Multispectral image segmentation using the rough-set-initialized EM algorithm

• Published in: IEEE transactions on geoscience and remote sensing Vol. 40; no. 11; pp. 2495 - 2501
• Main Authors: Pal, S.K., Mitra, P.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.11.2002; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied geophysics; Clustering algorithms; Clusters; Convergence; Data mining; Data points; Earth sciences; Earth, ocean, space; Exact sciences and technology; Gaussian processes; Granular materials; Image segmentation; Internal geophysics; Mathematical models; Maximization; Measurement uncertainty; Multispectral imaging; Pixel; Satellites; Segmentation; Time measurement; algorithms; models; correlation; multispectral remote sensing; Space remote sensing; imagery; data processing; segmentation; cluster analysis; theory; quality
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2002.803716

The problem of segmentation of multispectral satellite images is addressed. An integration of rough-set-theoretic knowledge extraction, the Expectation Maximization (EM) algorithm, and minimal spanning tree (MST) clustering is described. EM provides the statistical model of the data and handles the associated measurement and representation uncertainties. Rough-set theory helps in faster convergence and in avoiding the local minima problem, thereby enhancing the performance of EM. For rough-set-theoretic rule generation, each band is discretized using fuzzy-correlation-based gray-level thresholding. MST enables determination of nonconvex clusters. Since this is applied on Gaussians, determined by granules, rather than on the original data points, time required is very low. These features are demonstrated on two IRS-1A four-band images. Comparison with related methods is made in terms of computation time and a cluster quality measure.