Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Locating Facial Features in Image Sequences using Neural Networks
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
Real-Time Facial Analysis for Virtual Teleconferencing
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
An Automatic Construction of a Person's Face Model from the Person's Two Orthogonal Views
GMP '02 Proceedings of the Geometric Modeling and Processing — Theory and Applications (GMP'02)
Realistic 3D Face Modeling by Fusing Multiple 2D Images
MMM '05 Proceedings of the 11th International Multimedia Modelling Conference
Face Recognition Using Landmark-Based Bidimensional Regression
ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Face-tracking as an augmented input in video games: enhancing presence, role-playing and control
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
A Landmark Paper in Face Recognition
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
How effective are landmarks and their geometry for face recognition?
Computer Vision and Image Understanding
Journal of Cognitive Neuroscience
Robust shape-based head tracking
ACIVS'07 Proceedings of the 9th international conference on Advanced concepts for intelligent vision systems
Automatic 3D reconstruction for face recognition
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
| Hi-index | 0.00 |
Identifying landmark points in facial images is a very important task in computer vision and has several applications. Here we present a fast and robust algorithm capable of identifying a specific set of landmarks on face profile images. The algorithm is based on the local curvature of the profile contour and on the local analysis of the face features. In order to validate the approach, the algorithm has been tested on a set of images. Ground truth data on the real location of the landmarks are compared with the results of our algorithm. A percentage of 92% correct identification and a mean error of 3.5 pixels demonstrate the robustness of the approach.