Palmprint verification using competitive index with PCA

Among the various palmprint recognition techniques, competitive coding technique is very effective and gives efficient results. In the competitive coding method, gabor filters of six different orientation convolve with the palmprint image to extract the orientation information from the image. The winner-take-all strategy is used to select one orientation for each pixel, while each competitve index is coded into 3 bits, but in this study competitive index is not coded into bits. An approximation band of discrete wavelet transform of the image is used to compress the image, which has important information and makes the system illumination and translation invariant. Competitve index scheme is applied in the approximate band. Principal component analysis (PCA) is used to reduce the size of the feature vector and project the features in eigen space. Two different palmprints are matched using Euclidean distance metrics. This gives the equal error rate of .015% for palmprint verification.