文献类型：期刊文献

英文题名：Image classification with a new kind of shape representation

作者：Xu, Shaowu[1]; Miao, Jun[1]; Qing, Laiyun[2]; Qiao, Yuanhua[3]; Zou, Baixian[4]

第一作者：Xu, Shaowu

通讯作者：Miao, Jun

机构：[1] Beijing Key Laboratory of Internet Culture and Digital Dissemination Research, School of Computer Science, Beijing Information Science and Technology University, Beijing, 100101, China; [2] School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, 100049, China; [3] College of Applied Sciences, Beijing University of Technology, Beijing, 100124, China; [4] College of Applied Arts and Science, Beijing Union University, Beijing, 100191, China

第一机构：Beijing Key Laboratory of Internet Culture and Digital Dissemination Research, School of Computer Science, Beijing Information Science and Technology University, Beijing, 100101, China

年份：2018

卷号：10836

外文期刊名：Proceedings of SPIE - The International Society for Optical Engineering

收录：EI(收录号：20191006602854)

语种：英文

外文关键词：Encoding (symbols) - Signal encoding - Image representation - Neural networks

摘要：As one of the research hotspots in recent years, especially in pattern recognition, Convolutional Neural Network (CNN) is widely known for its high efficiency. However some researches show that there is a problem in the CNN which cannot learn the high-level features. In order to solve this problem, this paper proposes a new kind of image representation, which we call it "shape encoding maps". Our experimental results show that, in most cases, the recognition accuracies obtained by inputting the shape encoded maps to a CNN are higher than that of using the original image data for a CNN to learn directly without shape encoding. Copyright ? 2018 SPIE.