A novel neural network for object recognition with blurred shapes

Presents a neural network approach to shape recognition. The emphasis is on the development of an effective representation method to increase the degree of robustness in recognition of shapes which may be blurred by noise. A space-perturbation neural network is described which is characterized by two important properties. (1) The network can be trained using error back-propagation with only noise-free data, which avoids the convergence problem due to possibly large variance in each shape class. (2) The space-perturbation arrangement enables the network to discover class features independent of random variations in shape and hence not blurred by random variations in the input. As a recognition task, the classification of four closed planar shapes was chosen. For comparison, the neural network classifier based upon the extended training technique was implemented to perform the same task. Performance evaluation results for 4000 testing shapes from various blur conditions are given