Toward Practical Smile Detection

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 31; no. 11; pp. 2106 - 2111
• Main Authors: Whitehill, J., Littlewort, G., Fasel, I., Bartlett, M., Movellan, J.
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.11.2009; IEEE Computer Society; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Automatic control; Biometry - methods; Computer science; control theory; systems; Computer Simulation; computer vision; Exact sciences and technology; Face - anatomy & histology; Face and gesture recognition; Face recognition; Facial; Humans; Illumination; Image databases; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image registration; Learning systems; Lighting control; Machine learning; Machine learning algorithms; Models, Biological; Optimization; Pattern Recognition, Automated - methods; Pattern recognition. Digital image processing. Computational geometry; Recognition; Representations; Reproducibility of Results; Sensitivity and Specificity; Smiling; Spatial databases; Studies; Subtraction Technique; Training data; Computer vision; Image databank; Gesture recognition; Algorithmics; machine learning; Date; Optimization; Face and gesture recognition; Luminance; Lighting; Imaging; Optimal solution; Facies; Database; Illumination; Automatic recognition; Learning algorithm; Artificial intelligence; Facial expression
• ISSN: 0162-8828; 1939-3539; 1939-3539
• DOI: 10.1109/TPAMI.2009.42

Machine learning approaches have produced some of the highest reported performances for facial expression recognition. However, to date, nearly all automatic facial expression recognition research has focused on optimizing performance on a few databases that were collected under controlled lighting conditions on a relatively small number of subjects. This paper explores whether current machine learning methods can be used to develop an expression recognition system that operates reliably in more realistic conditions. We explore the necessary characteristics of the training data set, image registration, feature representation, and machine learning algorithms. A new database, GENKI, is presented which contains pictures, photographed by the subjects themselves, from thousands of different people in many different real-world imaging conditions. Results suggest that human-level expression recognition accuracy in real-life illumination conditions is achievable with machine learning technology. However, the data sets currently used in the automatic expression recognition literature to evaluate progress may be overly constrained and could potentially lead research into locally optimal algorithmic solutions.