A Novel Method Using Local and Global Features for Face Recognition

Face recognition is the process of identifying the presence of a face from a database that contains many faces. Face recognition technology has many applications such as Automatic Teller Machine access, verification of credit card, video surveillance etc. The global and local features play an important role for face recognition. In the proposed method, both global and local features are extracted from the input face image. Global features are extracted from whole face images by keeping the low frequency co-efficient of Fast Fourier Transforms. Odd and Even components in the low frequency band are concatenated into single feature vector named Global Fourier Features Vector (GFFV). Local features are extracted by Gabor wavelets. Gabor features are facially grouped into a number of feature vectors named Local Gabor Feature Vector (LGFV). Fisher liner discriminant is applied for both local and global features for classification. The resultant vectors are fused using region based image fusion method. The processed test face image is verified for a match with the faces in the database using Correlation Coefficient and recognition is done