A high-resolution 3D dynamic facial expression database

Liu, Yin; Chen, Xiaochen; Sun, Yi; Worm, Tony; Reale, Michael

doi:10.1109/afgr.2008.4813324

Cited by 418 publications

(274 citation statements)

References 27 publications

Supporting

Mentioning

272

Contrasting

Unclassified

Order By: Relevance

“…There are some existing 3-D facial databases, such as BU-3DFE [14], Bosphorus [15], ZJU-3DFED [16], BU-4DFE [17], etc. The main reason behind creating these databases is for the research of identity recognition and facial expression analysis.…”

Section: -D Dynamic Facial Databasementioning

confidence: 99%

Facial asymmetry analysis based on 3-D dynamic scans

Quan

Matuszewski

Shark

2012

2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

View full text Add to dashboard Cite

Abstract-Facial asymmetry is an important characteristic used in a number of applications. It plays a vital role in human perception of attractiveness and as such has been used in psychology including research on facial expressions evaluation as well as in plastic surgery and orthodontics. It has been also recognized as a biometric feature used for identification and has important applications in detection and quantification of medical disorders, including neurological conditions, such as stroke or Bell's palsy. The current methods for assessing facial asymmetry mainly rely on manual semi-automatic procedures which have significant limitations as they are subjective in nature. This paper presents a computer-based methodology of automatic facial asymmetry analysis which has been used for detection and quantification of facial dysfunctions. The method is based on dynamic 3-D scans of human faces. Using facial sequences from the Hi4D-ADSIP database, the preliminary evaluation results suggest that the proposed method is able to assist in quantification and diagnosis of facial dysfunctions for neurological patients.

show abstract

Section: -D Dynamic Facial Databasementioning

confidence: 99%

Facial asymmetry analysis based on 3-D dynamic scans

Quan

Matuszewski

Shark

2012

2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

View full text Add to dashboard Cite

show abstract

“…Note that spontaneous expression data are more difficult to classify than posed expression data. When the same approach was applied to the 3D posed dynamic facial expression database BU-4DFE [15], over 80% recognition rate was achieved for classifying six posed expressions. The performance degradation on classifying 3D spontaneous expressions is due to the complexity, mixture, and subtlety of the spontaneous expressions in the new database.…”

Section: ) Spontaneous Expression Classificationmentioning

confidence: 99%

“…Two-dimensional databases, such as RU-FACS [23] or Cohn-Kanade [2], are insufficient. The CMU Multi-PIE database [34], 3D dynamic AU database [35], Bosphorus database [9], KDEF [33], BU 3D Facial Expression Databases [14] [15], and ICT-3DRFE database [24] begin to address the need for 3D (or multi-view) data but are limited to posed facial behavior.…”

Section: Introductionmentioning

confidence: 99%

A high-resolution spontaneous 3D dynamic facial expression database

Zhang

Liu

Cohn

et al. 2013

2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

Self Cite

194

129

View full text Add to dashboard Cite

Abstract-Facial expression is central to human experience. Its efficient and valid measurement is a challenge that automated facial image analysis seeks to address. Most publically available databases are limited to 2D static images or video of posed facial behavior. Because posed and un-posed (aka "spontaneous") facial expressions differ along several dimensions including complexity and timing, well-annotated video of un-posed facial behavior is needed. Moreover, because the face is a three-dimensional deformable object, 2D video may be insufficient, and therefore 3D video archives are needed. We present a newly developed 3D video database of spontaneous facial expressions in a diverse group of young adults. Well-validated emotion inductions were used to elicit expressions of emotion and paralinguistic communication. Frame-level ground-truth for facial actions was obtained using the Facial Action Coding System. Facial features were tracked in both 2D and 3D domains using both personspecific and generic approaches. The work promotes the exploration of 3D spatiotemporal features in subtle facial expression, better understanding of the relation between pose and motion dynamics in facial action units, and deeper understanding of naturally occurring facial action.

show abstract

“…However, to the best of our knowledge, there is no 3D dynamic facial expression database publicly available. To investigate the usability and performance of the 3D dynamic facial models for FER, we created a dynamic 3D facial expression database [24] using the Dimensional Imaging's 3D dynamic capturing system [19]. The system captures a sequence of stereo images and produces the range models using a passive stereo-photogrammetry approach.…”

Section: Dynamic 3d Face Databasementioning

confidence: 99%

Facial Expression Recognition Based on 3D Dynamic Range Model Sequences

Sun

Liu

2008

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Traditionally, facial expression recognition (FER) issues have been studied mostly based on modalities of 2D images, 2D videos, and 3D static models. In this paper, we propose a spatio-temporal expression analysis approach based on a new modality, 3D dynamic geometric facial model sequences, to tackle the FER problems. Our approach integrates a 3D facial surface descriptor and Hidden Markov Models (HMM) to recognize facial expressions. To study the dynamics of 3D dynamic models for FER, we investigated three types of HMMs: temporal 1D-HMM, pseudo 2D-HMM (a combination of a spatial HMM and a temporal HMM), and real 2D-HMM. We also created a new dynamic 3D facial expression database for the research community. The results show that our approach achieves a 90.44% person-independent recognition rate for distinguishing six prototypic facial expressions. The advantage of our method is demonstrated as compared to methods based on 2D texture images, 2D/3D Motion Units, and 3D static range models. Further experimental evaluations also verify the benefits of our approach with respect to partial facial surface occlusion, expression intensity changes, and 3D model resolution variations.

show abstract

A high-resolution 3D dynamic facial expression database

Cited by 418 publications

References 27 publications

Facial asymmetry analysis based on 3-D dynamic scans

Facial asymmetry analysis based on 3-D dynamic scans

A high-resolution spontaneous 3D dynamic facial expression database

Facial Expression Recognition Based on 3D Dynamic Range Model Sequences

Contact Info

Product

Resources

About