论文标题
直方图纹理分析
Histogram Layers for Texture Analysis
论文作者
论文摘要
纹理分析的一个重要方面是提取描述局部空间区域值分布的特征。我们提供了用于人工神经网络的局部直方图层。所提出的直方图层没有像以前所做的那样计算全局直方图，而是直接计算局部纹理分析特征的空间分布和该层的参数是在反向传播过程中估计的。我们将方法与最先进的纹理编码方法进行比较，例如深度编码网络池，深层编码网络，Fisher Vector卷积神经网络以及在三个材料/纹理数据集上编码和表示的多级纹理纹理和表示：（1）可描述的纹理数据集； （2）在室外场景中的地形延伸； （3）和上下文数据集中的材料子集。结果表明，所提出的直方图层的包含可改善性能。直方图层的源代码公开可用：https：//github.com/gatorsense/histogram_layer。
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.
