Active shape models—their training and application
Computer Vision and Image Understanding
A morphable model for the synthesis of 3D faces
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
IEEE Transactions on Pattern Analysis and Machine Intelligence
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Interpreting Face Images Using Active Appearance Models
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Lucas-Kanade 20 Years On: A Unifying Framework
International Journal of Computer Vision
Active Appearance Models Revisited
International Journal of Computer Vision
Evaluating Error Functions for Robust Active Appearance Models
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Pattern Recognition and Machine Learning (Information Science and Statistics)
Pattern Recognition and Machine Learning (Information Science and Statistics)
Generic vs. person specific active appearance models
Image and Vision Computing
Bayesian tangent shape model: Estimating shape and pose parameters via bayesian inference
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Image and Vision Computing
Generic active appearance models revisited
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Hi-index | 0.00 |
Active appearance models (AAMs) have demonstrated great utility when being employed for non-rigid face alignment/tracking. The ''simultaneous'' algorithm for fitting an AAM achieves good non-rigid face registration performance, but has poor real time performance (2-3fps). The ''project-out'' algorithm for fitting an AAM achieves faster than real time performance (200fps) but suffers from poor generic alignment performance. In this paper we introduce an extension to a discriminative method for non-rigid face registration/tracking referred to as a constrained local model (CLM). Our proposed method is able to achieve superior performance to the ''simultaneous'' AAM algorithm along with real time fitting speeds (35fps). We improve upon the canonical CLM formulation, to gain this performance, in a number of ways by employing: (i) linear SVMs as patch-experts, (ii) a simplified optimization criteria, and (iii) a composite rather than additive warp update step. Most notably, our simplified optimization criteria for fitting the CLM divides the problem of finding a single complex registration/warp displacement into that of finding N simple warp displacements. From these N simple warp displacements, a single complex warp displacement is estimated using a weighted least-squares constraint. Another major advantage of this simplified optimization lends from its ability to be parallelized, a step which we also theoretically explore in this paper. We refer to our approach for fitting the CLM as the ''exhaustive local search'' (ELS) algorithm. Experiments were conducted on the CMU MultiPIE database.