Randomized decision forests for static and dynamic hand shape classification

This paper proposes a novel algorithm to perform hand shape classification using depth sensors, without relying on color or temporal information. Hence, the system is independent of lighting conditions and does not need a hand registration step. The proposed method uses randomized classification forests (RDF) to assign class labels to each pixel on a depth image, and the final class label is determined by voting. This method is shown to achieve 97.8% success rate on an American Sign Language (ASL) dataset consisting of 65k images collected from five subjects with a depth sensor. More experiments are conducted on a subset of the ChaLearn Gesture Dataset, consisting of a lexicon with static and dynamic hand shapes. The hands are found using motion cues and cropped using depth information, with a precision rate of 87.88% when there are multiple gestures, and 94.35% when there is a single gesture in the sample. The hand shape classification success rate is 94.74% on a small subset of nine gestures corresponding to a single lexicon. The success rate is 74.3% for the leave-one-subject-out scheme, and 67.14% when training is conducted on an external dataset consisting of the same gestures. The method runs on the CPU in real-time, and is capable of running on the GPU for further increase in speed.