A survey of approaches and challenges in 3D and multi-modal 3D + 2D face recognition

By Kevin W. Bowyer, Kyong I. Chang, Patrick J. Flynn. Computer Vision and Image Understanding, 2006

1,126 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/8e04d22f6e80a720c19bb557cc2ed197f16a151e

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

In Signal Processing

Citations in the corpus

Human computing and machine understanding of human behavior: a survey (2006, methodology): “The problem of face recognition has been tackled in various ways in 2D and 3D, using feature-, shape-, and appearance-based approaches as well as the combinations thereof [69], [31], [7].”
Deep Face Recognition: A Survey (2018, background): “Over the past few years, there have been several surveys on FR [222], [18], [3], [78], [136] and its subdomains, including illumination-invariant FR [234], 3D FR [136], pose-invariant FR [216] and so on.”
Handbook of Face Recognition, 2nd Edition (2011, background): “Most 3D face capture systems use the stereo or structured light approach [9].”
Three-Dimensional Face Recognition in the Presence of Facial Expressions: An Annotated Deformable Model Approach (2007, background): “0162-8828/07/$25.00 2007 IEEE Published by the IEEE Computer Society Bowyer et al. [ 1 ] and Chang et al. [3].”
KinectFaceDB: A Kinect Database for Face Recognition (2014, methodology): “previous studies (according to [59]) suggested to directly apply PCA on the 2.”
An Efficient Multimodal 2D-3D Hybrid Approach to Automatic Face Recognition (2007, methodology): “Bowyer et al. [7] state that multimodal face recognition outperforms both 2D and 3D face recognition alone.”
One-Shot Person Re-identification with a Consumer Depth Camera (2014, background): “The problem has also been tackled in a real-time setup [1, 16] and from a 3D perspective [6].”
Biometric Antispoofing Methods: A Survey in Face Recognition (2014, background): “Although in most cases no rigorous study has yet been carried out regarding their performance under liveness detection scenarios, such potentially useful mechanisms for face anti-spoofing would include: thermal imaging [153], [154], detection of the facial vein pattern [155], or 3D face acquisition ”
FRVT 2006 and ICE 2006 large-scale results (2007, neutral): “In general, sensors for 3D biometric imaging of faces are less mature than cameras for iris and face imaging [17].”
MPCA: Multilinear Principal Component Analysis of Tensor Objects (2008, background): “depth modes, in other words a 3rd-order tensor, has emerged as an important research direction [ 8 ]‐[10].”
3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey (2014, methodology): “quently used to assess the performance of each phase of a 3D object recognition system [3], [36], [37], [38].”
A Review of Point Cloud Registration Algorithms for Mobile Robotics (2015, background): “It took 12 years for a specialized survey of 3D registration in computer vision to appear [Bowyer et al., 2006].”
A Survey of Face Recognition Techniques (2009, background): “Comprehensive recent surveys of literature on 3D face recognition can be found in [251] and [252].”
Multiple Nose Region Matching for 3D Face Recognition under Varying Facial Expression (2006, background): “These results agree with previously reported observations: one, that ICP approaches outperform PCA approaches for 3D face recognition [10], [16], and, two, that expression variation degrades recognition performance [4], [5], [6], [7], [8], [17].”
On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes (2009, neutral): “Appearance based recognition has also been used in the case of 3D face recognition (Bowyer et al. 2006).”
SHREC 2007 3 D Shape Retrieval Contest (2006, background): “Each particular representation is suitable to cope with particular application needs.”