Application of Self-Organisation Neural Network for Direct Shape from Shading

Abstract

In this paper, a supervised self-organisation Neural Network (NN) for direct shape from shading is developed. The structure of the NN for the inclined light source model is derived based on the maximum uphill direct shape from shading approach. The major advantage of the NN model presented is the parallel learning or weight evolution for the direct shading. Here the proved convergent learning rule, the rate of convergence and a zero initialisation condition are shown. To increase the rate of convergence, the momentum factor is introduced. Furthermore, the application of the network on IC (Integrated Circuit) component shape reconstruction is presented.