Accurate detection of lip contour is important in many application areas, including biometric authentication, human computer interaction, and facial expression recognition. In this paper, we propose a new lip boundary localization scheme based on Game Theory (GT) to improve the facial expression detection performance. In addition, we use GT for selecting the proper set of facial features. We apply the Extended Contribution-Selection Algorithm (ECSA) for the dimensionality reduction of the facial features using a coalitional GT-based framework. We have conducted several sets of experiments to evaluate the proposed approach. The results show that the proposed approach has achieved recognition rates of 93.1% and 92.7% on the JAFFE and CK+ datasets, respectively. © 2012 Springer-Verlag.
CITATION STYLE
B, V. R., Magg, S., & Wermter, S. (2016). Towards Effective Classification of Imbalanced Date With Cnn. Artificial Neural Networks in Pattern Recognition, 9896, 150–162. Retrieved from http://link.springer.com/10.1007/978-3-319-46182-3
Mendeley helps you to discover research relevant for your work.