A Semi-Automated Colour Predicate for Robust Skin Detection

In this paper, we present the details of a Visual System for Hand Pose Classification, utilising an adaptation of the traditional Colour Predicate approach to skin detection, 1st and 2nd Order Central Moments and Principal Component Analysis. Additionally, discussed are a proposed semi-automated method for the training of the Predicate, in which a simplified logarithmic hue is used to threshold the training images rather than requiring the user to manually mark regions of interest. 1 [email protected] Department of Computer Science, University of Auckland Private Bag 92019, Auckland, New Zealand 2 [email protected] Department of Computer Science, University of Auckland Private Bag 92019, Auckland, New Zealand You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the CITR Tamaki web site under terms that include this permission. All other rights are reserved by the author(s). A Semi-Automated Colour Predicate for Robust Skin Detection Gareth Barton and Patrice Delmas Department of Computer Science, University of Auckland Private Bag 92019, Auckland, New Zealand [email protected], [email protected]