Contour Code: Robust and Efficient Multispectral Palmprint Encoding for Human Recognition

The authors propose 'Contour Code', a novel representation and binary hash table encoding for multi-spectral palmprint recognition. They first present a reliable technique for the extraction of a Region Of Interest (ROI) from palm images acquired with non-contact sensors. The Contour Code representation is then derived from the Non-subsampled Contourlet Transform. A uniscale pyramidal filter is convolved with the ROI followed by the application of a directional filter bank. The dominant directional sub-band establishes the orientation at each pixel and the index corresponding to this sub-band is encoded in the Contour Code representation.