Ultrasonic face recognition algorithm based on principal component analysis

Aimed at multi-channel detection mode in ultrasonic detection face recognition system,the facial features are optimized from the perspective of data fusion.The data dimensionality reduction algorithm and feature extraction method are studied,which are based on principal component analysis.The effectiveness of the algorithm is proved.On the premise of ensuring the recognition rate over 80%,this algorithm,which is used to extract the features of 100 subjects' free expression,can significantly reduce the number of dimensions of the feature vectors up to 80% and improve the speed of system more than 85%.The experimental results show that the PCA algorithm can effectively reduce the dimension of features and improve the operation speed.