首页> 外文期刊>International Journal of Applied Engineering Research >Handwritten Urdu Characters Recognition Using Multilayer Perceptron
【24h】

Handwritten Urdu Characters Recognition Using Multilayer Perceptron

机译:手写Urdu字符识别使用多层erceptron

获取原文
获取原文并翻译 | 示例
           

摘要

In recent years, Artificial Neural Networks are found to have a wide range of applications in many fields and Character recognition is one among them. In this paper, we intend to make use of artificial neural network in recognition of handwritten Urdu characters in isolated form with an aim of improving efficiency. The proposed method is based on the use of feed forward back propagation method to classify the Urdu characters. The Multilayer Perceptron neural network is trained using the Back Propagation algorithm in which handwritten Urdu letters represented in binary form are made ready as input to the neural network. An optimal architecture of the network with the limited sized training data is developed by balancing between model performance and training costs.
机译:近年来,发现人工神经网络在许多领域拥有广泛的应用,而字符识别是其中之一。 在本文中,我们打算利用人工神经网络,以识别孤立形式的手写Urdu字符,目的是提高效率。 该方法基于使用馈送前后传播方法来对URDU字符进行分类。 使用背部传播算法训练多层的Perceptron神经网络,其中以二进制形式表示的手写URDU字母准备好作为对神经网络的输入。 通过在模型性能和培训成本之间平衡,开发了具有有限尺寸培训数据的网络的最佳架构。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号