Title :
Automatic construction of active appearance models as an image coding problem
Author :
Baker, Simon ; Matthews, Iain ; Schneider, Jeff
Author_Institution :
Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
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.
Keywords :
gradient methods; image coding; learning (artificial intelligence); mesh generation; principal component analysis; PCA; active appearance models; automatic construction; base mesh vertices; energy minimizing image coding; gradient descent algorithm; training images; Active appearance model; Image coding; Image motion analysis; Motion estimation; Nonlinear optics; Optical sensors; Principal component analysis; Shape; Training data; Unsupervised learning; Index Terms- Active Appearance Models; automatic construction; image coding; inverse compositional image alignment; quadratic smoothness priors.; unsupervised learning; Algorithms; Artificial Intelligence; Cluster Analysis; Computer Graphics; Computer Simulation; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Information Storage and Retrieval; Models, Biological; Models, Statistical; Numerical Analysis, Computer-Assisted; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Subtraction Technique;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2004.77
