Three-dimensional pattern recognition using joint transform correlation

摘要

A three-dimensional (3D) pattern recognition technique using classical joint transform correlation was proposed recently. However, it exhibits the same drawbacks of classical two-dimensional classical joint transform correlation by producing wide and broad correlation peak in the output plane. Thus, we propose a technique based on fringe-adjusted joint transform correlation to be used in 3D pattern recognition. The proposed technique yields better correlation discrimination ability compared to alternate 3D classical joint transform correlation by producing sharper and stronger correlation peak intensity. Simulation results verify the performance of the proposed technique.