FACE RECOGNITION PERFORMANCES WITH PHASE INPUT JOINT TRANSFORM CORRELATORS
Pages 63-67
Alin C. Teuşdea
Abstract
Former works prove that phase input joint transform correlators have better detection efficiency than the amplitude ones. The preprocessed phase input joint transform correlator has the best detection efficiency. This correlator needs as parameters: the amplitude premodulation domain, dƒPRE, and the phase modulation domain, dƒPSLM.
Face recognition implies that the real world scene images are embedded in noise threfore it is important to test the correlators in these conditions. Computer simulations were done on some combinations of amplitude premodulation domains and phase modulation domains for four input images. Two images have black (null) background and grey (average) background and two images have two kinds of embedding noise. These simulations were done to find the combination of the amplitude premodulation domain and phase modulation domain that has the best detection efficiency for all images.