Spectral fuzzy classification system for target recognition

Abstract

The goal of this paper is to present an algorithm for terrain matching, leveraging an existing fuzzy clustering algorithm, and modifying it to its supervised version, in order to apply the algorithm to georegistration and, later on pattern recognition. Georegistration is the process of adjusting one drawing or image to the geographic location of a "known good" reference drawing, image, surface or map, The georegistration problem can be treated as a pattern recognition problem; and it can be applied to the target detection problem. The terrain matching algorithm will be based on fuzzy set theory as a very accurate method to represent the imprecision of the real world, and presented as a multicriteria decision making problem. The energy emitted and reflected by the Earth's surface has to be recorded by relatively complex remote sensing devices that have spatial, spectral and geometrical resolution constraints. Errors usually slip into the data acquisition process. Therefore, it is necessary to preprocess the remotely sensed data, prior to analyzing it (image restoration, involving the correction of distortion, degradation and noise introduced during the rendering process). In this paper we shall assume that all these problems have been solved, focusing our study on the image classification of a corrected image being close enough, both geometrically and radiometrically, to the radiant energy characteristics of the target scene. In particular, at a first stage we consider each pixel individually; and a class will be assigned to each pixel, taking into account several values measured in separate spectral bands. Then we shall describe an automatic detection system based on a previous algorithm developed in A. Del Amo et al., introducing now the fuzzy partition model proposed by A. Del Amo et al. A first phase will lead to a spectral definition of patterns; and a second phase will lead to classification and recognition. Similarity measures will then allow us to evaluate the degree to which a pixel can be associated to each pattern, or determine if a pattern is similar enough to a subimage of the main image, to establish that a target we are looking for can be found on that image.