article · 1999

Subspace Classifier in Reproducing Kernel Hilbert Space

Koji Tsuda Electrotechnical, Koji Tsuda

Cited by 0Abstract and details only

Abstract

To improve the performance of subspace classifier, it is effective to reduce the dimensionality of the intersections between subspaces. For this purpose, the feature space is mapped implicitly to a high dimensional reproducing kernel Hilbert space and the subspace classifier is applied in this space. As a result of Hiragana recognition experiment, our classifier outperformed the conventional subspace classifier. 1 Introduction Subspace classifier is the pattern recognition method which uses a linear subspace for describing a class[1]. In training, a subspace is fit to training samples so that the sum of the squared distances between the samples and the subspace is minimized. In classifying an unlabeled sample, the sample is classified to the class whose subspace is the nearest. It is known that the performance of subspace classifier is affected by the dimensionality of the intersections of subspaces[1]. When the dimensionality of the feature space is larger than the number of traini...

Cite this paper

APA 7

Electrotechnical, K. T., & Tsuda, K. (1999). Subspace Classifier in Reproducing Kernel Hilbert Space.

MLA 9

Electrotechnical, Koji Tsuda, and Koji Tsuda. “Subspace Classifier in Reproducing Kernel Hilbert Space.” 1999.

Chicago

Electrotechnical, Koji Tsuda, and Koji Tsuda. 1999. “Subspace Classifier in Reproducing Kernel Hilbert Space.”

Harvard

Electrotechnical, K.T. and Tsuda, K. (1999) ‘Subspace Classifier in Reproducing Kernel Hilbert Space’.

BibTeX

@article{electrotechnical1999subspace,
  title = {{Subspace Classifier in Reproducing Kernel Hilbert Space}},
  author = {Electrotechnical, Koji Tsuda and Tsuda, Koji},
  year = {1999}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.