Color pattern recognition using fringe-adjusted joint transform correlation

Abstract

A fringe-adjusted joint-transform correlator (JTC) based technique for improved color pattern recognition is introduced. In the proposed technique, a real-valued filter, called the fringe-adjusted filter is used to reshape the joint power spectrum in order to yield better correlation output. A color image is processed through three channels, and the fringe-adjusted filtering is applied to each of these channels to obtain excellent correlation discrimination. The correlation outputs from these channels are then fused together to achieve a decision on the detection of a given color pattern. It is also shown that the fringe-adjusted filtering can be applied to a multichannel single-output JTC to obtain excellent correlation output that represents the coherence level between the input target image and the reference image for all color channels. These two techniques can be easily implemented in real time as for practical color pattern recognition applications. Two architectures for all-optical implementation of the proposed techniques are presented.