Objectivity and Subjectivity in Aesthetic Quality Assessment of Digital Photographs

Won Hee Kim, Jun Ho Choi, Jong Seok Lee

Research output: Contribution to journalArticle

Abstract

Automatic prediction of the aesthetic quality of a photograph has been an important research problem in image processing and computer vision. While assessing the aesthetic quality of a photograph by human is highly subjective, most existing studies have considered only objective (or general) opinion of multiple viewers. In this paper, we provide a comprehensive investigation of the issue of subjectivity in aesthetic quality assessment using a large-scale database containing photos, user ratings, and user comments. First, we analyze how the mean aesthetic quality level and the level of subjectivity have evolved over time. Second, we examine the feasibility of automatic prediction of the level of subjectivity based on visual features, and identify which features are effective for the prediction. Third, we analyze the users comments given to photos to understand the sources of subjectivity of aesthetic quality rating. Our results show that several factors are simultaneously involved in determining the level of subjectivity of a photo, but it can be predicted with reasonable accuracy. We believe that our results provide insight toward personalized aesthetic photo applications.

Original languageEnglish
JournalIEEE Transactions on Affective Computing
DOIs
Publication statusAccepted/In press - 2018 Feb 24

Fingerprint

Computer vision
Image processing

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction

Cite this

@article{a81deb35235e4259bab1c57cc94a47c8,
title = "Objectivity and Subjectivity in Aesthetic Quality Assessment of Digital Photographs",
abstract = "Automatic prediction of the aesthetic quality of a photograph has been an important research problem in image processing and computer vision. While assessing the aesthetic quality of a photograph by human is highly subjective, most existing studies have considered only objective (or general) opinion of multiple viewers. In this paper, we provide a comprehensive investigation of the issue of subjectivity in aesthetic quality assessment using a large-scale database containing photos, user ratings, and user comments. First, we analyze how the mean aesthetic quality level and the level of subjectivity have evolved over time. Second, we examine the feasibility of automatic prediction of the level of subjectivity based on visual features, and identify which features are effective for the prediction. Third, we analyze the users comments given to photos to understand the sources of subjectivity of aesthetic quality rating. Our results show that several factors are simultaneously involved in determining the level of subjectivity of a photo, but it can be predicted with reasonable accuracy. We believe that our results provide insight toward personalized aesthetic photo applications.",
author = "Kim, {Won Hee} and Choi, {Jun Ho} and Lee, {Jong Seok}",
year = "2018",
month = "2",
day = "24",
doi = "10.1109/TAFFC.2018.2809752",
language = "English",
journal = "IEEE Transactions on Affective Computing",
issn = "1949-3045",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Objectivity and Subjectivity in Aesthetic Quality Assessment of Digital Photographs. / Kim, Won Hee; Choi, Jun Ho; Lee, Jong Seok.

In: IEEE Transactions on Affective Computing, 24.02.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Objectivity and Subjectivity in Aesthetic Quality Assessment of Digital Photographs

AU - Kim, Won Hee

AU - Choi, Jun Ho

AU - Lee, Jong Seok

PY - 2018/2/24

Y1 - 2018/2/24

N2 - Automatic prediction of the aesthetic quality of a photograph has been an important research problem in image processing and computer vision. While assessing the aesthetic quality of a photograph by human is highly subjective, most existing studies have considered only objective (or general) opinion of multiple viewers. In this paper, we provide a comprehensive investigation of the issue of subjectivity in aesthetic quality assessment using a large-scale database containing photos, user ratings, and user comments. First, we analyze how the mean aesthetic quality level and the level of subjectivity have evolved over time. Second, we examine the feasibility of automatic prediction of the level of subjectivity based on visual features, and identify which features are effective for the prediction. Third, we analyze the users comments given to photos to understand the sources of subjectivity of aesthetic quality rating. Our results show that several factors are simultaneously involved in determining the level of subjectivity of a photo, but it can be predicted with reasonable accuracy. We believe that our results provide insight toward personalized aesthetic photo applications.

AB - Automatic prediction of the aesthetic quality of a photograph has been an important research problem in image processing and computer vision. While assessing the aesthetic quality of a photograph by human is highly subjective, most existing studies have considered only objective (or general) opinion of multiple viewers. In this paper, we provide a comprehensive investigation of the issue of subjectivity in aesthetic quality assessment using a large-scale database containing photos, user ratings, and user comments. First, we analyze how the mean aesthetic quality level and the level of subjectivity have evolved over time. Second, we examine the feasibility of automatic prediction of the level of subjectivity based on visual features, and identify which features are effective for the prediction. Third, we analyze the users comments given to photos to understand the sources of subjectivity of aesthetic quality rating. Our results show that several factors are simultaneously involved in determining the level of subjectivity of a photo, but it can be predicted with reasonable accuracy. We believe that our results provide insight toward personalized aesthetic photo applications.

UR - http://www.scopus.com/inward/record.url?scp=85042706572&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042706572&partnerID=8YFLogxK

U2 - 10.1109/TAFFC.2018.2809752

DO - 10.1109/TAFFC.2018.2809752

M3 - Article

AN - SCOPUS:85042706572

JO - IEEE Transactions on Affective Computing

JF - IEEE Transactions on Affective Computing

SN - 1949-3045

ER -