Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Neural Networks 20 (2007) 559563 www.elsevier.com/locate/neunet
 

Summary: Neural Networks 20 (2007) 559563
www.elsevier.com/locate/neunet
Neural networks letter
Machine learning approach to color constancy
Vivek Agarwala,,1, Andrei V. Gribokb,, Mongi A. Abidic
a 400 Central Drive, School of Nuclear Engineering, Purdue University, West Lafayette, IN 47907, United States
b BHSAI/MRMC, Attn: MCMR-ZB-T, Building 363 Miller Dr., Fort Detrick, MD 21792-5012, United States
c 1508 Ferris Hall, Electrical and Computer Engineering, The University of Tennessee, Knoxville, TN 37996, United States
Received 18 February 2006; accepted 19 February 2007
Abstract
A number of machine learning (ML) techniques have recently been proposed to solve color constancy problem in computer vision. Neural
networks (NNs) and support vector regression (SVR) in particular, have been shown to outperform many traditional color constancy algorithms.
However, neither neural networks nor SVR were compared to simpler regression tools in those studies. In this article, we present results obtained
with a linear technique known as ridge regression (RR) and show that it performs better than NNs, SVR, and gray world (GW) algorithm on the
same dataset. We also perform uncertainty analysis for NNs, SVR, and RR using bootstrapping and show that ridge regression and SVR are more
consistent than neural networks. The shorter training time and single parameter optimization of the proposed approach provides a potential scope
for real time video tracking application.
c 2007 Elsevier Ltd. All rights reserved.
Keywords: Neural networks; Support vector regression; Ridge regression; Color constancy
1. Introduction

  

Source: Abidi, Mongi A. - Department of Electrical and Computer Engineering, University of Tennessee

 

Collections: Computer Technologies and Information Sciences