Automatic Interpretation and Coding of Face Images Using Flexible Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multidimensional Morphable Models: A Framework for Representing and Matching Object Classes
International Journal of Computer Vision
Generalized Image Matching: Statistical Learning of Physically-Based Deformations
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Elastic Model Based Non-rigid Registration Incorporation Statistical Shape Information
MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
Learning novel views to a single face image
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
Journal of Cognitive Neuroscience
Efficient Facial Features Warping Using BSM (Bayesian Shape Model)
ICCSA '08 Proceedings of the international conference on Computational Science and Its Applications, Part II
Improving segmentation of the left ventricle using a two-component statistical model
MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Hi-index | 0.00 |
We propose a model of appearance and a matching method which combines 'global' models (in which a few parameters control global appearance) with local elastic or optical-flow-based methods, in which deformation is described by many local parameters together with some regularisation constraints. We use an Active Appearance Model (AAM) as the global model, which can match a statistical model of appearance to a new image rapidly. However, the amount of variation allowed is constrained by the modes of the model, which may be too restrictive (for instance when insufficient training examples are available, or the number of modes is deliberately truncated for efficiency or memory conservation). To compensate for this, after global AAM convergence, we allow further local model deformation, driven by local AAMs around each model node. This is analogous to optical flow or 'demon' methods of non-linear image registration. We describe the technique in detail, and demonstrate that allowing this extra freedom can improve the accuracy of object location with only a modest increase in search time. We show the combined method is more accurate than either pure local or pure global model search.