期刊文献+

基于卷积神经网络的小样本车牌号码识别方法研究

下载PDF
导出
摘要 随着汽车使用量的增多,车牌号码识别成为车辆信息管理的重要部分.神经网络在数字图像识别上存在训练和识别时间较长,准确率不够高的缺点.文章使用卷积神经网络LeNet-5模型识别车牌号码,通过实验数据对比,LeNet-5模型相比于经典的BP神经网络在识别速度和准确率上都有明显的提升.
出处 《商丘职业技术学院学报》 2020年第2期71-75,共5页 JOURNAL OF SHANGQIU POLYTECHNIC
基金 2018年度河南省科技计划项目“基于强度滤波器的紧邻多目标高效率技术研究”(182102210116)。
  • 相关文献

参考文献4

二级参考文献97

  • 1高珊,刘万春,朱玉文.基于SVM的车牌字符分割和识别方法[J].微电子学与计算机,2005,22(6):34-36. 被引量:12
  • 2PHAM D V. Online handwriting recognition using multi convo.lution neural networks [M]. Berlin Heidelberg: Springer,2012:310.319.
  • 3LECUN Y,BOTTOU L,BENGIO Y,et al. Gradient. basedlearning applied to document recognition [C]// Proceeding ofIEEE. USA:IEEE,1998:2278.2324.
  • 4SIMARD P Y,STEINKRAUS Dave,PLATT John. Best practicesfor convolutional neural networks applied to visual documentanalysis [C]// International Conference on Document Analysisand Recognition(ICDAR). Los Alamitos:IEEE Computer So.ciety,2003:958.962.
  • 5SERMANET P,CHINTALA S,LECUN Y. Convolutional neu.ral networks applied to house numbers digit classification [C]//International Conference on Pattern Recognition. [S.l.]:IEEE,2012:3288.3291.
  • 6LECUN Y,BOTTOU L,ORR G B,et al. Efficient BackPropin neural networks: tricks of the trade, LNCS [M]. Heidel.berg:Springer,1998,1524:9.50.
  • 7LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
  • 8HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets [J]. Neural Computation, 2006, 18(7): 1527-1554.
  • 9LEE H, GROSSE R, RANGANATH R, et al. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations [C]// ICML '09: Proceedings of the 26th Annual International Conference on Machine Learning. New York: ACM, 2009: 609-616.
  • 10HUANG G B, LEE H, ERIK G. Learning hierarchical representations for face verification with convolutional deep belief networks [C]// CVPR '12: Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2012: 2518-2525.

共引文献579

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部