Facial contour labeling via congealing
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Face analysis using curve edge maps
ICIAP'11 Proceedings of the 16th international conference on Image analysis and processing - Volume Part II
Segmentation and labeling of face images for electronic documents
Expert Systems with Applications: An International Journal
Real-Time Facial Feature Tracking on a Mobile Device
International Journal of Computer Vision
Continuous regression for non-rigid image alignment
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Image and Vision Computing
Transfer learning with one-class data
Pattern Recognition Letters
A Comprehensive Survey to Face Hallucination
International Journal of Computer Vision
| Hi-index | 0.16 |
This paper proposes a discriminative framework for efficiently aligning images. Although conventional Active Appearance Models (AAMs)-based approaches have achieved some success, they suffer from the generalization problem, i.e., how to align any image with a generic model. We treat the iterative image alignment problem as a process of maximizing the score of a trained two-class classifier that is able to distinguish correct alignment (positive class) from incorrect alignment (negative class). During the modeling stage, given a set of images with ground truth landmarks, we train a conventional Point Distribution Model (PDM) and a boosting-based classifier, which acts as an appearance model. When tested on an image with the initial landmark locations, the proposed algorithm iteratively updates the shape parameters of the PDM via the gradient ascent method such that the classification score of the warped image is maximized. We use the term Boosted Appearance Models (BAMs) to refer to the learned shape and appearance models, as well as our specific alignment method. The proposed framework is applied to the face alignment problem. Using extensive experimentation, we show that, compared to the AAM-based approach, this framework greatly improves the robustness, accuracy, and efficiency of face alignment by a large margin, especially for unseen data.