Knowledge Commons of Institute of Automation,CAS
Robust offline handwritten character recognition through exploring writer-independent features under the guidance of printed data | |
Zhang, Yaping1,2; Liang, Shan1; Nie, Shuai1,2; Liu, Wenju1; Peng, Shouye3 | |
发表期刊 | PATTERN RECOGNITION LETTERS |
2018-04-15 | |
卷号 | 106期号:无页码:20-26 |
文章类型 | Article |
摘要 | Deep convolutional neural networks have made great progress in recent handwritten character recognition (HCR) by learning discriminative features from large amounts of labeled data. However, the large variance of handwriting styles across writers is still a big challenge to the robust HCR. To alleviate this issue, an intuitional idea is to extract writer-independent semantic features from handwritten characters, while standard printed characters are writer-independent stencils for handwritten characters. They could be used as prior knowledge to guide models to exploit writer-independent semantic features for HCR. In this paper, we propose a novel adversarial feature learning (AFL) model to incorporate the prior knowledge of printed data and writer-independent semantic features to improve the performance of HCR on limited training data. Different from available handcrafted features methods, the proposed AFL model exploits writer-independent semantic features automatically, and standard printed data as prior knowledge is learnt objectively. Systematic experiments on MNIST and CASIA-HWDB show that the proposed model is competitive with the state-of-the-art methods on the offline HCR task. |
关键词 | Handwritten Character Recognition Writer-independent Features Adversarial Feature Learning Convolutional Neural Network |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1016/j.patrec.2018.02.006 |
收录类别 | SCI |
语种 | 英语 |
项目资助者 | National Natural Science Foundation of China(61573357 ; 61503382 ; 61403370 ; 61273267 ; 91120303) |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000429325500004 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/22016 |
专题 | 多模态人工智能系统全国重点实验室_机器人视觉 |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Patten Recognit, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Xueersi Online Sch, Beijing, Peoples R China |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhang, Yaping,Liang, Shan,Nie, Shuai,et al. Robust offline handwritten character recognition through exploring writer-independent features under the guidance of printed data[J]. PATTERN RECOGNITION LETTERS,2018,106(无):20-26. |
APA | Zhang, Yaping,Liang, Shan,Nie, Shuai,Liu, Wenju,&Peng, Shouye.(2018).Robust offline handwritten character recognition through exploring writer-independent features under the guidance of printed data.PATTERN RECOGNITION LETTERS,106(无),20-26. |
MLA | Zhang, Yaping,et al."Robust offline handwritten character recognition through exploring writer-independent features under the guidance of printed data".PATTERN RECOGNITION LETTERS 106.无(2018):20-26. |
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 | ||
AFL_prletter18.pdf(756KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论