An Overview of Image Segmentation Algorithms

Image segmentation is a puzzled problem even after four decades of research. Research on image segmentation is currently conducted in three levels. Development of image segmentation methods, evaluation of segmentation algorithms and performance and study of these evaluation methods. Hundreds of techniques have been proposed for segmentation of natural images, noisy images, medical images etc. Currently most of the researchers are evaluating the segmentation algorithms using ground truth evaluation of (Berkeley segmentation database) BSD images. In this paper an overview of various segmentation algorithms is discussed. The discussion is mainly based on the soft computing approaches used for segmentation of images without noise and noisy images and the parameters used for evaluating these algorithms. Some of these techniques used are Markov Random Field (MRF) model, Neural Network, Clustering, Particle Swarm optimization, Fuzzy Logic approach and different combinations of these soft techniques.