基于随机非负独立元分析的掌纹识别

提出运用随机非负独立元分析（SN—ICA）的新方法进行掌纹识别。为了减少计算量，运用SN-ICA算法前，先采用主元分析（PCA）算法去除掌纹图像的二阶统计特征相关性，其余的高阶非负统计特征由SN-ICA分离。首先用PCA和SN-ICA提取投影向量，然后将训练图像和待识别图像向投影向量上投影得到低维特征向量，最后计算特征...

Palmprint recognition based on stochastic non-negative independent component analysis

A new palmprint recognition method based on stochastic non-negative independent component analysis(SN-ICA) is proposed.In order to reduce computational complexity,the principal component analysis(PCA) is used to eliminate the second-order dependencies in the palmprint images.The remaining higher-order dependencies are separated by SN-ICA.First,the PCA and SN-ICA are applied to extract the projection vectors.Then the training images and test images are projected onto the projection vectors to get the palmprint feature vectors.Finally,the cosine distance between two feature vectors is calculated to match palmprint.The new algorithm is tested in PolyU plmprint database.The results show that compared with principal component analysis(PCA),two-dimensional principal component analysis(2D-PCA),independent component analysis(ICA) and two-dimensional independent component analysis(2D-ICA),the recognition rate of the new algorithm is the highest which is 98.95%,and the total time for feature extraction and matching is 0.564 s,so it meets the real-time system specification.