Improving CNN-Based Texture Classification by Color Balancing
Improving CNN-Based Texture Classification by Color Balancing
复制标题
DOI：
10.3390/jimaging3030033
复制
发表时间：
2017-09-01
影响因子：
3.2
通讯作者：
Schettini, Raimondo
中科院分区：
文献类型：
--
作者：
Bianco, Simone;Cusano, Claudio;Schettini, Raimondo
纹理分类在计算机视觉领域有着悠久的历史。在过去的十年中，深度学习技术，特别是卷积神经网络(CNN)得到了广泛的肯定，使得纹理识别系统的精度得到了极大的提高。然而，由于纹理图像的特征通常是颜色分布，相对于网络在其训练期间看到的颜色分布而言，它们的性能可能会受到抑制。在这篇文章中，我们将展示合适的颜色平衡模型如何在识别许多CNN架构的纹理时显著提高准确性。在RawFooT数据集上的实验结果证明了该方法的可行性，该数据集包括在几种不同光照条件下获取的纹理图像。关键词：卷积神经网络；颜色平衡；深度学习；纹理
Texture classification has a long history in computer vision. In the last decade, the strong affirmation of deep learning techniques in general, and of convolutional neural networks (CNN) in particular, has allowed for a drastic improvement in the accuracy of texture recognition systems. However, their performance may be dampened by the fact that texture images are often characterized by color distributions that are unusual with respect to those seen by the networks during their training. In this paper we will show how suitable color balancing models allow for a significant improvement in the accuracy in recognizing textures for many CNN architectures. The feasibility of our approach is demonstrated by the experimental results obtained on the RawFooT dataset, which includes texture images acquired under several different lighting conditions. Keywords: convolutional neural networks; color balancing; deep learning; texture