【摘要】 基于BP神经网络原理对汽车牌照中数字与英文字母进行了识别.分析了汽车牌照图像的识别处理过程,提出一种将大量模式分成许多小模式组的方法,研究了学习速率、误差精度与隐含层节点数之间的关系.实验结果表明所设计的汽车牌照神经网络识别系统能够较好地识别汽车牌照字符.更多还原

【Abstract】 Based on the BP neural network,the recognitions of the numbers and letters in the (autocard) are made. The total transaction process is analyzed.A method of dividing a large number of models into some small groups is put forward and the relations among the study rate, error precision and nodes of the hidden layer are studied.The results show that the autocard characters can be well recognized through the designed BP network.更多还原