Facial expression recognition based on local binary patterns and kernel discriminant isomap

Abstract

Facial expression recognition is an interesting and challenging subject. Considering the nonlinear manifold structure of facial images, a new kernel-based manifold learning method, called kernel discriminant isometric mapping (KDIsomap), is proposed. KDIsomap aims to nonlinearly extract the discriminant information by maximizing the interclass scatter while minimizing the intraclass scatter in a reproducing kernel Hilbert space. KDIsomap is used to perform nonlinear dimensionality reduction on the extracted local binary patterns (LBP) facial features, and produce low-dimensional discrimimant embedded data representations with striking performance improvement on facial expression recognition tasks. The nearest neighbor classifier with the Euclidean metric is used for facial expression classification. Facial expression recognition experiments are performed on two popular facial expression databases, i.e., the JAFFE database and the Cohn-Kanade database. Experimental results indicate that KDIsomap obtains the best accuracy of 81.59% on the JAFFE database, and 94.88% on the Cohn-Kanade database. KDIsomap outperforms the other used methods such as principal component analysis (PCA), linear discriminant analysis (LDA), kernel principal component analysis (KPCA), kernel linear discriminant analysis (KLDA) as well as kernel isometric mapping (KIsomap).

Keywords: dimensionality reduction; facial expression recognition; isometric mapping; kernel; local binary patterns.

Figure 1.

An example of basic LBP operator.

Figure 2.

An example of the extended LBP with different (P, R).

Figure 3.

Examples of facial expression images from the JAFFE database.

Figure 4.

Examples of facial expression images from the Cohn-Kanade database.

Figure 5.

(a) Two eyes location of an original image from the Cohn-Kanade database. (b) The final cropped image of 110 × 150 pixels.

Figure 6.

The basic system structure for facial expression recognition experiments using dimensionality reduction methods.

Figure 7.

Performance comparisons of different methods on the JAFFE database.

Figure 8.

Performance comparisons of different methods on the Cohn-Kanade database.