A simple shape-based approach to hand gesture recognition

It is possible to recognize and classify ten hand gestures based solely on their shapes. This paper discusses a simple recognition algorithm that uses three shape-based features of a hand to identify what gesture it is conveying. The overall algorithm has three main steps: segmentation, feature calculation, and classification. The algorithm takes an input image of a hand gesture and calculates three features of the image, two based on compactness, and one based on radial distance. The parameters found in the classification step were obtained empirically using 200 hand images. The algorithm was tested on another 200 hand images, and was able to successfully classify 182 images, or with an overall success rate of 91 percent.