Research for Automatic Recognition for Vehicle Based on improved BP Network

摘要：

In this article, BP network learning algorithm is improved by using momentum and genetic algorithm after analyzing the defects of the BP network learning algorithm. Wavelet multi-scale edge detection is used to segment the vehicle image and extract the feature of the image. And then the features of moment invariants and improved BP neural network models are used to automatically recognize and classify the vehicle image. This algorithm can improve the speed and accuracy for the automatic identification and classification of the vehicle.

关键词： BP network momentum Genetic algorithm invariant Quadrature automatic recognition for vehicle

作者: Zhiwen WANG Shaozi LI

作者单位: Department of Computer and Engineering Guangxi University of Technology,Liuzhou 545006, China Cognit Cognitive Science Department of Xiamen University, Xiamen, 361005, China

会议类型: 国际会议

会议名称: 2010 International Conference on Computer and Communication Technologies in Agriculture Engineering(计算机与通信技术在农业工程国际会议 CCTAE 2010)

会议地点: 成都

会议语种:英文

页码: 105-108

在线出版日期: 2010-06-12（万方平台首次上网日期，不代表论文的发表时间）