一种基于RBF神经网络的英文字符识别方法

New Approach to English Character Recognition Based on RBF Neural Network

提出了一种基于RBF神经网络的英文字符识别方法。该方法首先提取字符的结构特征和统计特征,以它们作为神经网络的输入向量,然后用RBF神经网络进行识别。使用了高斯函数作为神经网络的激励函数,并以最小二乘准则对字符进行识别。对字符样本的识别结果显示,此方法在识别错误率和识别效率等方面均有很好的效果。

A new approach to English character recognition based on RBF neural network is presented . By this approach, the structural features and statistical features of characters are firstly extracted, then they are normalized to the input vector of neural network, and RBF neural network is used for recognition. Gauss function is used as neural network's inspirit function , and least square rule is used to recognize the character. Recognition result based on the character sample shows that the method achieves excellent performance in terms of recognition error rates and recognition efficiency.