EXTRA: An Extended Radial Mean Response Pattern for Hand Gesture Recognition

Abstract

Hand gesture recognition (HGR) has gained significant attention in recent year due to its varied applicability and ability to interact with machines efficiently. Hand gestures provide a way of communication for hearing-impaired persons. The HGR is a quite challenging task as its performance is influenced by various aspects such as illumination variations, cluttered backgrounds, spontaneous capture, multi-view etc. Thus, to resolve these issues in this paper, we propose an extended radial mean response (EXTRA) pattern for hand gesture recognition. The EXTRA pattern encodes the intensity variations by establishing a reconciled relationship between local neighboring pixels located at two radials r1 and r2. The gradient information between radials preserves the transitional texture that enhances the robustness to deal with illuminations changes. Moreover, the EXTRA pattern holds extensive radial information, thus it can conserve both high level and micro level edge variations that filter hand posture texture from the cluttered background. Furthermore, the mean responsive relationship between adjacency radial pixels improves robustness to noise conditions. The proposed technique is evaluated on three standard datasets viz NUS hand posture dataset-I, MUGD and Finger Spelling dataset. The experimental results and visual representations show that the proposed technique performs better than the existing algorithms for the purpose intended.