A facial expression recognition method based on supervised Isomap
暂无分享,去创建一个
In this paper, a facial expression recognition algorithm based on supervised Isomap is presented. First, supervised Isomap is used to map the high-dimensional facial expression images into a low-dimensional embedded subspace in which facial expression features are extracted. Then nearest neighbor classifier is applied to classify different expression features. The facial expression recognition experiments are performed on the JAFFE database, our experiments show that this proposed algorithm performs better than the PCA algorithm, and it is a feasible and effective algorithm.
[1] J. Tenenbaum,et al. A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.
[2] Wang Jiaxin. Multi-manifold learning using locally linear embedding(LLE) nonlinear dimensionality reduction , 2008 .
[3] Wang Jue. Locally Linear Embedding and Its Application in Facial Expressions Recognition , 2010 .