Rough Clustering Based Unsupervised Image Change Detection

Abstract

This paper introduces an unsupervised technique to detect the changed region of multitemporal images on a same reference plane with the help of rough clustering. The proposed technique is a soft-computing approach, based on the concept of rough set with rough clustering and Pawlak's accuracy. It is less noisy and avoids pre-deterministic knowledge about the distribution of the changed and unchanged regions. To show the effectiveness, the proposed technique is compared with some other approaches.

Proc. IEEE Conf. #30853, International Conference on Human Computer Interactions (ICHCI'13), Chennai, India, 23-24 Aug., 2013. (In Press)