Image Recoloring with Valence-Arousal Emotion Model

Hye Rin Kim, Henry Kang, In Kwon Lee

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

We introduce an affective image recoloring method for changing the overall mood in the image in a numerically measurable way. Given a semantically segmented source image and a target emotion, our system finds reference image segments from the collection of images that have been tagged via crowdsourcing with numerically measured emotion labels. We then recolorize the source segments using colors from the selected target segments while preserving the gradient of the source image to generate a seamless and natural result. User study confirms the effectiveness of our method in accomplishing the stated goal of altering the mood of the image to match the target emotion level.

Original languageEnglish
Pages (from-to)209-216
Number of pages8
JournalComputer Graphics Forum
Volume35
Issue number7
DOIs
Publication statusPublished - 2016 Oct 1

Fingerprint

Labels
Color

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design

Cite this

Kim, Hye Rin ; Kang, Henry ; Lee, In Kwon. / Image Recoloring with Valence-Arousal Emotion Model. In: Computer Graphics Forum. 2016 ; Vol. 35, No. 7. pp. 209-216.
@article{90295f21cac34ab78042cf1f68789cd8,
title = "Image Recoloring with Valence-Arousal Emotion Model",
abstract = "We introduce an affective image recoloring method for changing the overall mood in the image in a numerically measurable way. Given a semantically segmented source image and a target emotion, our system finds reference image segments from the collection of images that have been tagged via crowdsourcing with numerically measured emotion labels. We then recolorize the source segments using colors from the selected target segments while preserving the gradient of the source image to generate a seamless and natural result. User study confirms the effectiveness of our method in accomplishing the stated goal of altering the mood of the image to match the target emotion level.",
author = "Kim, {Hye Rin} and Henry Kang and Lee, {In Kwon}",
year = "2016",
month = "10",
day = "1",
doi = "10.1111/cgf.13018",
language = "English",
volume = "35",
pages = "209--216",
journal = "Computer Graphics Forum",
issn = "0167-7055",
publisher = "Wiley-Blackwell",
number = "7",

}

Image Recoloring with Valence-Arousal Emotion Model. / Kim, Hye Rin; Kang, Henry; Lee, In Kwon.

In: Computer Graphics Forum, Vol. 35, No. 7, 01.10.2016, p. 209-216.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Image Recoloring with Valence-Arousal Emotion Model

AU - Kim, Hye Rin

AU - Kang, Henry

AU - Lee, In Kwon

PY - 2016/10/1

Y1 - 2016/10/1

N2 - We introduce an affective image recoloring method for changing the overall mood in the image in a numerically measurable way. Given a semantically segmented source image and a target emotion, our system finds reference image segments from the collection of images that have been tagged via crowdsourcing with numerically measured emotion labels. We then recolorize the source segments using colors from the selected target segments while preserving the gradient of the source image to generate a seamless and natural result. User study confirms the effectiveness of our method in accomplishing the stated goal of altering the mood of the image to match the target emotion level.

AB - We introduce an affective image recoloring method for changing the overall mood in the image in a numerically measurable way. Given a semantically segmented source image and a target emotion, our system finds reference image segments from the collection of images that have been tagged via crowdsourcing with numerically measured emotion labels. We then recolorize the source segments using colors from the selected target segments while preserving the gradient of the source image to generate a seamless and natural result. User study confirms the effectiveness of our method in accomplishing the stated goal of altering the mood of the image to match the target emotion level.

UR - http://www.scopus.com/inward/record.url?scp=84992560066&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992560066&partnerID=8YFLogxK

U2 - 10.1111/cgf.13018

DO - 10.1111/cgf.13018

M3 - Article

VL - 35

SP - 209

EP - 216

JO - Computer Graphics Forum

JF - Computer Graphics Forum

SN - 0167-7055

IS - 7

ER -