Chinese Image Character Recognition using DNN and Machine Simulated Training Samples
Bai JF(白锦峰)
2014
会议名称International Conference on Artificial Neural Networks
会议日期15–19 September 2014
会议地点德国汉堡
摘要

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.


关键词Chinese Image Character Recognition Deep Neural Net- Work Image Text Video Text
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/21513
专题数字内容技术与服务研究中心_听觉模型与认知计算
推荐引用方式
GB/T 7714
Bai JF. Chinese Image Character Recognition using DNN and Machine Simulated Training Samples[C],2014.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
ICANN-2014.pdf(1197KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Bai JF(白锦峰)]的文章
百度学术
百度学术中相似的文章
[Bai JF(白锦峰)]的文章
必应学术
必应学术中相似的文章
[Bai JF(白锦峰)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: ICANN-2014.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。