Facial Expression Recognition (FER) plays an important role in the applications of human-centered computing. This paper presents a novel and effective FER via the Boosted Convolutional Neural Network (Boosted-CNN). First, we use the Convolutional Neural Network to train a strong classifier to classify different facial expressions. Based on the classification accuracy of each expression, we use random sampling methods for imbalanced learning on each expression to get better performance. The Extended Cohn-Kanade (CK+) database and the JAFFE database are used to evaluate the performance of the proposed Boosted-CNN method. Experimental results show that the proposed method can achieve better classification rates compared with other state-of-art methods.
CITATION STYLE
Liu, Z., Wang, H., Yan, Y., & Guo, G. (2015). Effective facial expression recognition via the boosted convolutional neural network. In Communications in Computer and Information Science (Vol. 546, pp. 179–188). Springer Verlag. https://doi.org/10.1007/978-3-662-48558-3_18
Mendeley helps you to discover research relevant for your work.