HMM-Based System for Recognizing Gestures in Image Sequences and Its Application in Continuous Gesture Recognition

In the article there is presented an efficient system for dynamic gesture recognition in movie sequences based on Hidden Markov Models. The system uses colour-based image segmentation methods and introduces high-dimensional feature vectors to more accurately describe hand shape in the picture. It also utilizes a-priori knowledge on gestures structure in order to allow effective dimensionality reduction, hand posture classification and detection schemes. There is also presented a comparison of the algorithm proposed with competitive methods and argued a particular suitability of the system for the situations when only a small amount of training data is available.