A study on footstep detection for personal recognition

Summary form only given. In this paper, personal recognition using the footstep is presented. The feature extraction of a footstep is investigated. If a footstep is discriminable, the application to various fields can be considered. We focus on recognizing a certain kind of footstep waveforms under the restricted condition. We propose a new methodology using feature parameters such as the peak frequency set by the mel-cepstrum analysis, the walking intervals and the similarity of spectrum envelope. It is shown for personal identification that the performance of the proposed method is effective.