Creating and sharing knowledge for telecommunications

Multilevel Image Segmentation based on Fractional-Order Darwinian Particle Swarm Optimization

Ghamisia, P. ; Couceiro, M. Couceiro ; Martins, F. ; Benediktsson, J. A.

IEEE Transactions on Geoscience and Remote Sensing Vol. 52, Nº 5, pp. 2382 - 2394, May, 2014.

ISSN (print): 0196-2892
ISSN (online):

Journal Impact Factor: 3,157 (in 2008)

Digital Object Identifier: 10.1109/TGRS.2013.2260552

Download Full text PDF ( 1 MB)

Hyperspectral remote sensing images contain hundreds of data channels. Due to the high dimensionality of the hyperspec-tral data, it is difficult to design accurate and efficient image segmentation algorithms for such imagery. In this paper, a new multilevel thresholding method is introduced for the segmentation of hyperspectral and multispectral images. The new method is based on Frac-tional-Order Darwinian Particle Swarm Optimization (FODPSO) which exploits the many swarms of test solutions that may exist at any time. In addition, the concept of fractional derivative is used to control the convergence rate of particles. In this work, the so-called Otsu problem is solved for each channel of the multispectral and hyperspectral data. Therefore, the problem of ��-level thresh-olding is reduced to an optimization problem in order to search for the thresholds that maximizes the between-class variance. Experi-mental results are favorable for the FODPSO when compared to other bio-inspired methods for multi-level segmentation of multispec-tral and hyperspectral images. The FODPSO presents a statistically significant improvement in terms of both CPU time and fitness value, i.e., the approach is able to find the optimal set of thresholds with a larger between-class variance in less computational time than the other approaches. In addition, a new classification approach based on Support Vector Machine (SVM) and FODPSO is intro-duced in this paper. Results confirm that the new segmentation method is able to improve upon results obtained with the standard SVM in terms of classification accuracies.

Keywords: multilevel segmentation; swarm optimization; image processing, classification