Facial Emotion Profiling Based on Emotion Specific Feature Model

Facial emotion profiling is rapidly becoming an area of intense interest in machine vision society for decade. In spite of major efforts, there are several open questions on how to embed the emotional intelligence in machine to respond immediately and precisely over facial expressions. In this sense, this paper presents an automatic facial emotion profiling from emotion specific feature model. A 17-point feature model on the frontal face region is proposed to track per frame facial emotion robustly. A measurement vector is formed based on a set of geometric distance displacements of a pair of feature points between neutral and expressive face frame. A two-stage fuzzy reasoning model is proposed to classify universal facial expressions. In the first stage measurements are fuzzified and mapped onto an Action Units (AUs) and later AUs are fuzzified and mapped onto an Emotion in the second-stage of fuzzy reasoning model. The overall performance of the proposed system is evaluated on two publicly available facial expression databases, average emotion recognition accuracy of 91 % was achieved for RaFD and 94 % for CK + database.

[1]  Maja Pantic,et al.  Facial action recognition for facial expression analysis from static face images , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[2]  Lionel Prevost,et al.  Facial Action Recognition Combining Heterogeneous Features via Multikernel Learning , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[3]  Takeo Kanade,et al.  Multi-PIE , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[4]  Michael J. Black,et al.  Neural control of computer cursor velocity by decoding motor cortical spiking activity in humans with tetraplegia , 2008, Journal of neural engineering.

[5]  Chu Kiong Loo,et al.  Geometric Feature-Based Facial Emotion Recognition Using Two-Stage Fuzzy Reasoning Model , 2014, ICONIP.

[6]  David Cristinacce,et al.  Automatic feature localisation with constrained local models , 2008, Pattern Recognit..

[7]  Yong-Guk Kim,et al.  Real-time Expression recognition System using Active Appearance Model and EFM , 2006, 2006 International Conference on Computational Intelligence and Security.

[8]  Simon Lucey,et al.  Face alignment through subspace constrained mean-shifts , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[9]  Ganesh K. Venayagamoorthy,et al.  Recognition of facial expressions using Gabor wavelets and learning vector quantization , 2008, Eng. Appl. Artif. Intell..

[10]  Laura Igual,et al.  Robust gait-based gender classification using depth cameras , 2013, EURASIP Journal on Image and Video Processing.

[11]  S. V. Dudul,et al.  Human emotion recognition system using optimally designed SVM with different facial feature extraction techniques , 2008 .

[12]  Gamini Dissanayake,et al.  Optical flow based analyses to detect emotion from human facial image data , 2010, Expert Syst. Appl..

[13]  J. Russell,et al.  The psychology of facial expression: Frontmatter , 1997 .

[14]  Ling Guan,et al.  Automatic landmark point detection and tracking for human facial expressions , 2013, EURASIP J. Image Video Process..

[15]  Shashidhar G. Koolagudi,et al.  Recognition of emotions from video using acoustic and facial features , 2015, Signal Image Video Process..

[16]  Pedro Jiménez,et al.  RSMAT: Robust simultaneous modeling and tracking , 2010, Pattern Recognit. Lett..

[17]  Oleg Starostenko,et al.  Facial Feature Model for Emotion Recognition Using Fuzzy Reasoning , 2010, MCPR.

[18]  Takeo Kanade,et al.  The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[19]  Hamed Shah-Hosseini,et al.  A novel fuzzy facial expression recognition system based on facial feature extraction from color face images , 2012, Eng. Appl. Artif. Intell..

[20]  Sotiris Malassiotis,et al.  Real-time 2D+3D facial action and expression recognition , 2010, Pattern Recognit..

[21]  Skyler T. Hawk,et al.  Presentation and validation of the Radboud Faces Database , 2010 .

[22]  P. Ekman,et al.  Facial action coding system: a technique for the measurement of facial movement , 1978 .