查询结果:   刘艳萍,杜秋晨,张进东.基于BP神经网络的纸币面向识别方法[J].计算机应用与软件,2015,32(11):176 - 179.
中文标题
基于BP神经网络的纸币面向识别方法
发表栏目
人工智能与识别
摘要点击数
1006
英文标题
RECOGNISING SURFACE AND DIRECTION OF BANKNOTES BASED ON BPNN
作 者
刘艳萍 杜秋晨 张进东 Liu Yanping Du Qiuchen Zhang Jindong
作者单位
河北工业大学信息工程学院 天津 300000 北京泰德瑞普科技有限公司 北京 100000    
英文单位
School of Information Engineering,Hebei University of Technology,Tianjin 300000,China Beijing Tiderip Technologies Co., Ltd., Beijing 100000,China    
关键词
纸币面向 图像预处理 神经网络 量化共轭梯度法
Keywords
Banknote surface and direction Image preprocess Neural network Scaled conjugate gradient (SCG)
基金项目
作者资料
刘艳萍,教授,主研领域:DSP技术及FP-GA技术。杜秋晨,硕士生。张进东,工程师。 。
文章摘要
纸币面向识别是纸币识别的基础,传统的纸币面向识别方法是人工提取特征,对于污损严重的纸币图像识别效率不高。针对传统方法的缺点,提出一种针对纸币图像的预处理方法。使用基于改进的BP神经网络的纸币面向识别方法,采用对纸币图像分块取平均值的方法提取特征,用量化共轭梯度法进行神经网络的训练,并且在TMS320DM648上进行实现。实验结果表明,这种方法完成纸币图像预处理和面向识别的时间不超过25 ms,准确率高于99%,具有计算量小、识别结果正确率高等优点。
Abstract
Banknote recognition in regard to surface and direction is the basis of banknote recognition. Traditional banknotes recognition method extracts the features of surface and direction of banknote manually, which has low recognition rate on seriously defaced banknote images. For the shortcoming of traditional methods, we proposed a new preprocessing method for banknote images. We used the improved BP neural network-based banknotes surface and direction recognition method, extracted features by the method of taking the mean of banknote image blocks, and used scaled conjugate gradient method to train neural networks, then implemented the new method on TMS320DM648. Experimental results showed that this method completed the banknote image preprocessing and surface and direction recognition within 25 ms in time and its accuracy was higher than 99%, it had the advantages of small computation load and high recognition accuracy rate.
下载PDF全文