Histogram Layers for Texture Analysis

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.

13 pages, 8 figures; Accepted to IEEE Transactions on Artificial Intelligence

References in corpus (1)

• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

Cited by in corpus (5)

• Wise-SrNet: A Novel Architecture for Enhancing Image Classification by Learning Spatial Resolution of Feature Maps
• Divergence Regulated Encoder Network for Joint Dimensionality Reduction and Classification
• Differentiable Histogram with Hard-Binning
• The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression
• Histogram Layers for Synthetic Aperture Sonar Imagery