Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2015 May:1:10.1109/FG.2015.7163082.
doi: 10.1109/FG.2015.7163082.

IntraFace

Fernando De la Torre  1 , Wen-Sheng Chu  1 , Xuehan Xiong  1 , Francisco Vicente  1 , Xiaoyu Ding  1 , Jeffrey Cohn  2
Affiliations

IntraFace

Fernando De la Torre et al. IEEE Int Conf Autom Face Gesture Recognit Workshops. 2015 May.

Abstract

Within the last 20 years, there has been an increasing interest in the computer vision community in automated facial image analysis algorithms. This has been driven by applications in animation, market research, autonomous-driving, surveillance, and facial editing among others. To date, there exist several commercial packages for specific facial image analysis tasks such as facial expression recognition, facial attribute analysis or face tracking. However, free and easy-to-use software that incorporates all these functionalities is unavailable. This paper presents IntraFace (IF), a publicly-available software package for automated facial feature tracking, head pose estimation, facial attribute recognition, and facial expression analysis from video. In addition, IFincludes a newly develop technique for unsupervised synchrony detection to discover correlated facial behavior between two or more persons, a relatively unexplored problem in facial image analysis. In tests, IF achieved state-of-the-art results for emotion expression and action unit detection in three databases, FERA, CK+ and RU-FACS; measured audience reaction to a talk given by one of the authors; and discovered synchrony for smiling in videos of parent-infant interaction. IF is free of charge for academic use at http://www.humansensing.cs.cmu.edu/intraface/.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
An overview of the functionalities provided by IntraFace (IF)
Fig. 2
Fig. 2
Automatic output of IntraFace to measure audience reaction while attending a talk,“Common Sense for Research (and Life),” by one of the authors.
Fig. 3
Fig. 3
(a) Manually labeled image with 66 landmarks. Blue outline indicates face detector. (b) Mean landmarks, x0, initialized using the face detector.
Fig. 4
Fig. 4
An illustration of IF on multiple face tracking. Faces belong to the same person are identified and tracked across different scenes. “N/A” indicates the frames where the face is not present or the tracker fails to track the person.
Fig. 5
Fig. 5
Pipeline for facial attribute recognition.
Fig. 6
Fig. 6
Basic emotions. From left to right: happiness, sadness, anger, fear, surprise, disgust, contempt, and embarrassment.
Fig. 7
Fig. 7
Facial Action Units (AUs) of upper and lower face
Fig. 8
Fig. 8
An illustration of IF on capturing amusement and attentiveness during a 45-minute talk on “Common Sense for Research (and Life)”. (a)/(b) and (c)/(d) show the lowest/highest amusement and attentiveness respectively. Check the text for the content about the talk.
Fig. 9
Fig. 9
An illustration of a mother-infant interaction during a Face-to-Face (FF) session. y-axis denotes the projected features onto the first principal component. Red framed rectangles indicate the discovered dyadic smiling faces; gray rectangles indicate other sampled frames.
Fig. 10
Fig. 10
An illustration of mouth features
See this image and copyright information in PMC

References

    1. Bartlett M, Littlewort G, Wu T, Movellan J. Computer expression recognition toolbox. Automatic Face & Gesture Recognition. 2008
    1. Bartlett M, Littlewort GC, Frank MG, Lainscsek C, Fasel IR, Movellan JR. Automatic recognition of facial actions in spontaneous expressions. Journal of Multimedia. 2006;1(6):22–35.
    1. Bruce V. What the human face tells the human mind: Some challenges for the robot-human interface. IEEE Int. Workshop on Robot and Human Communication. 1992
    1. Bruzzone L, Marconcini M. Domain adaptation problems: A dasvm classification technique and a circular validation strategy. PAMI. 2010;32(5):770–787. - PubMed
    1. Chang C-C, Lin C-J. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology. 2011;2(27):1–27. 27.

LinkOut - more resources