Facilitating efficient Mars terrain image classification with fuzzy-rough feature selection

Issue title: Rough and Fuzzy Methods for Data Mining

Guest editors: A.E. Hassanienav, H. Sakaibw, D. Ślȩzakx, M.K. Chakrabortydy and W. Zhuz

Article type: Research Article

Authors: Shang, Changjing^{; *} | Barnes, Dave | Shen, Qiang

Affiliations: Department of Computer Science, Aberystwyth University, Wales, UK | [v] Cairo University, Egypt | [w] Kyushu Institute of Technology, Japan | [x] University of Warsaw & Infobright Inc., Poland | [y] University of Calcutta, India | [z] UESTC, Chengdu, China

Correspondence: [*] Corresponding author. E-mail: [email protected]

Abstract: This paper presents an application study of exploiting fuzzy-rough feature selection (FRFS) techniques in aid of efficient and accurate Mars terrain image classification. The employment of FRFS allows the induction of low-dimensionality feature sets from sample descriptions of feature vectors of a much higher dimensionality. Supported with comparative studies, the work demonstrates that FRFS helps to enhance both the effectiveness and the efficiency of conventional classification systems such as multi-layer perceptrons and K-nearest neighbors, by minimizing redundant and noisy features. This is of particular significance for on-board image classification in future Mars rover missions.

Keywords: Mars images, image classification, fuzzy-rough feature selection

DOI: 10.3233/HIS-2011-0126

Journal: International Journal of Hybrid Intelligent Systems, vol. 8, no. 1, pp. 3-13, 2011