Similar handwritten Chinese character recognition based on deep neural networks with big data
The recognition rates of the traditional similar handwritten Chinese character recognition (SHCCR) systems are not very high due to the restriction of feature extraction methods.In order to improve the recognition accuracy,a new method based on deep neural networks (DNN) was proposed to learn effect...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2014-09-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.3969/j.issn.1000-436x.2014.09.019/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539708519186432 |
|---|---|
| author | Zhao YANG Da-peng TAO Shu-ye ZHANG Lian-wen JIN |
| author_facet | Zhao YANG Da-peng TAO Shu-ye ZHANG Lian-wen JIN |
| author_sort | Zhao YANG |
| collection | DOAJ |
| description | The recognition rates of the traditional similar handwritten Chinese character recognition (SHCCR) systems are not very high due to the restriction of feature extraction methods.In order to improve the recognition accuracy,a new method based on deep neural networks (DNN) was proposed to learn effective features automatically and conduct recog-nition.The method of how to generate similar handwritten Chinese character sets was introduced.The architecture of the DNN for SHCCR was presented.The performances with respect to different training data scale was compared.The ex-perimental results show that,DNN can learn features automatically and efficiently.The proposed DNN can achieve better performance comparing with support vector machine (SVM) and nearest neighbor classifier (1-NN) based on gradient features.Especially,with the increase of training data the recognition rate of DNN is improved observably,indicating that large training data is crucial for the performance of DNN. |
| format | Article |
| id | doaj-art-1910e958b9964561a20ef13e5e8d7209 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2014-09-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-1910e958b9964561a20ef13e5e8d72092025-01-14T06:44:04ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2014-09-013518418959684388Similar handwritten Chinese character recognition based on deep neural networks with big dataZhao YANGDa-peng TAOShu-ye ZHANGLian-wen JINThe recognition rates of the traditional similar handwritten Chinese character recognition (SHCCR) systems are not very high due to the restriction of feature extraction methods.In order to improve the recognition accuracy,a new method based on deep neural networks (DNN) was proposed to learn effective features automatically and conduct recog-nition.The method of how to generate similar handwritten Chinese character sets was introduced.The architecture of the DNN for SHCCR was presented.The performances with respect to different training data scale was compared.The ex-perimental results show that,DNN can learn features automatically and efficiently.The proposed DNN can achieve better performance comparing with support vector machine (SVM) and nearest neighbor classifier (1-NN) based on gradient features.Especially,with the increase of training data the recognition rate of DNN is improved observably,indicating that large training data is crucial for the performance of DNN.http://www.joconline.com.cn/zh/article/doi/10.3969/j.issn.1000-436x.2014.09.019/big datadeep neural networksdeep learningsimilar handwritten Chinese characters recognition |
| spellingShingle | Zhao YANG Da-peng TAO Shu-ye ZHANG Lian-wen JIN Similar handwritten Chinese character recognition based on deep neural networks with big data Tongxin xuebao big data deep neural networks deep learning similar handwritten Chinese characters recognition |
| title | Similar handwritten Chinese character recognition based on deep neural networks with big data |
| title_full | Similar handwritten Chinese character recognition based on deep neural networks with big data |
| title_fullStr | Similar handwritten Chinese character recognition based on deep neural networks with big data |
| title_full_unstemmed | Similar handwritten Chinese character recognition based on deep neural networks with big data |
| title_short | Similar handwritten Chinese character recognition based on deep neural networks with big data |
| title_sort | similar handwritten chinese character recognition based on deep neural networks with big data |
| topic | big data deep neural networks deep learning similar handwritten Chinese characters recognition |
| url | http://www.joconline.com.cn/zh/article/doi/10.3969/j.issn.1000-436x.2014.09.019/ |
| work_keys_str_mv | AT zhaoyang similarhandwrittenchinesecharacterrecognitionbasedondeepneuralnetworkswithbigdata AT dapengtao similarhandwrittenchinesecharacterrecognitionbasedondeepneuralnetworkswithbigdata AT shuyezhang similarhandwrittenchinesecharacterrecognitionbasedondeepneuralnetworkswithbigdata AT lianwenjin similarhandwrittenchinesecharacterrecognitionbasedondeepneuralnetworkswithbigdata |