2012 · 18 citations · 13 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningEmotion RecognitionFace RecognitionFacial ExpressionImage ClassificationPattern RecognitionSupport Vector MachinesComputational Complexity Of AlgorithmsFace Feature ExtractionFacial Expression AnalysisFacial Expression ClassificationFacial Expression RecognitionLocal Binary PatternsMulticlass ClassificationSupport Vector Machine Classification
We propose a novel approach using Complete Local Binary Pattern feature generation method for facial expression recognition with the help of Multi-Class Support Vector Machine. Complete Local Binary Pattern method is an extended version of Local Binary Pattern method with a little difference. LBP feature considers only signs of local differences, whereas CLBP feature considers both signs and magnitude of local differences as well as original center gray level value. CLBP and LBP have same computational complexity while CLBP performs better facial expression recognition over LBP using SVM training and multiclass classification with binary SVM classifiers. The experimental result demonstrate the average efficiency of recognition of propose method (35 images) with CLBP is 86.4%, while with LBP and CCV is 84.1255% and 75.83% in the JAFFE database.
13
Coding facial expressions with Gabor wavelets
Michael J. Lyons, Shigeru Akamatsu, Miyuki Kamachi et al. · 2002 · 2.2K citations · Full text
Automatic facial expression analysis: a survey
Beat Fasel, Juergen Luettin · Pattern Recognition · 2002 · 1.8K citations · Full text