摘要
基于Radon变换在一定意义上具有能量特征,结合增强的步态能量图(EGEI),将两种形式的能量特征相融合来进行步态识别。对经过预处理后的周期图像合成EGEI,运用行列相结合的二维主成分分析((2D)2PCA)方法降低特征向量维数。同样,对步态序列图像进行Radon变换,构造周期模板后用主成分分析(PCA)方法降维。识别时将两种特征使用决策层融合的方法获得最终结果。通过在CASIA步态数据库上进行实验,证明以上方法具有较高的识别性能。
Based on Radon transform in a sense,with energy feature,combined with enhanced gait energy image,a novel gait recognition method about the fusion of energy representation of both of them was proposed.Feature extraction from EGEI which described the gait characteristics was obtained from periodic sequence images,while Radon transform of the gait image sequence from one cyclical gait character was portrayed by using template structure.Following these,feature reduction was effected by using two directional two dimensional principal component analysis((2D)2PCA) and principal component analysis(PCA) respectively.Fusion of multiple views as well as multiple-characteristics was accomplished in the final gait recognition stage.The proposed gait recognition was evaluated method on CASIA gait database,and the experimental results demonstrate that our approach has encouraging recognition performance.
出处
《微计算机信息》
2010年第34期231-233,共3页
Control & Automation
关键词
增强的步态能量图
RADON变换
行列相结合的二维主成分分析
主成分分析
决策层
enhanced gait energy image(EGEI)
Radon transformation
two directional two dimensional principal component analysis((2D)2PCA)
principal component analysis(PCA)