Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification

Our Multi-Column Deep Neural Networks achieve best known recognition rates on Chinese characters from the ICDAR 2011 and 2013 offline handwriting competitions, approaching human performance.

cs.CV Computer Science

View graph Source

Paper

References (10)

01Mitosis Detection in Breast Cancer Histology Images with Deep Neural NetworksD. Ciresan, A. Giusti, L. Gambardella et al.2013 · International Conference on Medical Image Computing and Computer-Assisted Intervention · 1.6k citations

02ICDAR 2013 Chinese Handwriting Recognition CompetitionFei Yin, Qiu-Feng Wang, Xu-Yao Zhang et al.2013 · IEEE International Conference on Document Analysis and Recognition · 321 citations

03Learning Hierarchical Features for Scene LabelingC. Farabet, C. Couprie, Laurent Najman et al.2013 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2.8k citations

04Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy ImagesD. Ciresan, A. Giusti, L. Gambardella et al.2012 · Neural Information Processing Systems · 1.5k citations

05Transfer learning for Latin and Chinese characters with Deep Neural NetworksD. Ciresan, U. Meier, J. Schmidhuber2012 · IEEE International Joint Conference on Neural Network · 214 citations

06Multi-column deep neural networks for image classificationD. Ciresan, U. Meier, J. Schmidhuber2012 · 2012 IEEE Conference on Computer Vision and Pattern Recognition · 4.1k citations In Library

07ICDAR 2011 Chinese Handwriting Recognition CompetitionChenglin Liu, Fei Yin, Qiu-Feng Wang et al.2011 · IEEE International Conference on Document Analysis and Recognition · 79 citations

08Convolutional Neural Network Committees for Handwritten Character ClassificationD. Ciresan, U. Meier, L. Gambardella et al.2011 · IEEE International Conference on Document Analysis and Recognition · 512 citations

09Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence Flexible, High Performance Convolutional Neural Networks for Image Classification1.2k citations

10Technical Report No. IDSIA-05-13 5

Similar papers

Improved Deep Convolutional Neural Network For Online Handwritten Chinese Character Recognition using Domain-Specific KnowledgeWeixin Yang, Lianwen Jin, Zecheng Xie et al.2015 · IEEE International Conference on Document Analysis and Recognition · 91 citations In Library

A Residual-Attention Offline Handwritten Chinese Text Recognition Based on Fully Convolutional Neural NetworksYintong Wang, Yingjie Yang, Weiping Ding et al.2021 · IEEE Access · 21 citations In Library

Performance Evaluation of Advanced Deep Learning Architectures for Offline Handwritten Character RecognitionMoazam Soomro, Muhammad Ali Farooq, R. H. Raza2017 · International Conference on Frontiers of Information Technology · 18 citations In Library

Discriminative Deep Neural Network Model for In-air Handwritten Chinese Character RecognitionHu Deng, Xiwen Qu2025 · CNML · 0 citations In Library

Research on Offline Handwritten Chinese Character Recognition Based on Deep LearningQiuyun Hao, Xiaoming Wu, Sen-Yue Zhang et al.2019 · International Conference on Information and Software Technologies · 2 citations In Library

A new fully convolutional neural network architecture with text kernel for offline handwritten chinese text recognitionYuanyuan Li, Xinguang Yang, Zhiwei Ren2024 · Conference on Electronic Information Engineering and Data Processing · 1 citation In Library

Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New BenchmarkXu-Yao Zhang, Yoshua Bengio, Chenglin Liu2016 · Pattern Recognition · 292 citations In Library

Handwritten Chinese Characters Recognition Using Two-Stage Hierarchical Convolutional Neural NetworkNina Aleskerova, Aleksei Zhuravlev2020 · International Conference on Frontiers in Handwriting Recognition · 6 citations In Library

The Recognition and Implementation of Handwritten Character based on Deep LearningF. Dai, Zhongyong Ye, Xia Jin2019 · J. Robotics Netw. Artif. Life · 1 citation In Library

Deep Learning-Driven Approach for Handwritten Chinese Character ClassificationBoris Kriuk, Fedor Kriuk2024 · Doklady. Mathematics · 1 citation In Library

Patents near this paper

Apparatus For Recognition Of Handwritten Chinese CharactersUS 10,296,817 · GYRFALCON TECHNOLOGY INC. · 2019 ON-LINE PATTERN RECOGNITION SYSTEM FOR HAND-WRITTEN CHARACTERSUS 4,284,975 · NIPPON TELEGRAPH AND TELEPHONE CORPORATION · 1981 TIME DELAY NEURAL NETWORK FOR PRINTED AND CURSIVE HANDWRITTEN CHARACTER RECOGNITIONUS 5,105,468 · AMERICAN TELEPHONE AND TELEGRAPH COMPANY A CORPORATION OF NEW YORK · 1992 CHINESE CHARACTER HANDWRITING RECOGNITION SYSTEMUS 6,970,599 · AMERICA ONLINE, INC. · 2005 ON-LINE LEARNING FOR NEURAL NET-BASED CHARACTER RECOGNITION SYSTEMSUS 5,966,460 · XEROX CORPORATION · 1999

Source of record

arXiv