| 五种人民币序列号识别算法抗噪能力比较 |
| |
| 引用本文： | 刘小波,崔桂华,李长军,钱祥忠,严旭.五种人民币序列号识别算法抗噪能力比较[J].计算机系统应用,2016,25(8):29-34. |
| |
| 作者姓名： | 刘小波 崔桂华 李长军 钱祥忠 严旭 |
| |
| 作者单位： | 温州大学 物理与电子信息工程学院, 温州 325035,温州大学 物理与电子信息工程学院, 温州 325035,温州大学 物理与电子信息工程学院, 温州 325035,温州大学 物理与电子信息工程学院, 温州 325035,温州大学 物理与电子信息工程学院, 温州 325035 |
| |
| 基金项目： | 国家自然科学基金（61501331，61178053，61575090） |
| |
| 摘 要： | 为了比较不同的人工神经网络算法识别人民币序列号的性能，研究了离散Hopfield神经网络、BP神经网络、PNN神经网络、GRNN神经网络、SVM神经网络等五种算法的训练耗时、识别速度、识别率和抗噪声能力. 研究结果表明，在五种算法中BP算法的综合表现最差，其次为SVM和Hopfield算法，而PNN和GRNN算法表现最好，不仅识别率最高、训练和识别时间最短，而且具有较强的抗噪声能力.
|
| 关 键 词： | 神经网络 字符识别 Hopfield BP PNN GRNN SVM |
| 收稿时间： | 2015/12/16 0:00:00 |
| 修稿时间： | 2016/1/21 0:00:00 |
Comparison of Five Algorithms for Recognizing Serlal Number of Rmb Banknote |
| |
| LIU Xiao-Bo,CUI Gui-Hu,LI Chang-Jun,QIAN Xiang-Zhong and YAN Xu.Comparison of Five Algorithms for Recognizing Serlal Number of Rmb Banknote[J].Computer Systems& Applications,2016,25(8):29-34. |
| |
| Authors: | LIU Xiao-Bo CUI Gui-Hu LI Chang-Jun QIAN Xiang-Zhong and YAN Xu |
| |
| Affiliation: | College of Physics and Electronic Information Engineering, Wenzhou University, Wenzhou 235035, China,College of Physics and Electronic Information Engineering, Wenzhou University, Wenzhou 235035, China,College of Physics and Electronic Information Engineering, Wenzhou University, Wenzhou 235035, China,College of Physics and Electronic Information Engineering, Wenzhou University, Wenzhou 235035, China and College of Physics and Electronic Information Engineering, Wenzhou University, Wenzhou 235035, China |
| |
| Abstract: | To investigate the performance of different neural network algorithms in identifying serial number of RMB banknote, the training speed, recognizing speed and rate, and ability of anti-noise of five neural network algorithms, including the discrete Hopfield neural network, BP neural network, PNN neural network, GRNN neural network and SVM neural network, are studied. The simulation results show that amongst the five algorithms, BP performs worst, followed by SVM and Hopfield, with PNN and GRNN performs best, not only gives the higher recognition rate, shorter training and recognition time, but also is more robust to noise. |
| |
| Keywords: | neural network character recognition Hopfield BP PNN GRNN SVM |
|
| 点击此处可从《计算机系统应用》浏览原始摘要信息 |
|
点击此处可从《计算机系统应用》下载全文 |
|
