Histogram Layers for Texture Analysis

Joshua Peeples, Weihuang Xu, Alina Zare

Abstract: An essential aspect of texture analysis is the extraction of features that describe the distribution of values in local, spatial regions. We present a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">localized</i> histogram layer for artificial neural networks. Instead of computing global histograms as done previously, the proposed histogram layer directly computes the local, spatial distribution of features for texture analysis, and parameters for the layer are estimated during backpropagation. We compare our method to state-of-the-art texture encoding methods such as: The deep encoding pooling network, deep texture encoding network, Fisher vector convolutional neural network, and multilevel texture encoding and representation. We used three material/texture datasets: 1) The describable texture dataset; 2) an extension of the ground terrain in outdoor scenes dataset; and 3) a subset of the materials in context dataset. Results indicate that the inclusion of the proposed histogram layer improves performance.