We present the Computer Expression Recognition Toolbox (CERT), a software tool for fully automatic real-time facial expression recognition, and officially release it for free academic use. CERT can automatically code the intensity of 19 different facial actions from the Facial Action Unit Coding System (FACS) and 6 different prototypical facial expressions. It also estimates the locations of 10 facial features as well as the 3-D orientation (yaw, pitch, roll) of the head. On a database of posed facial expressions, Extended Cohn-Kanade (CK+[1]), CERT achieves an average recognition performance (probability of correctness on a two-alternative forced choice (2AFC) task between one positive and one negative example) of 90.1% when analyzing facial actions. On a spontaneous facial expression dataset, CERT achieves an accuracy of nearly 80%. In a standard dual core laptop, CERT can process 320 × 240 video images in real time at approximately 10 frames per second.
10 a3D orientation 10 aAccuracy 10 aautomatic real-time facial expression recognition 10 aCERT 10 acomputer expression recognition toolbox 10 aDetectors 10 adual core laptop 10 aEmotion recognition 10 aEncoding 10 aextended Cohn-Kanade 10 aFace 10 aface recognition 10 afacial action unit coding system 10 afacial expression dataset 10 aFacial features 10 aFACS 10 aGold 10 aImage coding 10 asoftware tool 10 asoftware tools 10 atwo-alternative forced choice task 1 aLittlewort, G. 1 aWhitehill, J. 1 aWu, T. 1 aFasel, I. 1 aFrank, M. 1 aMovellan, J. 1 aBartlett, M. uhttps://rubi.ucsd.edu/content/computer-expression-recognition-toolbox-cert 03033nas a2200565 4500008004100000022001400041245003700055210003700092260001200129300001400141490000700155520134500162653001501507653002801522653001401550653005301564653003501617653001301652653002401665653002001689653002201709653000901731653003301740653002101773653002701794653004801821653002801869653002001897653002201917653002501939653004401964653003902008653003202047653002802079653001302107653002102120653003002141653003102171653003202202653001202234653002602246653002202272653002102294100001802315700001902333700001402352700001702366700001702383856006702400 2009 eng d a0162-8828 00 aToward Practical Smile Detection 0 aToward Practical Smile Detection c11/2009 a2106-2111 0 v31 3 aMachine 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.
10 aAlgorithms 10 aArtificial intelligence 10 aAutomated 10 aautomatic facial expression recognition research 10 aBiological Pattern Recognition 10 aBiometry 10 aComputer simulation 10 aComputer vision 10 aComputer-Assisted 10 aFace 10 aFace and gesture recognition 10 aface recognition 10 afeature representation 10 ahuman-level expression recognition accuracy 10 aillumination conditions 10 aImage databases 10 aImage Enhancement 10 aImage Interpretation 10 aimage registration image representation 10 alearning (artificial intelligence) 10 amachine learning approaches 10 aMachine Learning Models 10 an Humans 10 aobject detection 10 apractical smile detection 10 aReproducibility of Results 10 aSensitivity and Specificity 10 aSmiling 10 aSubtraction Technique 10 atraining data set 10 avisual databases 1 aWhitehill, J. 1 aLittlewort, G. 1 aFasel, I. 1 aBartlett, M. 1 aMovellan, J. uhttps://rubi.ucsd.edu/content/toward-practical-smile-detection 02714nas a2200361 4500008004100000020002200041245006200063210006200125260003200187520158600219653002801805653002001833653002201853653002301875653002401898653003001922653001901952653001201971653003601983653003902019653002102058653002002079653002302099653003502122653001602157653001702173653001102190653001702201100001502218700001402233700001702247856008802264 2008 eng d a978-1-4244-1646-2 00 aAuditory mood detection for social and educational robots 0 aAuditory mood detection for social and educational robots aPasadena, CA bIEEE c05/2008 3 aSocial robots face the fundamental challenge of detecting and adapting their behavior to the current social mood. For example, robots that assist teachers in early education must choose different behaviors depending on whether the children are crying, laughing, sleeping, or singing songs. Interactive robotic applications require perceptual algorithms that both run in real time and are adaptable to the challenging conditions of daily life. This paper explores a novel approach to auditory mood detection which was born out of our experience immersing social robots in classroom environments. We propose a new set of low-level spectral contrast features that extends a class of features which have proven very successful for object recognition in the modern computer vision literature. Features are selected and combined using machine learning approaches so as to make decisions about the ongoing auditory mood. We demonstrate excellent performance on two standard emotional speech databases (the Berlin Emotional Speech [W. Burkhardt et al., 2005], and the ORATOR dataset [H. Quast, 2001]). In addition we establish strong baseline performance for mood detection on a database collected from a social robot immersed in a classroom of 18-24 months old children [J. Movellan er al., 2007]. This approach operates in real time at little computational cost. It has the potential to greatly enhance the effectiveness of social robots in daily life environments.
10 aauditory mood detection 10 aComputer vision 10 aeducational robot 10 aEducational robots 10 aEmotion recognition 10 aemotional speech database 10 aface detection 10 ahearing 10 ainteractive robotic application 10 alearning (artificial intelligence) 10 aMachine Learning 10 aMood Prototypes 10 aobject recognition 10 aRobotics and Automation Robots 10 asocial mood 10 asocial robot 10 aSpeech 10 aUSA Councils 1 aRuvolo, P. 1 aFasel, I. 1 aMovellan, J. uhttps://rubi.ucsd.edu/content/auditory-mood-detection-social-and-educational-robots 00495nas a2200109 4500008004100000245007700041210006900118260005200187490002600239100001400265856010600279 2006 eng d 00 aLearning Real-Time Object Detectors: Probabilistic Generative Approaches 0 aLearning RealTime Object Detectors Probabilistic Generative Appr aSan Diego b University of California, San Diego 0 vDoctoral dissertation 1 aFasel, I. uhttps://rubi.ucsd.edu/content/learning-real-time-object-detectors-probabilistic-generative-approaches 00346nas a2200109 4500008004100000245004000041210003900081100001400120700002000134700001700154856006500171 2005 eng d 00 aMPT: the Machine Perception Toolbox 0 aMPT the Machine Perception Toolbox 1 aFasel, I. 1 aFortenberry, B. 1 aMovellan, J. uhttps://rubi.ucsd.edu/content/mpt-machine-perception-toolbox 00540nas a2200133 4500008004100000245010000041210006900141100001900210700001700229700001400246700001400260700001700274856011500291 2004 eng d 00 aAnalysis of machine learning methods for real-time recognition of facial expressions from video 0 aAnalysis of machine learning methods for realtime recognition of 1 aLittlewort, G. 1 aBartlett, M. 1 aFasel, I. 1 aChenu, J. 1 aMovellan, J. uhttps://rubi.ucsd.edu/content/analysis-machine-learning-methods-real-time-recognition-facial-expressions-video 00668nas a2200181 4500008004100000245012300041210006900164300001400233490000700247100001900254700001700273700001400290700001400304700001400318700001700332700001700349856012000366 2004 eng d 00 aTowards social robots: Automatic evaluation of human-robot interaction by face detection and expression classification 0 aTowards social robots Automatic evaluation of humanrobot interac a1563-1570 0 v16 1 aLittlewort, G. 1 aBartlett, M. 1 aChenu, J. 1 aFasel, I. 1 aKanda, T. 1 aIshiguro, H. 1 aMovellan, J. uhttps://rubi.ucsd.edu/content/towards-social-robots-automatic-evaluation-human-robot-interaction-face-detection-and