Construction and visualisation of three-dimensional facial statistics

This paper presents a new method for the construction of three-dimensional (3D) probabilistic Facial averages and demonstrates the potential for appli cations in clinical craniofacial research and patient assessment. Averages are constructed from a database of registered laser-range scans and photogr aphic images using feature based image warping. Facial features are extract ed using a template of connected contours, adapted to each subject interact ively using snakes. Each subject's images are warped to the average templat e shape acid the mean depth, colour and covariance matrix is found at each point. Statistical comparison of individuals with an average or between two averages is visualised by converting the probabilities to a coloured textu re map. (C) 2000 Elsevier Science Inland Ltd. All rights reserved.