首页> 外文会议>International Conference on Cloud Computing and Security >PCANet for Color Image Classification in Various Color Spaces
【24h】

PCANet for Color Image Classification in Various Color Spaces

机译:PCANet用于各种颜色空间中的彩色图像分类

获取原文

摘要

Principal component analysis network (PCANet), which is a recently proposed novel deep learning algorithm, has aroused the interest of a wide variety of researchers. In this paper, we evaluate the performance of PCANet in various color spaces on different types of color image dataset. Experimental results on CURet texture database, UC Merced land use database, and Georgia Tech face database show that Luminance and Chrominance based principal component analysis network outperforms other color spaces in the vast majority of cases. Therefore, when dealing with the problem of color image dataset classification, Luminance and Chrominance based principal component network is recommended.
机译:主成分分析网络(PCANet)是最近提出的一种新型深度学习算法,引起了众多研究人员的兴趣。在本文中,我们评估了PCANet在不同类型的彩色图像数据集上的各种颜色空间中的性能。在CURet纹理数据库,UC Merced土地使用数据库和Georgia Tech人脸数据库上的实验结果表明,在大多数情况下,基于亮度和色度的主成分分析网络优于其他颜色空间。因此,在处理彩色图像数据集分类问题时,建议使用基于亮度和色度的主成分网络。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利