Palmprint recognition using Fisher-Gabor feature extraction

This paper presents a new approach for palmprint recognition using a combined Fisher linear discriminant (FLD) and Gabor Wavelet responses. Gabor wavelets have properties of being more robust to image illuminations, small translations, limited rotations and having a superior feature representation in both spatial and frequency domains. On the other hand, FLD seeks those projections that are efficient for data discrimination and produces well separated classes in low-dimensional subspaces. The new combined method involves convolving a palmprint image with a series of Gabor wavelets at different scales and rotations before extracting features from the resulting Gabor filtered images. Linear discriminant analysis is then applied to the feature vectors for dimension reduction as well as class separability. Experiments show that the proposed method yields a high classification rate even when using a simple classifier when compared with other popular approaches reported in the literature.