Palmprint recognition method using Dual-Tree Complex Wavelet Transform and Local Binary Pattern Histogram

In the paper, we combine the Local Binary Pattern Histogram (LBPH) approach with Dual-Tree Complex Wavelet Transform (DT-CWT) to propose a new method, DT-CWT based LBPH, for palmprint recognition. The approximate shift invariant property of the DT-CWT and its good directional selectively in 2D make it a very appealing choice for palmprint recognition. LBPH is a powerful texture description method, which considers both shape and texture information to represent image. By combining these two tools, we don’t need to train samples to construct a palmprint model, which is not like some methods based on subspace discriminant analysis or statistical learning. In the approach, the dual-tree complex wavelet features are divided into small regions from which LBPH are extracted, and the all the sub-histograms are concatenated into a single feature histogram effectively representing the palmprint image. Our experimental results on our palmprint database show the proposed method outperform other considered methods.