HGR: Hand-Gesture-Recognition Based Text Input Method for AR/VR Wearable Devices
Nooruddin Nooruddin, Rahool Dembani, Nizamuddin Maitlo
Abstract
Hand gestures, whether static or dynamic, are a field of intense study and have several potential uses for human-computer interaction in real-time systems. Static and dynamic hand gestures are rudimentary ways for human-computer interaction. This paper presents a technique for the text input method which is hand-gesture-recognition based. This compact hand-based text input system is proposed for augmented reality (AR) and virtual reality (VR) devices. To recognize and classify hand gestures, the hand image is captured by a standard camera. After, the hand is segmented using background subtraction, and then the segmented hand gesture is input in the trained neural network for gesture recognition. Finally, hand movements are tracked and recorded using a convex hull algorithm. The corresponding written character is passed to a trained neural network. The proposed architecture is tested and the experimental results are compared with other methods, which showed that the proposed method performed better than traditional methods and achieved 96.12% accuracy, achieved accuracy is overall better than existing methods.