The performance of gait recognition systems are usually affected by clothing, carrying conditions, and other intraclass variations which are also referred to as "covariates". This paper proposes a supervised feature selection method which is able to select relevant features for human recognition to mitigate the impact of covariates and hence improve the recognition performance. The proposed method is evaluated using CASIA Gait Database (Dataset B) and the experimental results suggest that our method yields attractive results when compared to similar ones.
|Title of host publication||2014 26th International Conference on Microelectronics (ICM)|
|Place of Publication||Piscataway, NJ|
|Publication status||Published - 2014|