BibTeX:

@article{IJIRSTV3I4109,
     title={Efficient Facial Expression Recognition System for Tilted Face Images},
     author={Nifi C Joy and Dr. Prasad J. C.},
     journal={International Journal for Innovative Research in Science & Technology},
     volume={3},
     number={4},
     pages={357--366},
     year={},
     url={http://www.ijirst.org/articles/IJIRSTV3I4109.pdf},
     publisher={IJIRST (International Journal for Innovative Research in Science & Technology)},
}

Automatic facial expression recognition is still a hard research area with several challenges to meet. Efficient facial expression recognition system is developed to recognize the facial expressions even when the face is slightly tilted. Applications of facial expression recognition system include border security systems, forensics, virtual reality, computer games, robotics, machine vision, video conferencing, user profiling for customer satisfaction, broadcasting and web services. Initially the face localization is done using the viola jones face detector. The facial components are extracted if the facial components are properly detected and the features are extracted from the whole face if the facial components are not detected. The extracted facial features are represented by three features vectors: the Zernike moments, LBP features and DCT transform components. In order to reduce the dimensionality, a subset feature selection algorithm is used prior to training process. The paper presents a comparison between the PCA based method and Normalized mutual information selection method for reducing the dimensionality. The feature vectors are combined and reduced and then applied to SVM classifier for training process. Experiment results shows that the proposed methodology affirms a good performance in facial expression recognition.

Facial Expression Recognition, Zernike Moments, LBP, Discrete Cosine Transform, Principal Component Analysis, Normalized Mutual Information Selection, SVM Classifier