An image segmentation system : a novel super pixel based approach applied to image segmentation

Abstract

Nowadays, image segmentation has become an important topic in many fields like medical, machine vision, object detection, etc. In this context, many researchers have worked on improving the reliability of image segmentation systems and several methods were developed for this purpose. This paper presents an improved super pixel-based approach applied to image segmentation. The developed approach is based on obtaining an optimum number of clusters and regions of an image. Edge detection, Color frequencies, and texture measures are used in developing the new algorithm. It is compared with other techniques using different segmentation and clustering measures. The results show the improved performance of the proposed technique.