Histogram Layers for Texture Analysis

TL;DR

This paper introduces a localized histogram layer for neural networks that captures local spatial feature distributions, improving texture analysis performance across multiple datasets.

Contribution

The paper proposes a novel localized histogram layer for neural networks that estimates parameters during backpropagation for enhanced texture feature extraction.

Findings

Improved texture classification accuracy on three datasets.

Outperforms existing texture encoding methods.

Source code is publicly available.

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 localized 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 with state-of-the-art texture encoding methods such as the Deep Encoding Network Pooling, Deep Texture Encoding Network, Fisher Vector convolutional neural network, and Multi-level Texture Encoding and Representation on three material/texture datasets: (1) the Describable Texture Dataset; (2) an extension of the ground terrain in outdoor scenes; (3) and a subset of the Materials in Context dataset. Results indicate that the inclusion of the proposed histogram layer improves performance. The source code for the histogram layer is publicly available: https://github.com/GatorSense/Histogram_Layer.