Expression, pose and occlusion resistant 3D facial landmarking

This paper contrasts two approaches to facial landmarking in 3D. The first approach is statistical in nature, and is based on modeling the shape of each feature with Gaussian mixtures. The advantage of this approach is the uniform treatment of landmarks. The second approach is a hybrid method to find the nose tip, which does not require learning, and is robust under adverse conditions. We demonstrate the accuracy and cross-database performance of these methods on FRGC and Bosphorus databases.

[1]  Patrick J. Flynn,et al.  Overview of the face recognition grand challenge , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[2]  L. Akarun,et al.  3D Facial Landmarking under Expression, Pose, and Occlusion Variations , 2008, 2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems.

[3]  Berk Gökberk,et al.  3D shape-based face recognition using automatically registered facial surfaces , 2004, ICPR 2004.

[4]  I. Ulusoy,et al.  3D face representation using scale and transform invariant features , 2008, 2008 IEEE 16th Signal Processing, Communication and Applications Conference.

[5]  Carlos D. Castillo,et al.  Facial Action Coding , 2009, Encyclopedia of Biometrics.

[6]  Albert Ali Salah,et al.  Incremental mixtures of factor analysers , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[7]  Albert Ali Salah,et al.  3D Facial Feature Localization for Registration , 2006, MRCS.

[8]  Mohammed Bennamoun,et al.  An Efficient Multimodal 2D-3D Hybrid Approach to Automatic Face Recognition , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Tieniu Tan,et al.  Combining local features for robust nose location in 3D facial data , 2006, Pattern Recognit. Lett..

[10]  Arman Savran,et al.  3D Face Recognition Benchmarks on the Bosphorus Database with Focus on Facial Expressions , 2008, BIOID.

[11]  Chitra Dorai,et al.  COSMOS - A Representation Scheme for 3D Free-Form Objects , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Ramesh C. Jain,et al.  Invariant surface characteristics for 3D object recognition in range images , 1985, Comput. Vis. Graph. Image Process..

[13]  K JainAnil,et al.  COSMOS-A Representation Scheme for 3D Free-Form Objects , 1997 .

[14]  Albert Ali Salah,et al.  Registration of three-dimensional face scans with average face models , 2008, J. Electronic Imaging.

[15]  Bülent Sankur,et al.  Robust facial landmarking for registration , 2007, Ann. des Télécommunications.

[16]  Arman Savran,et al.  Bosphorus Database for 3D Face Analysis , 2008, BIOID.

[17]  Berk Gökberk,et al.  3D shape-based face recognition using automatically registered facial surfaces , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..