A Stroke Based Representation of Indian Sign Language Signs Incorporating Global and Local Motion Information
Hand gesture recognition is the key technology to realize interaction of virtual reality. The accuracy and stability of the current hand gesture methods are still unsatisfactory due to various reasons. In YCbCr color space, the distribution of skin color has a good clustering. The paper uses skin detection in YCbCr color space for hand regional image, and proposes a hand gesture recognition method based on HU moments which have invariance property of translation, rotation and size. By extracting HU moments of the hand contour, this paper applies support vector machine (SVM) method to achieve the real-time hand gesture recognition. Experiments prove that the proposed method has very good precision and stability in virtual reality interaction.