Research for automatic recognition for vehicle based on improved BP network

Author

Wang, Zhiwen ; Li, Shaozi

Author_Institution

Dept. of Comput. & Eng., Guangxi Univ. of Technol., Liuzhou, China

Volume

3

fYear

2010

Firstpage

105

Lastpage

108

Abstract

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.

Keywords

backpropagation; edge detection; feature extraction; genetic algorithms; image classification; image segmentation; learning (artificial intelligence); traffic engineering computing; BP neural network; automatic vehicle recognition; feature extraction; genetic algorithm; learning algorithm; momentum; vehicle image segmentation; wavelet multiscale edge detection; Vehicles; BP network; Genetic algorithm; invariant Quadrature automatic recognition for vehicle; momentum;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Communication Technologies in Agriculture Engineering (CCTAE), 2010 International Conference On

Print_ISBN

978-1-4244-6944-4

Type

conf

DOI

10.1109/CCTAE.2010.5544165

Filename

5544165