Shape from focus using multilayer feedforward neural networks.

Asif, M; Choi, T S · IEEE Trans Image Process · 2001

basic_science · Level V

Where this comes from

Abstract

The conventional shape-from-focus (SFF) methods have inaccuracies because of piecewise constant approximation of the focused image surface (FIS). We propose a scheme for SFF based on representation of three-dimensional (3-D) FIS in terms of neural network weights. The neural networks are trained to learn the shape of the FIS that maximizes the focus measure.