3D facial expression recognition: A perspective on promises and challenges

Fang, Tianhong; Zhao, Xi; Ocegueda, Omar; Shah, Shishir K.; Kakadiaris, Ioannis A.

doi:10.1109/fg.2011.5771466

Cited by 69 publications

(38 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Incidentally, models provided in the testing database, BU-3DFE, are already rather well aligned, so we did not find appropriate to describe such a method in this paper. Numerous approaches have been proposed for this problem in 3D FER, as in [7] or [13].…”

Section: Overview Of the Proposed Approachmentioning

confidence: 99%

“…The current research on 3D FER has featured 2 main streams: feature-based approaches or model-based approaches [7]. Feature-based approaches are [8], [9], [10], [11], [12], [13] and [14].…”

Section: Introductionmentioning

confidence: 99%

“…Model-based approaches are [1], [15] and [7]. They generally fit a template 3D face model to analyze the deformations between a neutral state to an expressionnal state.…”

Section: Introductionmentioning

confidence: 99%

“…Using both asymmetric and symmetric formulations, they encoded identity and expression at the same time. [7] used the AFM, an annotated deformable Face Model. After a registration to the studied model, the face is represented into the conformal space, and a set of Point Distribution Models is established, using various surface descriptors (position, normals, curvature, wavelets...).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fully automatic 3D facial expression recognition using a region-based approach

Lemaire

Amor

Ardabilian

et al. 2011

Proceedings of the 2011 Joint ACM Workshop on Human Gesture and Behavior Understanding

View full text Add to dashboard Cite

Abstract-In this paper, we propose an holistic, fully automatic approach to 3D Facial Expression Recognition (FER). A novel facial representation, namely Differential Mean Curvature Maps (DMCMs), is proposed to capture both global and local facial surface deformations which typically occur during facial expressions. These DMCMs are directly extracted from 3D depth images, by calculating the mean curvatures thanks to an integral computation. To account for facial morphology variations, they are further normalized through an aspect ratio deformation. Finally, Histograms of Oriented Gradients (HOG) are applied to regions of these normalized DMCMs and allow for the generation of facial features that can be fed to the widely used Multiclass-SVM classification algorithm. Using the protocol proposed by Gong et al.[1] on the BU-3DFE dataset, the proposed approach displays competitive performance while staying entirely automatic.

show abstract

Section: Overview Of the Proposed Approachmentioning

confidence: 99%

“…The current research on 3D FER has featured 2 main streams: feature-based approaches or model-based approaches [7]. Feature-based approaches are [8], [9], [10], [11], [12], [13] and [14].…”

Section: Introductionmentioning

confidence: 99%

“…Model-based approaches are [1], [15] and [7]. They generally fit a template 3D face model to analyze the deformations between a neutral state to an expressionnal state.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fully automatic 3D facial expression recognition using a region-based approach

Lemaire

Amor

Ardabilian

et al. 2011

Proceedings of the 2011 Joint ACM Workshop on Human Gesture and Behavior Understanding

View full text Add to dashboard Cite

show abstract

“…Furthermore, they also capture accurate geometry information closely sensitive to expression variations. In recent years, research has been done in this area [5], and significant progress has been made [10]. Existing methods for facial expression recognition based on static 3D data can be categorized into two streams, i.e.…”

Section: Introductionmentioning

confidence: 99%

Automatic 3D facial expression recognition using geometric and textured feature fusion

Jan

Meng

2015

2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

View full text Add to dashboard Cite

Abstract-3D facial expression recognition has gained more and more interests from affective computing society due to issues such as pose variations and illumination changes caused by 2D imaging having been eliminated. There are many applications that can benefit from this research, such as medical applications involving the detection of pain and psychological effects in patients, in human-computer interaction tasks that intelligent systems use in today's world. In this paper, we look into 3D Facial Expression Recognition, by investigating many feature extraction methods used on the 2D textured images and 3D geometric data, fusing the 2 domains to increase the overall performance. A One Vs All Multi-class SVM Classifier has been adopted to recognize the expressions Angry, Disgust, Fear, Happy, Neutral, Sad and Surprise from the BU-3DFE and Bosphorus databases. The proposed approach displays an increase in performance when the features are fused together.

show abstract