A Novel Feature Recognition Neural Network and its Application to Character Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Matching Using Deformable Templates
IEEE Transactions on Pattern Analysis and Machine Intelligence
Design of Supervised Classifiers Using Boolean Neural Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
This paper describes a neural network architecture that has beendeveloped to perform deformation tolerant object recognition fromgrey-scale images. It uses a form ofdeformable template matching, generating new templates in aself-organising manner. The results demonstrate the network‘s ability to buildclasses when no suitable classes are available. The amount ofdeformation allowed within a class can be controlled to allow thenetwork to be applied to a wide range of applications. Results arepresented for a set of generated images which allow the effects of theselection of the major network parameters to be shown.