Abstract
Regression methods have been widely used in the problem of spectral reflectance estimation from camera responses, due to their simple application without needing prior knowledge of the imaging system. These methods can be called global regression methods since the regression functions are trained on all the training samples. Recently, local learning methods have received considerable attention due to their capability in exploiting the local manifold structure of data. In this paper, we propose a set of reflectance estimation methods based on local regression methods. These methods can be seen as the local versions of the traditional global regression methods. The training set is confined to the test point’s k-nearest neighbors. Experimental results show that the local ridge regression has the best generalization performance in the compared methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Hardeberg, J.Y.: Filter Selection for Multispectral Color Image Acquistion. J. Imaging Sci. Technol. 48, 105–110 (2004)
Connah, D., Hardeberg, J.Y.: Spectral Recovery Using Polynomial Models. In: Proc. SPIE, vol. 5667, pp. 65–75 (2005)
Shimano, N., Terai, K., Hironaga, M.: Recovery of Spectral Reflectances of Objects being Imaged by Multispectral Cameras. J. Opt. Soc. Am. A 24, 3211–3219 (2007)
Shen, H.L., Xin, J.H.: Estimation of Spectral Reflectance of Object Surfaces with the Consideration of Perceptual Color Space. Opt. Lett. 32, 96–98 (2007)
Heikkinen, V., Jetsu, T., Parkkinen, J., Hauta-Kasari, M., Jaaskelainen, T., Lee, S.D.: Regularized Learning Framework in the Estimation of Reflectance Spectra from Camera Responses. J. Opt. Soc. Am. A 24, 2673–2683 (2007)
Zhang, W.F., Dai, D.Q.: Spectral Reflectance Estimation from Camera Responses by Support Vector Regression and a Composite Model. J. Opt. Soc. Am. A 25, 2286–2296 (2008)
Lansel, S., Parmar, M., Wandell, B.A.: Dictionaries for Sparse Representation and Recovery of Reflectances. In: Proc. SPIE, Comp. Imaging VII., vol. 7246, p. 72460D (2009)
Zhang, W.F., Tang, G., Dai, D.Q., Nehorai, A.: Estimation of Reflectance from Cameara Responses by the Regularized Local Linear Model. Opt. Lett. 36, 3933–3935 (2011)
Lansel, S.: Local Linear Learned Method for Image and Reflectance Estimation. Doctoral Dissertation, Standford University (2011)
Roweis, S.T., Saul, L.K.: Nonlinear Dimensionality Reduction by Locally Linear Embedding. Science 290, 2323–2326 (2000)
Wu, M., Schölkopf, B.: A Local Learning Approach for Clustering. In: Advances in Neural Information Processing Systems 19, pp. 1529–1536. MIT Press (2007)
Gupta, M.R., Garcia, E.K., Chin, E.: Adaptive Local Linear Regression with Application to Printer Color Mangement. IEEE T. Image. Process. 17, 936–945 (2008)
Ladický, L., Torr, P.H.S.: Locally Linear Support Vector Machines. In: Proceddings of the 28th International Conference on Machine Learning (2011)
Spectral Database. University of Joensuu Color Group, http://spectral.joensuu.fi/
Barnard, K., Martin, L., Funt, B., Coath, A.: A Data Set for Color Research. Color Res. Appl. 27, 147–151 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, WF., Yang, P., Dai, DQ., Nehorai, A. (2012). Reflectance Estimation Using Local Regression Methods. In: Wang, J., Yen, G.G., Polycarpou, M.M. (eds) Advances in Neural Networks – ISNN 2012. ISNN 2012. Lecture Notes in Computer Science, vol 7367. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31346-2_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-31346-2_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31345-5
Online ISBN: 978-3-642-31346-2
eBook Packages: Computer ScienceComputer Science (R0)