摘要
FBP和FCNN网络是模式识别中应用最为广泛的两种神经网络,本文将这两种网络应用于车型识别,分别建立了车型识别模型。利用混沌对初值的极端敏感依赖提出了FCNN网络算法,通过对车型图像数据库进行仿真实验,对比分析它们各自的识别率和泛化能力等性能指标,证明了FCNN网络算法的有效性。
FBP and FCNN neural networks are widely applied in pattern recognition. These two methods are used for vehicle model recogni- tion, and their face recognition models are established respectively. Basd on analyzing the theory of fuzzy neural network recognition, simulation experiments are carried out using vehicle model recognition database. The characteristics of two neural networks, such as recognition rate and generalization ability are discussed, which should be considered in the practical applications of these two types of neural networks. Finally we prove FCNN neural networks are effective.
出处
《世界科技研究与发展》
CSCD
2009年第5期814-816,857,共4页
World Sci-Tech R&D
