TY - JFULL AU - Muhammad Imran Ahmad and Ruzelita Ngadiran and Mohd Nazrin Md Isa and Nor Ashidi Mat Isa and Mohd Zaizu Ilyas and Raja Abdullah Raja Ahmad and Said Amirul Anwar Ab Hamid and Muzammil Jusoh PY - 2015/2/ TI - Local Spectrum Feature Extraction for Face Recognition T2 - International Journal of Electronics and Communication Engineering SP - 364 EP - 369 VL - 9 SN - 1307-6892 UR - https://publications.waset.org/pdf/10000915 PU - World Academy of Science, Engineering and Technology NX - Open Science Index 97, 2015 N2 - This paper presents two techniques, local feature extraction using image spectrum and low frequency spectrum modelling using GMM to capture the underlying statistical information to improve the performance of face recognition system. Local spectrum features are extracted using overlap sub block window that are mapped on the face image. For each of this block, spatial domain is transformed to frequency domain using DFT. A low frequency coefficient is preserved by discarding high frequency coefficients by applying rectangular mask on the spectrum of the facial image. Low frequency information is non- Gaussian in the feature space and by using combination of several Gaussian functions that has different statistical properties, the best feature representation can be modelled using probability density function. The recognition process is performed using maximum likelihood value computed using pre-calculated GMM components. The method is tested using FERET datasets and is able to achieved 92% recognition rates. ER -