. Auto-segmentation can be used in detecting the objects and the further results can be used for many purposes like clustering , marketing purpose , medical purpose .Over the past years, many segmentation Algorithms have been introduced in order to retrieve the useful data. In this thesis , we have proposed a new approach for auto-segmentation using mean –shift Algorithm to probe further in this arena. We have used different datasets including Drive Dataset and Berkeley Dataset to test our approach. In this, we came to know that the autosegmentation algorithm gives better results at high value of entropy.