AN MLP-BASED TEXTURE SEGMENTATION METHOD WITHOUT SELECTING A FEATURE SET

A texture segmentation technique which employs a multilayer perceptron (MLP) and does not consider the selection of features is presented in this paper. Thus, users can avoid selection and computation of the fe ature set and hence real-time segmentation may be possible. The techni que apparently works in a fashion similar to our visual system whereby we do not consciously compute any feature for texture discrimination. A detailed study has been made for the selection of the network size. A newly proposed variant of the backpropagation algorithm has been us ed for more efficient training of the network. An edge-preserving nois e-smoothing approach has been proposed to remove noise from the segmen ted image. (C) 1997 Elsevier Science B.V.