Research Article

Facial Expression Recognition Using Improved Support Vector Machine by Modifying Kernels

This study proposes a novel facial expression recognition approach based on improved Support Vector Machine (SVM) by modifying kernels. The idea comes from the work of Amari that enlarging the spatial resolution around the margin by a conformal mapping, such that the separability between classes is increased. Experiments on Japanese Female Facial Expressions (JAFFE) database show that the Classification Accuracy Rate (CAR) is remarkably improved after modifying the Gaussian kernel. Experiments also show that the importance of selecting an appropriate parameter when modifying the kernel.

PDF Fulltext XML References Citation

How to cite this article

W. Liejun, Q. Xizhong and Z. Taiyi, 2009. Facial Expression Recognition Using Improved Support Vector Machine by Modifying Kernels. Information Technology Journal, 8: 595-599.

DOI: 10.3923/itj.2009.595.599

URL: https://scialert.net/abstract/?doi=itj.2009.595.599

Information Technology Journal

Article Trend

Total views 573

Search

Authors

W. Liejun

Q. Xizhong

Z. Taiyi

Keywords

Research Article

Facial Expression Recognition Using Improved Support Vector Machine by Modifying Kernels

How to cite this article

Related Articles

Leave a Comment