Granular computing for gait recognition through singular spectrum analysis

Gait Recognition is a biometric application that aims to identify a person by analyzing his/her gait. It is based on the fact that people often feel that they can identify a familiar person from afar simply by recognizing the way the person walks. In this paper, a Granular Computing approach is applied to the accelerometers signals obtained from gait. This approach involves information granules based on density measures and collected from a reconstructed attractor filtered using Singular Spectrum Analysis. Granular computing allows to recognize interesting regularities in the data at different levels of granularity. The performance of the method is evaluated on a set of 12 people. The results of this evaluation is presented and analyzed.