Certain and correlated neighboring pixels in multispectral image classification

Author

Matcha, Subhakar ; Hung, Chih-Cheng ; Chen, Imao

Author_Institution

Dept. of Comput. & Inf. Sci., Alabama A&M Univ., Normal, AL, USA

fYear

1993

fDate

14-17 Sep 1993

Firstpage

539

Abstract

This paper presents two image classification algorithms, which utilize spectral attributes and spatial interdependency of neighboring pixels. These classifiers, namely FKNN-mean classifier and FKNN-median classifier, incorporate the K-nearest-neighbor rule into their algorithms. Fuzzy membership functions are suggested in solving the problem of inherent ambiguity of spatial boundaries in images. Experimental results of these algorithms when compared with those generated by perpixel classification algorithms show significant improvement

Keywords

correlation methods; fuzzy set theory; image recognition; spectral analysis; FKNN-mean classifier; FKNN-median classifier; K-nearest-neighbor rule; correlated neighboring pixels; experimental results; fuzzy membership functions; image classification algorithms; multispectral image classification; perpixel classification algorithms; spatial boundaries ambiguities; spatial interdependency; spectral attributes; Classification algorithms; Data analysis; Earth; Image analysis; Image classification; Image processing; Multispectral imaging; Pixel; Remote sensing; Smoothing methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering, 1993. Canadian Conference on

Conference_Location

Vancouver, BC

Print_ISBN

0-7803-2416-1

Type

conf

DOI

10.1109/CCECE.1993.332351

Filename

332351