Description: 基于BP神经网络识别字符.
BP神经网络算法是把一组样本输入输出问题转化为一个非线性优化问题，并通过梯度算法利用迭代运算求解权值的一种学习方法。采用BP网络进行分类，并附加线性感知器来实现单字符的有效识别，算法简便，识别率高，可适用于多种高噪声环境中的印刷体字符识别。-BP neural network based character recognition. BP neural network algorithm is a set of sample input and output is transformed into a nonlinear optimization problem, and through the use of iterative gradient algorithm for computing the value of a solution of the right way of learning. BP network used for classification, and additional linear perceptron to achieve an effective single-character recognition, the algorithm is simple, a high recognition rate, applicable to a wide range of high-noise environments print character recognition. Platform: |
Size: 113664 |
Author:吕寿鹏 |
Hits:
Description: The following Matlab project contains the source code and Matlab examples used for neural network programs. Perceptron LMS Feed Forward Back Propagation Character Recognition
The source code and files included in this project are listed in the project files section, please make sure whether the listed source code meet your needs there. Platform: |
Size: 13312 |
Author:sina |
Hits:
Search - perceptron character recognition matlab