Title: Target recognition by Fast Optimal Fuzzy C-Means image segmentation

Authors: Junwei Tian, Qing E. Wu, Yongxuan Huang, Tuo Wang

Addresses: School of Mechanical and Electronic Engineering, Xi'an Technological University, Xi'an 710032, China. ' College of Electric and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou, 450002, China. ' School of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an 710049, China. ' School of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an 710049, China

Abstract: We propose a novel Fast Optimal Fuzzy C-Means (FOFCM) clustering algorithm to improve target recognition in image processing. FOFCM can find the best clustering number of images by exploiting the characteristics of the given images, and reduce the segmentation time significantly at the same time. Experiments on serials images are employed to demonstrate the performance of FOFCM. The experiment results show that FOFCM has significantly better performance and lower complexity than previously proposed approaches. The correct recognition rate is increased by 29.24%, which is 94.59%. The clustering efficiency is improved by 6-132 times.

Keywords: multi-threshold segmentation; FCM; fuzzy-C means; relative entropy loss; target recognition; image processing; imaging systems; clustering algorithms; image segmentation.

DOI: 10.1504/IJSISE.2011.041602

International Journal of Signal and Imaging Systems Engineering, 2011 Vol.4 No.2, pp.79 - 95

Accepted: 28 Dec 2010
Published online: 13 Mar 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article