Nain Delphine, Haker Steven, Bobick Aaron, Tannenbaum Allen R
College of Computing, Georgia Institute of Technology, Atlanta, GA 30332-0280, USA.
Med Image Comput Comput Assist Interv. 2005;8(Pt 2):459-67. doi: 10.1007/11566489_57.
Shape priors attempt to represent biological variations within a population. When variations are global, Principal Component Analysis (PCA) can be used to learn major modes of variation, even from a limited training set. However, when significant local variations exist, PCA typically cannot represent such variations from a small training set. To address this issue, we present a novel algorithm that learns shape variations from data at multiple scales and locations using spherical wavelets and spectral graph partitioning. Our results show that when the training set is small, our algorithm significantly improves the approximation of shapes in a testing set over PCA, which tends to oversmooth data.
形状先验试图表示群体中的生物变异。当变异是全局性的时，主成分分析（PCA）可用于学习主要的变异模式，即使是从有限的训练集中。然而，当存在显著的局部变异时，PCA通常无法从小训练集中表示此类变异。为了解决这个问题，我们提出了一种新颖的算法，该算法使用球面小波和谱图划分从多个尺度和位置的数据中学习形状变异。我们的结果表明，当训练集较小时，我们的算法在测试集中对形状的近似比PCA有显著改进，PCA往往会过度平滑数据。
