Reliable colorization algorithm for images and videos

Dae Young Hyun, Jun Hee Heu, Chang-Su Kim, Sang Uk Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this work, we propose an efficient image and video colorization algorithm. To achieve natural colorization, we first define initial color values and compute their reliabilities. For image colorization, initial colors are assigned by the user interaction. For video colorization, initial colors are transferred from the previous frame and their reliabilities are computed based on the motion information. Then, we formulate an energy function and minimize the function to refine the initial colors. Simulation results show that the proposed algorithm provides more natural colorization results on various images and videos than the conventional algorithms.

Original languageEnglish
Title of host publicationEuropean Signal Processing Conference
Pages263-267
Number of pages5
Publication statusPublished - 2009
Event17th European Signal Processing Conference, EUSIPCO 2009 - Glasgow, United Kingdom
Duration: 2009 Aug 242009 Aug 28

Other

Other17th European Signal Processing Conference, EUSIPCO 2009
CountryUnited Kingdom
CityGlasgow
Period09/8/2409/8/28

Fingerprint

Color

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Hyun, D. Y., Heu, J. H., Kim, C-S., & Lee, S. U. (2009). Reliable colorization algorithm for images and videos. In European Signal Processing Conference (pp. 263-267)

Reliable colorization algorithm for images and videos. / Hyun, Dae Young; Heu, Jun Hee; Kim, Chang-Su; Lee, Sang Uk.

European Signal Processing Conference. 2009. p. 263-267.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hyun, DY, Heu, JH, Kim, C-S & Lee, SU 2009, Reliable colorization algorithm for images and videos. in European Signal Processing Conference. pp. 263-267, 17th European Signal Processing Conference, EUSIPCO 2009, Glasgow, United Kingdom, 09/8/24.
Hyun DY, Heu JH, Kim C-S, Lee SU. Reliable colorization algorithm for images and videos. In European Signal Processing Conference. 2009. p. 263-267
Hyun, Dae Young ; Heu, Jun Hee ; Kim, Chang-Su ; Lee, Sang Uk. / Reliable colorization algorithm for images and videos. European Signal Processing Conference. 2009. pp. 263-267
@inproceedings{3bcf489c56914cf285a7bdfbcbaf4298,
title = "Reliable colorization algorithm for images and videos",
abstract = "In this work, we propose an efficient image and video colorization algorithm. To achieve natural colorization, we first define initial color values and compute their reliabilities. For image colorization, initial colors are assigned by the user interaction. For video colorization, initial colors are transferred from the previous frame and their reliabilities are computed based on the motion information. Then, we formulate an energy function and minimize the function to refine the initial colors. Simulation results show that the proposed algorithm provides more natural colorization results on various images and videos than the conventional algorithms.",
author = "Hyun, {Dae Young} and Heu, {Jun Hee} and Chang-Su Kim and Lee, {Sang Uk}",
year = "2009",
language = "English",
pages = "263--267",
booktitle = "European Signal Processing Conference",

}

TY - GEN

T1 - Reliable colorization algorithm for images and videos

AU - Hyun, Dae Young

AU - Heu, Jun Hee

AU - Kim, Chang-Su

AU - Lee, Sang Uk

PY - 2009

Y1 - 2009

N2 - In this work, we propose an efficient image and video colorization algorithm. To achieve natural colorization, we first define initial color values and compute their reliabilities. For image colorization, initial colors are assigned by the user interaction. For video colorization, initial colors are transferred from the previous frame and their reliabilities are computed based on the motion information. Then, we formulate an energy function and minimize the function to refine the initial colors. Simulation results show that the proposed algorithm provides more natural colorization results on various images and videos than the conventional algorithms.

AB - In this work, we propose an efficient image and video colorization algorithm. To achieve natural colorization, we first define initial color values and compute their reliabilities. For image colorization, initial colors are assigned by the user interaction. For video colorization, initial colors are transferred from the previous frame and their reliabilities are computed based on the motion information. Then, we formulate an energy function and minimize the function to refine the initial colors. Simulation results show that the proposed algorithm provides more natural colorization results on various images and videos than the conventional algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84863771579&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863771579&partnerID=8YFLogxK

M3 - Conference contribution

SP - 263

EP - 267

BT - European Signal Processing Conference

ER -