https://github.com/sfu-cs-vision-lab/tps
Thin-Plate Spline Illumination Estimation Automatic White Balancing Method
https://github.com/sfu-cs-vision-lab/tps
camera-calibration color color-constancy color-measurement color-vision digital-image-processing illumination image-registration interpolation light-sources neural-networks vision visual-optics
Last synced: 3 months ago
JSON representation
Thin-Plate Spline Illumination Estimation Automatic White Balancing Method
- Host: GitHub
- URL: https://github.com/sfu-cs-vision-lab/tps
- Owner: sfu-cs-vision-lab
- License: agpl-3.0
- Created: 2025-01-10T03:34:59.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2025-01-16T20:14:09.000Z (5 months ago)
- Last Synced: 2025-02-03T13:16:52.281Z (5 months ago)
- Topics: camera-calibration, color, color-constancy, color-measurement, color-vision, digital-image-processing, illumination, image-registration, interpolation, light-sources, neural-networks, vision, visual-optics
- Language: MATLAB
- Homepage: https://doi.org/10.1364/JOSAA.28.000940
- Size: 466 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
- Citation: CITATION.cff
Awesome Lists containing this project
README
# Thin-Plate Spline Illumination Estimation Automatic White Balancing Method
[](https://matlab.mathworks.com/open/github/v1?repo=sfu-cs-vision-lab/tps)
### Abstract
Thin-plate spline interpolation is used to interpolate the chromaticity of the color of the incident scene illumination across a training set of images. Given the image of a scene under unknown illumination, the chromaticity of the scene illumination can be found from the interpolated function. The resulting illumination-estimation method can be used to provide color constancy under changing illumination conditions and automatic white balancing for digital cameras. A thin-plate spline interpolates over a nonuniformly sampled input space, which in this case is a training set of image thumbnails and associated illumination chromaticities. To reduce the size of the training set, incremental k medians are applied. Tests on real images demonstrate that the thin-plate spline method can estimate the color of the incident illumination quite accurately, and the proposed training set pruning significantly decreases the computation.
### Citation
```
@article{Shi:11,
author = {Lilong Shi and Weihua Xiong and Brian Funt},
journal = {J. Opt. Soc. Am. A},
keywords = {Digital image processing; Vision, color, and visual optics ; Color; Color, measurement ; Color vision; Camera calibration; Illumination; Image registration; Interpolation; Light sources; Neural networks},
number = {5},
pages = {940--948},
publisher = {Optica Publishing Group},
title = {Illumination estimation via thin-plate spline interpolation},
volume = {28},
month = {May},
year = {2011},
url = {https://opg.optica.org/josaa/abstract.cfm?URI=josaa-28-5-940},
doi = {10.1364/JOSAA.28.000940},
abstract = {Thin-plate spline interpolation is used to interpolate the chromaticity of the color of the incident scene illumination across a training set of images. Given the image of a scene under unknown illumination, the chromaticity of the scene illumination can be found from the interpolated function. The resulting illumination-estimation method can be used to provide color constancy under changing illumination conditions and automatic white balancing for digital cameras. A thin-plate spline interpolates over a nonuniformly sampled input space, which in this case is a training set of image thumbnails and associated illumination chromaticities. To reduce the size of the training set, incremental k medians are applied. Tests on real images demonstrate that the thin-plate spline method can estimate the color of the incident illumination quite accurately, and the proposed training set pruning significantly decreases the computation.},
}
```