Independent Component Analysis and Nonnegative Linear Model Analysis of Illuminant and Reflectance Spectra

Peer reviewed: 
Yes, item is peer reviewed.
Scholarly level: 
Faculty/Staff
Final version published as: 

Xiong, W., and Funt, B., "Independent Component Analysis and Nonnegative Linear Model Analysis of Illuminant and Reflectance Spectra," Proc. AIC2005 10th Congress of the International Color Association, Granada, May 2005.

Date created: 
2005-05
Keywords: 
Colour vision
Independent component analysis
Modeling spectra
Finite dimensional models
Sensor design
Abstract: 

Principal Component Analysis (PCA), Independent Component Analysis (ICA), Non-Negative Matrix Factorization (NNMF) and Non-Negative Independent Component Analysis (NNICA) are all techniques that can be used to compute basis vectors for finite-dimensional models of spectra. The two non-negative techniques turn out to be especially interesting because the pseudo-inverse of their basis vectors is also close to being non-negative. This means that after truncating any negative components of the pseudo-inverse vectors to zero, the resulting vectors become physically realizable sensors functions whose outputs map directly to the appropriate finite-dimensional weighting coefficients in terms of the associated (NNMF or NNICA) basis. Experiments show that truncating the negative values incurs only a very slight performance penalty in terms of the accuracy with which the input spectrum can be approximated using a finite-dimensional model.

Description: 

Presented at the AIC2005 10th Congress of the International Color Association, May 2005.

Language: 
English
Document type: 
Conference presentation
Rights: 
Rights remain with the authors.
File(s): 
Statistics: