Bosphorus Database for 3D Face Analysis

@inproceedings{Savran2008BosphorusDF,
  title={Bosphorus Database for 3D Face Analysis},
  author={Arman Savran and Nese Aly{\"u}z and Hamdi Dibeklioğlu and Oya Celiktutan and Berk G{\"o}kberk and B{\"u}lent Sankur and Lale Akarun},
  booktitle={BIOID},
  year={2008}
}
A new 3D face database that includes a rich set of expressions, systematic variation of poses and different types of occlusions is presented in this paper. This database is unique from three aspects: i) the facial expressions are composed of judiciously selected subset of Action Units as well as the six basic emotions, and many actors/actresses are incorporated to obtain more realistic expression data; ii) a rich set of head pose variations are available; and iii) different types of face… 
3D Facial Landmarking under Expression, Pose, and Occlusion Variations
TLDR
This paper assesses a fully automatic 3D facial landmarking algorithm that relies on accurate statistical modeling of facial features and introduces a curvature-based method for localizing the nose tip that is shown to perform well under severe conditions.
UPM-3D Facial Expression Recognition Database(UPM-3DFE)
TLDR
A 3D facial expression database named UPM-3DFE database was built, containing 350 face images of 50 persons, with each posing the six universally accepted facial expressions ie; happy, sad, angry, fear, disgust and surprise.
A Novel Expression Deformation Model for 3D Face Recognition
TLDR
Given a training set of non-neutral and neutral 3D face scan pairs from the same subject, a set of Fourier seriesients for each face scan is reconstructed and PCA is applied to learn expression deformation patterns.
UMB-DB: A database of partially occluded 3D faces
TLDR
The UMB-DB 3D face database has been built to test algorithms and systems for3D face analysis in uncontrolled and challenging scenarios, in particular in those cases where faces are occluded.
3D Assisted Face Recognition: Dealing With Expression Variations
TLDR
This paper proposes an analysis-by-synthesis-based scheme, in which a number of synthetic face images with different expressions are produced, and significant improvements are achieved in face recognition accuracies, for each database and algorithm.
4DFAB: A Large Scale 4D Database for Facial Expression Analysis and Biometric Applications
TLDR
4DFAB is a new large scale database of dynamic high-resolution 3D faces (over 1,800,000 3D meshes) that can be used for both face and facial expression recognition, as well as behavioural biometrics.
Nasal Region-Based 3D Face Recognition under Pose and Expression Variations
TLDR
This work proposes a fully automatic pose and expression invariant part-based 3D face recognition system based on pose correction and curvature-based nose segmentation, and shows that the utilization of anatomically-cropped nose region increases the recognition accuracy up to 94.10 per cent.
Part-based registration for expression resistant 3D face recognition
TLDR
A new 3D face database is presented which is collected for studies on expression analysis and on face recognition in the presence of facial expression and a new3D face registration and recognition method based on facial regions is proposed.
About 3D Faces
TLDR
This Chapter introduces the general and main methodologies for 3D face data acquisition and preprocessing, also presenting some 3D benchmark databases and performance indicators used for evaluation and comparison.
Real-time Expression Recognition from Dynamic Sequences of 3D Facial Scans
TLDR
An original approach is proposed that relies on automatically extracting a set of 3D facial points, and modeling their mutual distances along time to obtain effective results with the clear advantage of an implementation that fits to real-time constraints.
...
...

References

SHOWING 1-10 OF 25 REFERENCES
3D Face Recognition Performance under Adversarial Conditions
TLDR
A campaign to build a 3D face database including systematic variation of poses, different types of occlusions, and a rich set of expressions is conducted to enable various research paths from face recognition to facial landmarking and to expression estimation.
Robust 2D/3D Face Landmarking
TLDR
This work evaluates the contributions to the accuracy of facial feature localization of graph-based methods and of joint usage of 2D and 3D information for feature localization.
A 3D facial expression database for facial behavior research
TLDR
This is the first attempt at making a 3D facial expression database available for the research community, with the ultimate goal of fostering the research on affective computing and increasing the general understanding of facial behavior and the fine 3D structure inherent in human facial expressions.
Multi-attribute robust facial feature localization
TLDR
This paper focuses on the reliable detection of facial fiducial points, such as eye, eyebrow and mouth corners, and explores the potential of several feature modalities, namely, gabor wavelets, independent component analysis (ICA), non-negative matrix factorization (NMF), and discrete cosine transform (DCT), both singly and jointly.
Face verification from 3D and grey level clues
Using a Multi-Instance Enrollment Representation to Improve 3D Face Recognition
TLDR
This paper examines a multi-instance enrollment representation as a means to improve the performance of a 3D face recognition system and shows that using a gallery comprised of multiple expressions offers consistently higher performance than using any single expression.
Robust 3D Face Recognition Using Learned Visual Codebook
TLDR
A novel learned visual code-book (LVC) for 3D face recognition is proposed, which encompasses the efficiency of Gabor features for face recognition and the robustness of texton strategy for texture classification simultaneously.
Non-rigid registration of 3D surfaces by deformable 2D triangular meshes
  • A. Savran, B. Sankur
  • Computer Science
    2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
  • 2008
TLDR
A new automatic surface registration method which utilizes both attraction forces originating from geometrical and textural similarities, and stresses due to non-linear elasticity of the surfaces, which allows it to handle large deformations, which can be essential for facial expressions.
View dependence of complex versus simple facial motions
TLDR
The viewpoint dependency of complex facial expressions versus simple facial motions (so-called “action units”) is investigated to shed light on the cognitive processes underlying the processing of complex and simple facial motion for expression recognition.
...
...