A Grassmann graph embedding framework for gait analysis

Abstract

Gait recognition is important in a wide range of monitoring and surveillance applications. Gait information has often been used as evidence when other biometrics is indiscernible in the surveillance footage. Building on recent advances of the subspace-based approaches, we consider the problem of gait recognition on the Grassmann manifold. We show that by embedding the manifold into reproducing kernel Hilbert space and applying the mechanics of graph embedding on such manifold, significant performance improvement can be obtained. In this work, the gait recognition problem is studied in a unified way applicable for both supervised and unsupervised configurations. Sparse representation is further incorporated in the learning mechanism to adaptively harness the local structure of the data. Experiments demonstrate that the proposed method can tolerate variations in appearance for gait identification effectively.

On Biometrics With Eye Movements

“…For instance, it may depend on illumination and a subject's pose whether face images are applicable, and the dryness or cleanliness of the fingertips may determine whether good fingerprint images can be obtained. For every modality, various shortcomings are recognized [13]. Thus, novel modalities have been introduced in recent years.…”

“…Typically, these are physiological signals measured from subjects, such as EEG, ECG, and voice signals [12]. Furthermore, gait [12,13] is an interesting alternative that is recognized from video streams of walking subjects. The use of EEG, ECG, and voice signals as biometric techniques may be quite difficult because they are not easy to interpret and may vary depending on the circumstances.…”