Link functions and Matern kernel in the estimation of reflectance spectra from RGB responses
| Autor: | Juha Alho, Ville Heikkinen, Arash Mirhashemi |
|---|---|
| Přispěvatelé: | Department of Social Research (2010-2017) |
| Jazyk: | angličtina |
| Rok vydání: | 2013 |
| Předmět: |
business.industry
education 02 engineering and technology 222 Other engineering and technologies 01 natural sciences Atomic and Molecular Physics and Optics Kernel principal component analysis Electronic Optical and Magnetic Materials 010309 optics Kernel method Optics Kernel embedding of distributions Variable kernel density estimation Polynomial kernel 0103 physical sciences Radial basis function kernel 0202 electrical engineering electronic engineering information engineering Kernel smoother Kernel regression 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition business Algorithm Mathematics |
| Popis: | We evaluate three link functions (square root, logit, and copula) and Matern kernel in the kernel-based estimation of reflectance spectra of the Munsell Matte collection in the 400–700 nm region. We estimate reflectance spectra from RGB camera responses in case of real and simulated responses and show that a combination of link function and a kernel regression model with a Matern kernel decreases spectral errors when compared to a Gaussian mixture model or kernel regression with the Gaussian kernel. Matern kernel produces performance similar to the thin plate spline model, but does not require a parametric polynomial part in the model. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|