Baker Simon, Matthews Iain, Schneider Jeff
The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
IEEE Trans Pattern Anal Mach Intell. 2004 Oct;26(10):1380-4. doi: 10.1109/TPAMI.2004.77.
The automatic construction of Active Appearance Models (AAMs) is usually posed as finding the location of the base mesh vertices in the input training images. In this paper, we repose the problem as an energy-minimizing image coding problem and propose an efficient gradient-descent algorithm to solve it.
主动外观模型(AAMs)的自动构建通常被视为在输入训练图像中找到基础网格顶点的位置。在本文中,我们将该问题重新表述为一个能量最小化图像编码问题,并提出一种高效的梯度下降算法来解决它。