Bayesian versus support vector machine based approaches for facial feature classification in image sequences. Patil, R., A., Sahula, V., & Mandal, A., S. In 2011 2nd International Conference on Computer and Communication Technology (ICCCT-2011), pages 174-179, 9, 2011. Ieee.
![Bayesian versus support vector machine based approaches for facial feature classification in image sequences [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper ![Bayesian versus support vector machine based approaches for facial feature classification in image sequences [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website doi abstract bibtex
Paper Website doi abstract bibtex A method for automatic facial expression recognition in image sequences, is introduced which make use of Candide wire frame model and active appearance algorithm for tracking, and Bayesian classifier for classification. On the first frame of face image sequence, Candide wire frame model is adapted properly. In subsequent frames of image sequence, facial features are tracked using active appearance algorithm. The algorithm adapts Candide wire frame model to the face in each of the frames and tracks the grid in consecutive video frames over time. Last frame of image sequence corresponds to greatest facial expression intensity. The difference of the node coordinates between the first and the greatest facial expression intensity frame, called the geometrical displacement of Candide wire frame nodes is used as an input to a classifier, which classifies facial expression into one of the class such as happy, surprise, sad, anger, disgust and fear. The experimental results show that the proposed method is better in classification correctness in comparison with binary SVM tree classifier.
@inproceedings{
title = {Bayesian versus support vector machine based approaches for facial feature classification in image sequences},
type = {inproceedings},
year = {2011},
keywords = {Adaptation models,Bayes methods,Bayesian classifier,Candide wire frame model,Computational modeling,Face,Feature recognition,Image sequences,SVM,Support vector machines,Training,Vectors,active appearance algorithm,automatic facial expression recognition,face recognition,facial expression intensity frame,facial feature classification,feature tracking,geometrical displacement,image classification,image sequences,support vector machine,support vector machines},
pages = {174-179},
websites = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6075168},
month = {9},
publisher = {Ieee},
institution = {NIT Jaipur},
id = {da468e43-df8b-3cc1-82f4-2f76ab3fd17f},
created = {2016-04-21T16:39:32.000Z},
accessed = {2015-12-15},
file_attached = {true},
profile_id = {03d2ca17-6bde-3cfe-95de-fcbe4f21507b},
last_modified = {2017-03-14T01:22:09.162Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Patil2011c},
short_title = {Computer and Communication Technology (ICCCT), 201},
private_publication = {false},
abstract = {A method for automatic facial expression recognition in image sequences, is introduced which make use of Candide wire frame model and active appearance algorithm for tracking, and Bayesian classifier for classification. On the first frame of face image sequence, Candide wire frame model is adapted properly. In subsequent frames of image sequence, facial features are tracked using active appearance algorithm. The algorithm adapts Candide wire frame model to the face in each of the frames and tracks the grid in consecutive video frames over time. Last frame of image sequence corresponds to greatest facial expression intensity. The difference of the node coordinates between the first and the greatest facial expression intensity frame, called the geometrical displacement of Candide wire frame nodes is used as an input to a classifier, which classifies facial expression into one of the class such as happy, surprise, sad, anger, disgust and fear. The experimental results show that the proposed method is better in classification correctness in comparison with binary SVM tree classifier.},
bibtype = {inproceedings},
author = {Patil, Rajesh A. and Sahula, Vineet and Mandal, A. S.},
doi = {10.1109/ICCCT.2011.6075168},
booktitle = {2011 2nd International Conference on Computer and Communication Technology (ICCCT-2011)}
}Downloads: 0
{"_id":"NjZKBhhrZxp3RNZNj","bibbaseid":"patil-sahula-mandal-bayesianversussupportvectormachinebasedapproachesforfacialfeatureclassificationinimagesequences-2011","author_short":["Patil, R., A.","Sahula, V.","Mandal, A., S."],"bibdata":{"title":"Bayesian versus support vector machine based approaches for facial feature classification in image sequences","type":"inproceedings","year":"2011","keywords":"Adaptation models,Bayes methods,Bayesian classifier,Candide wire frame model,Computational modeling,Face,Feature recognition,Image sequences,SVM,Support vector machines,Training,Vectors,active appearance algorithm,automatic facial expression recognition,face recognition,facial expression intensity frame,facial feature classification,feature tracking,geometrical displacement,image classification,image sequences,support vector machine,support vector machines","pages":"174-179","websites":"http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6075168","month":"9","publisher":"Ieee","institution":"NIT Jaipur","id":"da468e43-df8b-3cc1-82f4-2f76ab3fd17f","created":"2016-04-21T16:39:32.000Z","accessed":"2015-12-15","file_attached":"true","profile_id":"03d2ca17-6bde-3cfe-95de-fcbe4f21507b","last_modified":"2017-03-14T01:22:09.162Z","read":false,"starred":false,"authored":"true","confirmed":"true","hidden":false,"citation_key":"Patil2011c","short_title":"Computer and Communication Technology (ICCCT), 201","private_publication":false,"abstract":"A method for automatic facial expression recognition in image sequences, is introduced which make use of Candide wire frame model and active appearance algorithm for tracking, and Bayesian classifier for classification. On the first frame of face image sequence, Candide wire frame model is adapted properly. In subsequent frames of image sequence, facial features are tracked using active appearance algorithm. The algorithm adapts Candide wire frame model to the face in each of the frames and tracks the grid in consecutive video frames over time. Last frame of image sequence corresponds to greatest facial expression intensity. The difference of the node coordinates between the first and the greatest facial expression intensity frame, called the geometrical displacement of Candide wire frame nodes is used as an input to a classifier, which classifies facial expression into one of the class such as happy, surprise, sad, anger, disgust and fear. The experimental results show that the proposed method is better in classification correctness in comparison with binary SVM tree classifier.","bibtype":"inproceedings","author":"Patil, Rajesh A. and Sahula, Vineet and Mandal, A. S.","doi":"10.1109/ICCCT.2011.6075168","booktitle":"2011 2nd International Conference on Computer and Communication Technology (ICCCT-2011)","bibtex":"@inproceedings{\n title = {Bayesian versus support vector machine based approaches for facial feature classification in image sequences},\n type = {inproceedings},\n year = {2011},\n keywords = {Adaptation models,Bayes methods,Bayesian classifier,Candide wire frame model,Computational modeling,Face,Feature recognition,Image sequences,SVM,Support vector machines,Training,Vectors,active appearance algorithm,automatic facial expression recognition,face recognition,facial expression intensity frame,facial feature classification,feature tracking,geometrical displacement,image classification,image sequences,support vector machine,support vector machines},\n pages = {174-179},\n websites = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6075168},\n month = {9},\n publisher = {Ieee},\n institution = {NIT Jaipur},\n id = {da468e43-df8b-3cc1-82f4-2f76ab3fd17f},\n created = {2016-04-21T16:39:32.000Z},\n accessed = {2015-12-15},\n file_attached = {true},\n profile_id = {03d2ca17-6bde-3cfe-95de-fcbe4f21507b},\n last_modified = {2017-03-14T01:22:09.162Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {Patil2011c},\n short_title = {Computer and Communication Technology (ICCCT), 201},\n private_publication = {false},\n abstract = {A method for automatic facial expression recognition in image sequences, is introduced which make use of Candide wire frame model and active appearance algorithm for tracking, and Bayesian classifier for classification. On the first frame of face image sequence, Candide wire frame model is adapted properly. In subsequent frames of image sequence, facial features are tracked using active appearance algorithm. The algorithm adapts Candide wire frame model to the face in each of the frames and tracks the grid in consecutive video frames over time. Last frame of image sequence corresponds to greatest facial expression intensity. The difference of the node coordinates between the first and the greatest facial expression intensity frame, called the geometrical displacement of Candide wire frame nodes is used as an input to a classifier, which classifies facial expression into one of the class such as happy, surprise, sad, anger, disgust and fear. The experimental results show that the proposed method is better in classification correctness in comparison with binary SVM tree classifier.},\n bibtype = {inproceedings},\n author = {Patil, Rajesh A. and Sahula, Vineet and Mandal, A. S.},\n doi = {10.1109/ICCCT.2011.6075168},\n booktitle = {2011 2nd International Conference on Computer and Communication Technology (ICCCT-2011)}\n}","author_short":["Patil, R., A.","Sahula, V.","Mandal, A., S."],"urls":{"Paper":"https://bibbase.org/service/mendeley/03d2ca17-6bde-3cfe-95de-fcbe4f21507b/file/180d4605-fbce-3055-7121-ed3b3b814061/2011-Bayesian_versus_support_vector_machine_based_approaches_for_facial_feature_classification_in_image_sequences.pdf.pdf","Website":"http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6075168"},"biburl":"https://bibbase.org/service/mendeley/03d2ca17-6bde-3cfe-95de-fcbe4f21507b","bibbaseid":"patil-sahula-mandal-bayesianversussupportvectormachinebasedapproachesforfacialfeatureclassificationinimagesequences-2011","role":"author","keyword":["Adaptation models","Bayes methods","Bayesian classifier","Candide wire frame model","Computational modeling","Face","Feature recognition","Image sequences","SVM","Support vector machines","Training","Vectors","active appearance algorithm","automatic facial expression recognition","face recognition","facial expression intensity frame","facial feature classification","feature tracking","geometrical displacement","image classification","image sequences","support vector machine","support vector machines"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/service/mendeley/03d2ca17-6bde-3cfe-95de-fcbe4f21507b","dataSources":["foRZzjCMmTPmTF8eH","ya2CyA73rpZseyrZ8"],"keywords":["adaptation models","bayes methods","bayesian classifier","candide wire frame model","computational modeling","face","feature recognition","image sequences","svm","support vector machines","training","vectors","active appearance algorithm","automatic facial expression recognition","face recognition","facial expression intensity frame","facial feature classification","feature tracking","geometrical displacement","image classification","image sequences","support vector machine","support vector machines"],"search_terms":["bayesian","versus","support","vector","machine","based","approaches","facial","feature","classification","image","sequences","patil","sahula","mandal"],"title":"Bayesian versus support vector machine based approaches for facial feature classification in image sequences","year":2011}