Spectral Eigenface Representation for Human Identification


Human identification based on face images, as physical biometric means, plays animperative role in many applications area. The methods for human identification usingface image uses either part of the face, all face, or mixture from these methods, in eithertime domain or frequency domain. This paper investigate the ability to implement theeigenface in frequency domain, the result spectral eigenface is utilize as a feature vectormeans for human identification. The converting from eigenface implementation in timedomain, into spectral eigenface implementation in frequency domain, is based onimplemented the correlation by using FFT. The Min-max is invoked as normalizationtechniques that increase spectral eigenface robustness to variations in facial geometryand illumination. Two face images are contrast in terms of their correlation distance. Athreshold (10.50x107) is used to restrict the impostor face image from being identified.The experimental results point up the effectiveness of a new method in either usingvarying (noisy images, unknown image, face expressions, illumine, and scale s), withidentification value of 100%.