On The Power of Joint Wavelet-DCT Features for Multispectral Palmprint Recognition

Biometric based identification has drawn a lot of attention in the recent years. Among all biometrics, palmprint is known to possess a rich set of features including geometrical and textural features, lines, corners and so on. Therefore, the features that can be used to pinpoint a single palmprint are many, but it is important to choose the combination of the most distinguishing features to minimize the calculations and maximize efficiency. In this paper we proposed to use DCT-based features in parallel with wavelet-based ones for palmprint identification. Then these features are used to match palmprints using the majority voting algorithm (MV). The features introduced here are very simple to compute and result in extremely highly accurate identification. This method is tested on a well-known multispectral palmprint database and an accuracy rate of 99.97-100% is achieved which beats all previous methods under the same scenario.