GRAM-SCHMIDT ORTHOGONALIZATION BASED FACE RECOGNITION USING DWT

The personal identification based on face recognition is essential to create Unique Identification (UID) card, which can be used for voting in electoral systems, accessing secured areas, identification to avail government and nongovernment facilities. In this paper we propose the Gram-Schmidt Orthogonalization based Face Recognition using DWT (GSFRD). The Discrete Wavelet Transform is applied on face images of Libor Spacek database. The LL subband is considered and Fast Principal Component Analysis using Gram-Schmidt orthogonalization process is applied to generate feature coefficient vectors. The Euclidean Distance between test and database face image coefficient vectors are computed and compared with the predefined threshold value. It is observed that the face recognition rate is 100% and has better computational efficiency compared to existingalgorithm with same Mean Square Error (MSE).