Feature extraction from faces using deformable templates
International Journal of Computer Vision
Probabilistic Visual Learning for Object Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Fast and Accurate Face Detector Based on Neural Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Non-Linear Dimensionality Reduction
Advances in Neural Information Processing Systems 5, [NIPS Conference]
Convolutional Face Finder: A Neural Architecture for Fast and Robust Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer Vision and Image Understanding - Special issue on eye detection and tracking
A robust and efficient algorithm for eye detection on gray intensity face
ICAPR'05 Proceedings of the Third international conference on Pattern Recognition and Image Analysis - Volume Part II
Multiple neural networks for facial feature localization in orientation-free face images
ANNPR'06 Proceedings of the Second international conference on Artificial Neural Networks in Pattern Recognition
Neural network cascade for facial feature localization
ANNPR'10 Proceedings of the 4th IAPR TC3 conference on Artificial Neural Networks in Pattern Recognition
Image and Vision Computing
Hi-index | 0.10 |
We present in this paper a new facial feature localizer. It uses a kind of auto-associative neural network trained to localize specific facial features (like eyes and mouth corners) in orientation-free face-images (i.e. images where faces are rotated in-plane and out-of-plane). To increase localization accuracy, two extensions are presented. The first one uses space displacement neural networks instead of classical, fully-connected networks. The second one combines several specialized networks trained to deal with each face orientation. A gating network is then used for combination. Finally, a two stage localizer is presented, which increases speed. Thorough evaluation is performed; including sensitivity to identity, noise and occlusions. The mean localization error (estimated on more than 4000 test images) is about 15% and the system can perform 40 images/s.