A classification approach to image structure segmentation based on the wavelet transform

Investigates a novel approach to image structure segmentation based on detecting the critical image edges by formulating the problem as a classification task. The main goal of such a research effort is to better identify abrupt image changes without increasing the presence of noise in the resulting image. The suggested methodology is based on the discrete 2D wavelet transform applied to the original image in an attempt to extract more informative features for facilitating the decision-making process subsequently involved. This process is considered as a classification procedure employing supervised training techniques and, more specifically, multivariate stepwise discriminant analysis. The feasibility of this novel proposed approach is preliminarily studied by applying it to the image structure segmentation problem of a brain slice MRI image.