Improving CNN-based texture classification by color balancing

被引：32

作者：

Bianco, Simone ^{[1
]}

Cusano, Claudio ^{[2
]}

Napoletano, Paolo ^{[1
]}

Schettini, Raimondo ^{[1
]}

机构：

[1] Department of Computer Science, Systems and Communications, University of Milano-Bicocca, Milan,20126, Italy

[2] Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia,27100, Italy

来源：

Journal of Imaging | 2017年 / 3卷 / 03期

关键词：

Color computer graphics - Convolution - Deep neural networks - Image texture - Textures;

D O I：

10.3390/jimaging3030033

中图分类号：

学科分类号：

摘要：

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. © 2017 by the authors.

引用