Paper texture classification via multi-scale Restricted Boltzman Machines
Arash Sangari, William A. Sethares · 2014 48th Asilomar Conference on Signals, Systems and Computers · 2014
The performance of two classification algorithms based on Restricted Boltzman Machine (RBM) are compared in the paper texture classification application when utilizing a multi-scale Local Binary Pattern sampling. In the first approach, a separate RBM is trained for each texture-type to estimate the joint probability distribution of samples. In the second approach, a Deep Belief Net, which consists of a cascade of RBM layers, is used to extract texture features which are then fed into a logistic regression layer. The classification performance of the two methods are compared in detail.