Designing illuminant spectral power distribution for surface classification - Sample Data
Abstract/Contents
- Abstract
There are many scientific, medical and industrial imaging applications where users have full control of the scene illumination and color reproduction is not the primary objective. For example, it is possible to co-design sensors and spectral illumination in order to classify and detect changes in biological tissues, organic and inorganic materials, and object surface properties. In this paper, we propose two different approaches to illuminant spectrum selection for surface classification. In the first approach, a supervised framework, we formulate a biconvex optimization problem where we alternate between optimizing support vector classifier weights and optimal illuminants. In the second approach, an unsupervised dimensionality reduction, we describe and apply a new sparse Principal Component Analysis (PCA) algorithm. We efficiently solve the non-convex PCA problem using a convex relaxation and Alternating Direction Method of Multipliers (ADMM). We compare the classification accuracy of a monochrome imaging sensor with optimized illuminants to the classification accuracy of conventional RGB cameras with natural broadband illumination.
This repository contains sample image data used in the analysis and classification results.
Description
Type of resource | software, multimedia |
---|---|
Date created | [ca. June 2016 - December 2016] |
Creators/Contributors
Author | Blasinski, Henryk |
---|---|
Contributing author | Farrell, Joyce |
Primary advisor | Wandell, Brian |
Subjects
Subject | multispectral imaging |
---|---|
Subject | nonnegative sparse PCA |
Subject | illuminant spectrum selection |
Genre | Dataset |
Bibliographic information
Related Publication | H. Blasinski, J. Farrell, B. Wandell; 'Designing illuminant spectral power distribution for surface classification' in proc. IEEE Computer Vision and Pattern Recognition CVPR, July 2017. https://doi.org/10.1109/CVPR.2017.287 |
---|---|
Related item |
|
Location | https://purl.stanford.edu/rq453qp3526 |
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
- License
- This work is licensed under an Open Data Commons Attribution License v1.0.
Collection
Contact information
- Contact
- hblasins@stanford.edu
Also listed in
Loading usage metrics...