Feature extraction in 2D or 3D via histograms of normal Gabor-wavelets

These functions compute normals of Gabor-wavelets and use spherical patches to extract features.

This package implements the feature extraction algorithm using spherical patches from the Gabor-wavelet normal maps explained in:
M. Emambakhsh and A. Evans, “Nasal patches and curves for an expression-robust 3D face recognition,”
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 39, no. 5, pp. 995-1007, 2017.
Simply run the Demo_spherical_patched.m file to see a step by step output. Despite it is introduced for 3D face recognition, its applications can also be extended to other classes of 2D, 2.5D or 3D images, given a set of landmarks are available over the region.