Abstract
Algorithms incorporating 3D information have proven to be superior to purely 2D approaches in many areas of computer vision in- cluding face biometrics and recognition. Still, the range of methods for feature extraction from 3D surfaces is limited. Very popular in 2D image analysis, active contours have been generalized to curved surfaces only recently. Current implementations require a global surface parametrisa- tion. We show that a balloon force cannot be included properly in existing methods, making them unsuitable for applications with noisy data. To overcome this drawback we propose a new algorithm for evolving geo- desic active contours on implicit surfaces. We also introduce a new nar- rowband scheme which results in linear computational complexity. The performance of our model is illustrated on various real and synthetic 3D surfaces.