IMAGE CHARACTER RECOGNITION USING DEEP CONVOLUTIONAL NEURAL NETWORK LEARNED FROM DIFFERENT LANGUAGES

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 听觉模型与认知计算

	IMAGE CHARACTER RECOGNITION USING DEEP CONVOLUTIONAL NEURAL NETWORK LEARNED FROM DIFFERENT LANGUAGES
	Jinfeng Bai; Zhineng Chen; Bailan Feng; Bo Xu
	2014
会议日期	2014
会议地点	Pairs, France
关键词	Deep Convolutional Neural Network Image Character Recognition Multi-task Learning
页码	2560-2564
英文摘要	This paper proposes a shared-hidden-layer deep convolutional neural network (SHL-CNN) for image character recognition. In SHL-CNN, the hidden layers are made common across characters from different languages, performing a universal feature extraction process that aims at learning common character traits existed in different languages such as strokes, while the final softmax layer is made language dependent, trained based on characters from the destination language only. This paper is the first attempt to introduce the SHL-CNN framework to image character recognition. Under the SHL-CNN framework, we discuss several issues including architecture of the network, training of the network, from which a suitable SHL-CNN model for image character recognition is empirically learned. The effectiveness of the learned SHL-CNN is verified on both English and Chinese image character recognition tasks, showing that the SHL-CNN can reduce recognition errors by 16-30% relatively compared with models trained by characters of only one language using conventional CNN, and by 35.7% relatively compared with state-of-the-art methods. In addition, the shared hidden layers learned are also useful for unseen image character recognition tasks.
会议录	International Conference on Image Processing (ICIP)
语种	英语
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/41219]
专题	数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者	Zhineng Chen
推荐引用方式 GB/T 7714	Jinfeng Bai,Zhineng Chen,Bailan Feng,et al. IMAGE CHARACTER RECOGNITION USING DEEP CONVOLUTIONAL NEURAL NETWORK LEARNED FROM DIFFERENT LANGUAGES[C]. 见:. Pairs, France. 2014.