Abstract
Robust vision-based hand pose estimation is highly sought but still remains a challenging task, due to its inherent difficulty partially caused by self-occlusion among hand fingers. In this paper, an innovative framework for real-time static hand gesture recognition is introduced, based on an optimized shape representation build from multiple shape cues. The framework incorporates a specific module for hand pose estimation based on depth map data, where the hand silhouette is first extracted from the extremely detailed and accurate depth map captured by a time-of-flight (ToF) depth sensor. A hybrid multi-modal descriptor that integrates multiple affine-invariant boundary-based and region-based features is created from the hand silhouette to obtain a reliable and representative description of individual gestures. Finally, an ensemble of one-vs.-all support vector machines (SVMs) is independently trained on each of these learned feature representations to perform gesture classification. When evaluated on a publicly available dataset incorporating a relatively large and diverse collection of egocentric hand gestures, the approach yields encouraging results that agree very favorably with those reported in the literature, while maintaining real-time operation.
Highlights
Automatic vision-based recognition of hand gestures has recently received a great deal of researchers’ attention in pattern recognition, computer vision, and biometrics communities, due to its potential applicability across a wide variety of applications, ranging from intelligent human-computer interfaces and human-machine communication to machine translation of sign languages of people with severe/profound speech and hearing impairments [1]
This paper proposes a real-time method for hand gesture recognition based on an optimized shape representation build from multiple shape cues
We propose to apply an ensemble of support vector machine (SVM) to hand gesture classification as a first step towards integration into a full gesture recognition framework
Summary
Automatic vision-based recognition of hand gestures has recently received a great deal of researchers’ attention in pattern recognition, computer vision, and biometrics communities, due to its potential applicability across a wide variety of applications, ranging from intelligent human-computer interfaces and human-machine communication to machine translation of sign languages of people with severe/profound speech and hearing impairments [1]. One finds that a significant body of existing work on hand gesture recognition mainly follows the typical steps of pattern analysis, starting with image preprocessing, segmentation, feature extraction, and classification [22,23,24].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have