CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
Chinese Image Character Recognition using DNN and Machine Simulated Training Samples
Bai JF(白锦峰)
Conference NameInternational Conference on Artificial Neural Networks
Conference Date15–19 September 2014
Conference Place德国汉堡

Inspired by the success of DNN models in solving challenging visual problems, this paper studies the task of Chinese Image Charac- ter Recognition (ChnICR) by leveraging DNN model and huge machine simulated training samples. To generate the samples, clean machine born Chinese characters are extracted and are plus with common variations of image characters such as changes in size, front, boldness, shift and complex backgrounds, which in total produces over 28 million character images, covering the vast majority of occurrences of Chinese character in real life images. Based on these samples, a DNN training procedure is employed to learn the appropriate Chinese character recognizer, where the width and depth of DNN, and the volume of samples are empirically discussed. Parallel to this, a holistic Chinese image text recognition sys- tem is developed. Encouraging experimental results on text from 13 TV channels demonstrate the effectiveness of the learned recognizer, from which significant performance gains are observed compared to the base- line system.

KeywordChinese Image Character Recognition Deep Neural Net- Work Image Text Video Text
Document Type会议论文
Recommended Citation
GB/T 7714
Bai JF. Chinese Image Character Recognition using DNN and Machine Simulated Training Samples[C],2014.
Files in This Item: Download All
File Name/Size DocType Version Access License
ICANN-2014.pdf(1197KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Bai JF(白锦峰)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Bai JF(白锦峰)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Bai JF(白锦峰)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: ICANN-2014.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.