%0 Conference Paper %B 2009 4th ACM/IEEE International Conference on Human-Robot Interaction (HRI) %D 2009 %T Sociable robot improves toddler vocabulary skills %A Movellan, J. %A Eckhardt, M. %A Virnes, M. %A Rodriguez, A %K Algorithms %K autonomously operated robot %K Early Childhood Education Center %K Educational institutions %K Educational robots %K Games %K human factors %K Human-robot interaction %K intervention period %K Pediatrics %K Robot sensing systems %K robotics %K sociable robot %K social aspects of automation %K time 2 week %K toddler vocabulary skills %K Ubiquitous computering %K Vocabulary %X

We report results of a study in which a low cost sociable robot was immersed at an Early Childhood Education Center for a period of 2 weeks. The study was designed to investigate whether the robot, which operated fully autonomously during the intervention period, could improve target vocabulary skills of 18-24 month of age toddlers. The results showed a 27% improvement in knowledge of the target words taught by the robot when compared to a matched set of control words. The results suggest that sociable robots may be an effective and low cost technology to enrich Early Childhood Education environments.

%B 2009 4th ACM/IEEE International Conference on Human-Robot Interaction (HRI) %I IEEE %C La Jolla, CA %8 03/2009 %@ 978-1-60558-404-1 %G eng %M 12908586 %0 Journal Article %J IEEE Transactions on Pattern Analysis and Machine Intelligence %D 2009 %T Toward Practical Smile Detection %A Whitehill, J. %A Littlewort, G. %A Fasel, I. %A Bartlett, M. %A Movellan, J. %K Algorithms %K Artificial intelligence %K Automated %K automatic facial expression recognition research %K Biological Pattern Recognition %K Biometry %K Computer simulation %K Computer vision %K Computer-Assisted %K Face %K Face and gesture recognition %K face recognition %K feature representation %K human-level expression recognition accuracy %K illumination conditions %K Image databases %K Image Enhancement %K Image Interpretation %K image registration image representation %K learning (artificial intelligence) %K machine learning approaches %K Machine Learning Models %K n Humans %K object detection %K practical smile detection %K Reproducibility of Results %K Sensitivity and Specificity %K Smiling %K Subtraction Technique %K training data set %K visual databases %X

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.

%B IEEE Transactions on Pattern Analysis and Machine Intelligence %V 31 %P 2106-2111 %8 11/2009 %G eng %N 11 %& 2106