Image and Video Colorization Using Vector-Valued Reproducing Kernel Hilbert Spaces

  • Authors:
  • Minh Ha Quang;Sung Ha Kang;Triet M. Le

  • Affiliations:
  • Humboldt University of Berlin, Berlin, Germany;School of Mathematics, Georgia Institute of Technology, Atlanta, USA;Department of Mathematics, Yale University, New Haven, USA

  • Venue:
  • Journal of Mathematical Imaging and Vision
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Motivated by the setting of reproducing kernel Hilbert space (RKHS) and its extensions considered in machine learning, we propose an RKHS framework for image and video colorization. We review and study RKHS especially in vectorial cases and provide various extensions for colorization problems. Theory as well as a practical algorithm is proposed with a number of numerical experiments.