Adaptive classification of textured images using moments and autoregressive models

ABSTRACT An adaptive approach to the classification of textured images is presented, based onthe extraction of appropriate features from images. Autoregressive linear prediction mod-els, as well as moments of images, are features which are examined and compared in thepaper. Classification is achieved in an adaptive way, using an artificial feedforward neuralnetwork, which is trained by examples, using an efficient variant of the backpropagation learning algorithm. It is also shown that an adaptive least squares estimation algorithm can be appropriately interweaved with the network, resulting in an on-line adaptive clas- sification scheme. Simulation results are given, which illustrate the performance of the presented method. 1. INTRODUCTION Segmentation and classification of textured images has received considerable attention in many applications, such as cartography, military surveillance and recognition, land classification and medical imaging . Extraction of characteristic features is generallyrequired before the classification task, in order to reduce the dimension of the problem