中国科学院重庆绿色智能技术研究院机构知识库

QQ客服 官方微博 反馈留言

	Handwritten Chinese character recognition by joint classification and similarity ranking
	Cheng, Cheng1; Zhang, Xu-Yao2; Shao, Xiao-Hu1; Zhou, Xiang-Dong1
	2017
摘要	Deep convolutional neural networks (DCNN) have recently achieved state-of-the-art performance on handwritten Chinese character recognition (HCCR). However, most of DCNN models employ the softmax activation function and minimize cross-entropy loss, which may loss some inter-class information. To cope with this problem, we demonstrate a small but consistent advantage of using both classification and similarity ranking signals as supervision. Specifically, the presented method learns a DCNN model by maximizing the inter-class variations and minimizing the intra-class variations, and simultaneously minimizing the cross-entropy loss. In addition, we also review some loss functions for similarity ranking and evaluate their erformance. Our experiments demonstrate that the presented method achieves state-of-the-art accuracy on the well-known ICDAR 2013 offline HCCR competition dataset. © 2016 IEEE.
语种	英语
DOI	10.1109/ICFHR.2016.0099
会议(录)名称	15th International Conference on Frontiers in Handwriting Recognition, ICFHR 2016
页码	507-511
收录类别	EI
会议地点	Shenzhen, China
会议日期	October 23, 2016 - October 26, 2016