摘要
在对3种数据降维技术进行了比较研究的基础上,提出一种基于主成分分析(PCA)和BP神经网络的车标识别算法.首先,利用PCA方法获得特征车标;然后,将待识别车标投影到特征车标张成的子空间;最后,通过BP神经网络进行车标识别.实验结果表明,该算法能有效提高车标的识别率,对光照和噪声有很强的鲁棒性.
Based on principal component analysis,the vehicle logo recognition algorithm is proposed in this paper,which is on the basis of comparative data dimension reduction methods.Firstly,eigen-vehicle-logos is obtained by using principal component analysis.Secondly,projection coordinates on the eigen-vehicle-logos subspace of the known samples are used as the features of vehicle logo recognition.Finally,according to the projection coordinates of the unknown sample,vehicle logo types are recognized by BP neural network.The practical experiment results show that the proposed method can increase the recognition rate and reduce the computing cost greatly,and it is robust to noises and illumination variation.
出处
《辽宁师范大学学报（自然科学版）》
CAS
2010年第2期179-184,共6页
Journal of Liaoning Normal University:Natural Science Edition
基金
辽宁省博士科研启动基金项目(20061052)
