A neural network based integrated image processing environment for object recognition in medical applications

Abstract

The paper outlines an integrated image processing environment that uses neural networks for object recognition and classification. The image processing environment which is Windows based, encapsulates a multiple-document interface (MDI) and is menu driven. Object (shape) parameter extraction is focused on features that are invariant in terms of translation, rotation and scale transformations. The neural network models incorporated into the environment allow both clustering and classification of objects from the analysed image. Mapping neural networks perform input sensitivity analysis on the extracted feature measurements and thus facilitates the removal of irrelevant features and improvements in the degree of generalisation.