Feature Extraction for Regression Problems and an Example Application for Pose Estimation of a Face
In this paper, we propose a new feature extraction method for regression problems. It is a modified version of linear discriminant analysis (LDA) which is a very successful feature extraction method for classification problems. In the proposed method, the between class and the within class scatter matrices in LDA are modified so that they fit in regression problems. The samples with small differences in the target values are used to constitute the within class scatter matrix while the ones with large differences in the target values are used for the between class scatter matrix. We have applied the proposed method in estimating the head pose and compared the performance with the conventional feature extraction methods.
KeywordsRegression Feature extraction Dimensionality reduction LDA
Unable to display preview. Download preview PDF.
- 1.Cios, K.J., Pedrycz, W., Swiniarski, R.W.: Data Mining Methods for Knowledge Discovery, ch. 9. Kluwer Academic Publishers, Dordrecht (1998)Google Scholar
- 2.Joliffe, I.T.: Principal Component Analysis. Springer, Heidelberg (1986)Google Scholar
- 5.Weisberg, S.: Applied Linear Regression, ch. 3, 2nd edn., p. 324. John Wiley, New York (1985)Google Scholar
- 6.Loog, M.: Supervised Dimensionality Reduction and Contextual Pattern Recognition in Medical Image Processing, ch. 3. Ponsen & Looijen, Wageningen, The Netherlands (2004)Google Scholar
- 9.Kwak, N., Kim, C.: Dimensionality reduction based on ICA for regression problems. In: Proc. Int’l Conf. on Artificial Neural Networks (IJCNN), pp. 1–10 (2006)Google Scholar