Efficiency Enhancement of Neural Network with Phase Only Correlation

The research work is carried out to enhance the recognition accuracy of neural network with Phase Only Correlation (POC) and reduce the time required for POC by refining its input. In this research work neural network has not been directly used for recognition but for the minimization of the search space. The fusion of neural network with POC is tested on face recognition application to validate the proposed idea. Neural network helps to prune all those faces of subjects which have lower response values from the neurons output and pass it to POC for post processing. The first five high response values of neuron are selected from forty responses for POC post processing. This amalgamation of data from two recognition techniques have enabled us to look into the new dimension of not only improving the accuracy of neural network but also to decrease the computational and time cost of phase only correlation.