Distortion-invariant target detection using shifted-reference joint transform correlator

Abstract

A new pattern recognition system is proposed using multiple phase-shifted-reference fringe-adjusted joint transform correlation technique. The algorithm involves four different phase-shifted versions of the reference image, which eliminates all unwanted correlation terms and produces a single cross-correlation signal corresponding to each potential target. A fringe-adjusted filter is designed to generate a delta-like correlation peak with high discrimination between the signal and the noise. In addition, the detection performance is made invariant to different spatial distortions by incorporating a synthetic discriminant function, which is created from a set of training images of the reference object. The target detection system is also designed for recognition of multiple targets belonging to multiple reference objects simultaneously in the given input scene and hence provides a real-time class-associative decision on the presence of any target. The proposed technique is investigated using computer simulation with binary as well as gray images in various complex environments where it performs excellent in every case.