Image Recoloring with Valence-Arousal Emotion Model

Hye Rin Kim; Henry Kang; In Kwon Lee

doi:10.1111/cgf.13018

Image Recoloring with Valence-Arousal Emotion Model

Hye Rin Kim, Henry Kang, In Kwon Lee

College of Computing

Research output: Contribution to journal › Article › peer-review

9 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 language	English
Pages (from-to)	209-216
Number of pages	8
Journal	Computer Graphics Forum
Volume	35
Issue number	7
DOIs	https://doi.org/10.1111/cgf.13018
Publication status	Published - 2016 Oct 1

Bibliographical note

Publisher Copyright:
© 2016 The Author(s) Computer Graphics Forum © 2016 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.

All Science Journal Classification (ASJC) codes

Computer Graphics and Computer-Aided Design

Access to Document

10.1111/cgf.13018

Cite this

@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}",

note = "Publisher Copyright: {\textcopyright} 2016 The Author(s) Computer Graphics Forum {\textcopyright} 2016 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.",

year = "2016",

month = oct,

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",

}

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

AN - SCOPUS:84992560066

SN - 0167-7055

VL - 35

SP - 209

EP - 216

JO - Computer Graphics Forum

JF - Computer Graphics Forum

IS - 7

ER -

Image Recoloring with Valence-Arousal Emotion Model

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this