Identity recognition of plantar pressure image based on compressed sensing

Herein, a new identity recognition method of plantar pressure image (PPI) was investigated based on compressed sensing. During the process of identity recognition, the PPIs were collected with platform system in normal walking speed. The sparse representation of PPI was then obtained according to the sparse basis (i.e., wavelet basis). Finally, measurement vectors were calculated by the Topelitz measurement matrix and the PPI was recognized by compressed sensing classifier. The results showed that the accuracy of identity recognition of PPI based on compressed sensing exceeded 97.76%, demonstrating the effectiveness and stability of the Topelitz-compressed sensing algorithm. Meanwhile, the method used in this study reduced the data storage amount and increased the real-time recognition during the PPI process.