Nonlinear feature extraction based on centroids and kernel functions

✍ Scribed by Cheong Hee Park; Haesun Park

• Publisher: Elsevier Science
• Year: 2004
• Tongue: English
• Weight: 266 KB
• Volume: 37
• Category: Article
• ISSN: 0031-3203
• DOI: 10.1016/j.patcog.2003.07.011

✦ Synopsis

A nonlinear feature extraction method is presented which can reduce the data dimension down to the number of classes, providing dramatic savings in computational costs. The dimension reducing nonlinear transformation is obtained by implicitly mapping the input data into a feature space using a kernel function, and then ÿnding a linear mapping based on an orthonormal basis of centroids in the feature space that maximally separates the between-class relationship. The experimental results demonstrate that our method is capable of extracting nonlinear features e ectively so that competitive performance of classiÿcation can be obtained with linear classiÿers in the dimension reduced space.