Hand detection for contactless biometrics identification

Julien Doublet (1) , Olivier Lepetit (1) , Marinette Revenu (2)

1 FT R&D - France Télécom Recherche & Développement
2 Equipe Image - Laboratoire GREYC - UMR6072

In this paper, we present a new hand detection system based on a combination of skin color modelling and active shape model. Skin color distribution specified by a multiresolution neural network constrains active shape model evolutions on skin objects. We present the skin color detection performances of this near real time system on many color spaces and show that a combination of skin color and active shape model increase robustness and accuracy of hand detection in complex images.

Mots clés: Image Processing; Skin Detection; Active Shape Model; Machine Learning; Biometrics

Domaines: Algorithme et structure de données [cs.DS]; Traitement des images [eess.IV]

Julien Doublet, Olivier Lepetit, Marinette Revenu. Hand detection for contactless biometrics identification. COGIS, 2006, Paris, France. 6 p. ⟨hal-00090702⟩