This paper introduces an improved texture mapping method to meet the future requirement of palm equipment applications. In the case of a lower resource configuration, because there is no requirement of the exact matching between model and texture, the facial texture is extracted from a single frontal face image through a few simple interactions. According to the feature points manual- marked on the texture image, the local texture coordinates can be auto-adjusted alternatively by the algorithm. Experimental results show that the algorithm is rapid, real-time and robust; and that the output model is photo-realistic.
Published in:
Image and Graphics, 2007. ICIG 2007. Fourth International Conference on
Date of Conference: 22-24 Aug. 2007