Three-Dimensional Face Recognition in the Presence of Facial Expressions: An Annotated Deformable Model Approach

By Ioannis A. Kakadiaris, Georgios Passalis, George Toderici, Mohammed N. Murtuza, Yunliang Lu, Nikolaos Karampatziakis, Theoharis Theoharis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007

517 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f921e6f5085f1ebbd8289081e499240a89bf6c43

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

A Survey on Human Motion Analysis from Depth Data (2013, background): “[82] non-rigidly align an annotated model to face meshes.”
Face recognition across pose: A review (2009, methodology): “Holistic approaches Principal component analysis [43, 74, 75], Fisher d iscriminant analysis [7] Artificial neural network (Convolutional Networks [ 47]) Line edge maps [27], directional corner point [28] Local approaches Template matching [16], Modular PCA [61] Elastic bunch graph matching [79], lo”
Multi-Factor Authentication: A Survey (2018, background): “Finally, the advancement of this system reached the point of recognizing the actual expressions of the user [88].”
Multilinear Wavelets: A Statistical Shape Space for Human Faces (2014, methodology): “[13] shares some similarities with our model, they use a fixed annotated face model, and wavelet transforms to compare facial geometry images.”
End-to-End 3D Face Reconstruction with Deep Neural Networks (2017, methodology): “For the AFM 3D facial shape model, we select 203 neutral 3D facial scans from the FRGC2 [21] and the BU-3DFE [31] databases and register them using the fitting algorithm proposed by [12] to build the shape basis.”
Random Forests for Real Time 3D Face Analysis (2012, background): “[35] non-rigidly align an annotated model to face meshes.”
Review of statistical shape spaces for 3D data with comparative analysis for human faces (2012, methodology): “n Faces global Morphable model (PCA) [7, 8, 9, 10] global Morphable model (PCA) [11] p global Multilinear model [12, 13, 14, 15] p part-based Part-based model [16, 17, 18] part-based Part-based model [19] p localized detail Hierarchical pyramids [20] local Local wavelet model [21] Bodies global PCA ”
KinectFaceDB: A Kinect Database for Face Recognition (2014, methodology): “One possible solution is to use deformable face models such as the annotated face model (AFM) [60] and the active appearance model (AAM) [85], [86] to overcome the local distortion problem caused by facial expression for the Kinect images.”