| 基于深度卷积神经网络的手写哈萨克文字母识别方法 |
| |
| 引用本文： | 张晶,吴磊,贺建军,刘文鹏. 基于深度卷积神经网络的手写哈萨克文字母识别方法[J]. 大连民族学院学报, 2017, 19(5): 503-508 |
| |
| 作者姓名： | 张晶 吴磊 贺建军 刘文鹏 |
| |
| 作者单位： | 大连民族大学 信息与通信工程学院,辽宁 大连 116605 |
| |
| 基金项目： | 国家自然科学基金项目(61503058);辽宁省自然科学基金项目(201602190, 2015020099);大连市青年科技之星项目(2016RQ072); 中央高校基本科研业务费专项资金资助项目(DC201501055,DC201501060401)。 |
| |
| 摘 要： | 利用卷积神经网络在图像识别方面的优势,提出了一种基于深度卷积神经网的哈萨克手写字母识别方法(DCNN-KLR),成功建立了一种哈萨克手写文字识别模型。 与传统的方法(SVM+HOG)相比,不仅训练方便、速度快,而且提高了哈萨克手写文字的识别率。在5708个数据样本上进行训练和测试,将样本分为33类和100类,正确识别率分别达到93.29%和92.38%。
|
| 关 键 词： | 卷积神经网络 哈萨克文字母 字符识别 |
A Handwritten Kazakh Letter Recognition Method Based on Deep Convolutional Neural Network |
| |
| ZHANG Jing,WU Lei,HE Jian-jun,LIU Wen-peng. A Handwritten Kazakh Letter Recognition Method Based on Deep Convolutional Neural Network[J]. Journal of Dalian Nationalities University, 2017, 19(5): 503-508 |
| |
| Authors: | ZHANG Jing WU Lei HE Jian-jun LIU Wen-peng |
| |
| Affiliation: | School of Information and Communication Engineering, Dalian Minzu University,
Dalian Liaoning 116605, China |
| |
| Abstract: | This paper proposes a handwritten Kazakh letter recognition method based on deep convolutional neural network (DCNN-KLR). We exploit the advantages of the convolutional neural network in image recognition to build a model for handwritten Kazakh letter recognition. Compared to traditional method (SVM+HOG), this method is not only convenient and fast in training but also achieves a higher recognition accuracy. We use 5708 data samples for training and testing. The data is divided into 33 classes with 100 categories, and the highest recognition rate can be up to 93.29% and 92.38%. |
| |
| Keywords: | convolutional neural network handuritten Kazakh letters letter recognition |
|
| 点击此处可从《大连民族学院学报》浏览原始摘要信息 |
|
点击此处可从《大连民族学院学报》下载全文 |
|
