Detecting Hands in Video Images using Scale Invariant Local Descriptors

J. Richarz, T. Pltz, and G.A. Fink (Germany)


hand detection, human-computer interaction, scale invariant features


In this paper, we describe our approach on hand detection in cluttered images using scale invariant features. We claim that, while modelling hands as a whole is bound to fail because of their strongly articulated nature, treating them as a collection of weakly connected characteristic regions seems promising. Different approaches to ļ¬nding and ro bustly modelling such regions - or local object descriptors - invariantly to scale and orientation of the object in ques tion have been proposed. As an example, we demonstrate our approach using the well-known scale-invariant feature transform (SIFT), combined with a region-based postpro cessing to eliminate false positives. We present detailed results on a large set of images from a realistic interaction scenario with a smart room.

Important Links:

Go Back