Texture Feature Extraction based on Multichannel Decoded Local Binary Pattern

Automatic classification of texture features is very challenging in image analysis and scene understanding. In this project we are mainly concentrating on the images acquired in various rotation and illumination conditions. The traditional way of binary combination is to simply concatenate the LBPs from each channel, but it increases the dimensionality of the pattern. Here in this paper we propose a multi-channel decoded local binary pattern for the extraction of features. We introduce adder and decoder based two schemas for the combination of the LBPs from more than one channel. The multi-channel decoded local binary pattern is equipped with the kernel-based extreme learning machine for classification. The n the classification accuracy and computational complexity are used as the parameters for the performance evaluation of feature extraction algorithm.