Convolutional Neural Networks for the Recognition of Malayalam Characters

机译：卷积神经网络，用于识别Malayalam字符

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Optical Character Recognition (OCR) has an important role in information retrieval which converts scanned documents into machine editable and searchable text formats. This work is focussing on the recognition part of OCR. LeNet-5, a Convolutional Neural Network (CNN) trained with gradient based learning and backpropagation algorithm is used for classification of Malayalam character images. Result obtained for multi-class classifier shows that CNN performance is dropping down when the number of classes exceeds range of 40. Accuracy is improved by grouping misclassified characters together. Without grouping, CNN is giving an average accuracy of 75% and after grouping the performance is improved upto 92%. Inner level classification is done using multi-class SVM which is giving an average accuracy in the range of 99-100%.

机译：光学字符识别（OCR）在信息检索中具有重要作用，它将扫描文档转换为机器可编辑和可搜索的文本格式。这项工作主要关注OCR的识别部分。 LENET-5，基于梯度的学习和BackProjagation算法训练的卷积神经网络（CNN）用于Malayalam字符图像的分类。多级分类器获得的结果表明，当类的数量超过40的范围时，CNN性能正在下降。通过将错误分类的字符分组在一起，提高了准确性。在没有分组的情况下，CNN的平均精度为75％，分组后，性能提高到92％。内部级别分类是使用多级SVM完成的，该SVM在99-100％的范围内提供平均精度。

著录项

来源
《International Conference on Frontiers of Intelligent Computing : Theory and Applications》|2014年||共8页
会议地点
作者
R. Anil; K. Manjusha; S. Sachin Kumar; K. P. Soman;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类 TP301.4-532;
关键词
Optical Character Recognition (OCR); Deep learning; Multi-stage classification; Convolutional Neural Network (CNN); Gradient based learning; Backpropagation; Multiclass SVM;

机译：光学字符识别（OCR）;深度学习;多级分类;卷积神经网络（CNN）;基于梯度的学习;BackPropagation;多牌SVM;

相似文献

外文文献
中文文献
专利

1. Integrating scattering feature maps with convolutional neural networks for Malayalam handwritten character recognition [J] . K. Manjusha, M. Anand Kumar, K. P. Soman International Journal on Document Analysis and Recognition . 2018,第3期

机译：结合散射特征图和卷积神经网络进行马拉雅拉姆语手写字符识别
2. Freeman Code Based Online Handwritten Character Recognition for Malayalam using Backpropagation Neural Networks [J] . Amritha Sampath, Tripti C, Govindaru V Advanced Computing: an International Journal . 2012,第4期

机译：基于反向传播神经网络的基于Freeman代码的马拉雅拉姆语在线手写字符识别
3. Towards Directing Convolutional Neural Networks Using Computational Geometry Algorithms: Application to Handwritten Arabic Character Recognition [J] . Mohsine Elkhayati, Youssfi Elkettani Advances in Science, Technology and Engineering Systems . 2020,第5期

机译：使用计算几何算法指导卷积神经网络：应用于手写的阿拉伯语字符识别
4. Convolutional Neural Networks for the Recognition of Malayalam Characters [C] . R. Anil, K. Manjusha, S. Sachin Kumar, International Conference on Frontiers of Intelligent Computing : Theory and Applications . 2014

机译：卷积神经网络，用于识别Malayalam字符
5. Facial Expression Recognition in the Wild Using Convolutional Neural Networks [D] . Farzaneh, Amir Hossein. 2020

机译：使用卷积神经网络野外的面部表情识别
6. Handwritten Bangla Character Recognition Using the State-of-the-Art Deep Convolutional Neural Networks [O] . Md Zahangir Alom, Paheding Sidike, Mahmudul Hasan, 2018

机译：使用最先进的深度卷积神经网络进行手写Bangla字符识别
7. Handwritten Hindi Character Recognition Using Layer-Wise Training of Deep Convolutional Neural Networks [O] . Abhishek Mehta, Subhashchandra Desai, Ashish Chaturvedi 2020

机译：手写的印度人字符识别使用深度卷积神经网络的层面训练

Convolutional Neural Networks for the Recognition of Malayalam Characters

摘要

著录项

相似文献

相关主题

期刊订阅