Can we detect harmony in artistic compositions? A machine learning approach

Adam Vandor; Marie van Vollenhoven; Gerhard Weiss; Gerasimos Spanakis

doi:10.5220/0010244901870195

Can we detect harmony in artistic compositions? A machine learning approach

Adam Vandor^*, Marie van Vollenhoven, Gerhard Weiss, Gerasimos Spanakis

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

61 Downloads (Pure)

Abstract

Harmony in visual compositions is a concept that cannot be defined or easily expressed mathematically, even by humans. The goal of the research described in this paper was to find a numerical representation of artistic compositions with different levels of harmony. We ask humans to rate a collection of grayscale images based on the harmony they convey. To represent the images, a set of special features were designed and extracted. By doing so, it became possible to assign objective measures to subjectively judged compositions. Given the ratings and the extracted features, we utilized machine learning algorithms to evaluate the efficiency of such representations in a harmony classification problem. The best performing model (SVM) achieved 80% accuracy in distinguishing between harmonic and disharmonic images, which reinforces the assumption that concept of harmony can be expressed in a mathematical way that can be assessed by humans.

Original language	English
Title of host publication	Proceedings of the 13th International Conference on Agents and Artificial Intelligence - (Volume 2)
Subtitle of host publication	ICAART 2021
Editors	Ana Paula Rocha, Luc Steels, Jaap van den Herik
Pages	187-195
Number of pages	9
Volume	2
DOIs	https://doi.org/10.5220/0010244901870195
Publication status	Published - 2021
Event	13th International Conference on Agents and Artificial Intelligence - Vienna, Austria Duration: 4 Feb 2021 → 6 Feb 2021

Conference

Conference	13th International Conference on Agents and Artificial Intelligence
Abbreviated title	ICAART 2021
Country/Territory	Austria
City	Vienna
Period	4/02/21 → 6/02/21

Keywords

Artistic Compositions
Feature Extraction
Machine Learning

Access to Document

10.5220/0010244901870195Licence: CC BY-NC-ND

Full text Final published version, 5.07 MBLicence: Taverne

Cite this

Vandor, A., Vollenhoven, M. V., Weiss, G., & Spanakis, G. (2021). Can we detect harmony in artistic compositions? A machine learning approach. In A. P. Rocha, L. Steels, & J. van den Herik (Eds.), Proceedings of the 13th International Conference on Agents and Artificial Intelligence - (Volume 2): ICAART 2021 (Vol. 2, pp. 187-195) https://doi.org/10.5220/0010244901870195

@inproceedings{fec8d3b23fde4c97bfa0356ad2fbbf5a,

title = "Can we detect harmony in artistic compositions? A machine learning approach",

abstract = "Harmony in visual compositions is a concept that cannot be defined or easily expressed mathematically, even by humans. The goal of the research described in this paper was to find a numerical representation of artistic compositions with different levels of harmony. We ask humans to rate a collection of grayscale images based on the harmony they convey. To represent the images, a set of special features were designed and extracted. By doing so, it became possible to assign objective measures to subjectively judged compositions. Given the ratings and the extracted features, we utilized machine learning algorithms to evaluate the efficiency of such representations in a harmony classification problem. The best performing model (SVM) achieved 80% accuracy in distinguishing between harmonic and disharmonic images, which reinforces the assumption that concept of harmony can be expressed in a mathematical way that can be assessed by humans.",

keywords = "Artistic Compositions, Feature Extraction, Machine Learning",

author = "Adam Vandor and Vollenhoven, {Marie van} and Gerhard Weiss and Gerasimos Spanakis",

note = "DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.; 13th International Conference on Agents and Artificial Intelligence, ICAART 2021 ; Conference date: 04-02-2021 Through 06-02-2021",

year = "2021",

doi = "10.5220/0010244901870195",

language = "English",

isbn = "978-989-758-484-8",

volume = "2",

pages = "187--195",

editor = "Rocha, {Ana Paula} and Luc Steels and {van den Herik}, Jaap",

booktitle = "Proceedings of the 13th International Conference on Agents and Artificial Intelligence - (Volume 2)",

}

Vandor, A, Vollenhoven, MV, Weiss, G & Spanakis, G 2021, Can we detect harmony in artistic compositions? A machine learning approach. in AP Rocha, L Steels & J van den Herik (eds), Proceedings of the 13th International Conference on Agents and Artificial Intelligence - (Volume 2): ICAART 2021. vol. 2, pp. 187-195, 13th International Conference on Agents and Artificial Intelligence, Vienna, Austria, 4/02/21. https://doi.org/10.5220/0010244901870195

Can we detect harmony in artistic compositions? A machine learning approach. / Vandor, Adam; Vollenhoven, Marie van; Weiss, Gerhard et al.
Proceedings of the 13th International Conference on Agents and Artificial Intelligence - (Volume 2): ICAART 2021. ed. / Ana Paula Rocha; Luc Steels; Jaap van den Herik. Vol. 2 2021. p. 187-195.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Can we detect harmony in artistic compositions? A machine learning approach

AU - Vandor, Adam

AU - Vollenhoven, Marie van

AU - Weiss, Gerhard

AU - Spanakis, Gerasimos

N1 - DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2021

Y1 - 2021

N2 - Harmony in visual compositions is a concept that cannot be defined or easily expressed mathematically, even by humans. The goal of the research described in this paper was to find a numerical representation of artistic compositions with different levels of harmony. We ask humans to rate a collection of grayscale images based on the harmony they convey. To represent the images, a set of special features were designed and extracted. By doing so, it became possible to assign objective measures to subjectively judged compositions. Given the ratings and the extracted features, we utilized machine learning algorithms to evaluate the efficiency of such representations in a harmony classification problem. The best performing model (SVM) achieved 80% accuracy in distinguishing between harmonic and disharmonic images, which reinforces the assumption that concept of harmony can be expressed in a mathematical way that can be assessed by humans.

AB - Harmony in visual compositions is a concept that cannot be defined or easily expressed mathematically, even by humans. The goal of the research described in this paper was to find a numerical representation of artistic compositions with different levels of harmony. We ask humans to rate a collection of grayscale images based on the harmony they convey. To represent the images, a set of special features were designed and extracted. By doing so, it became possible to assign objective measures to subjectively judged compositions. Given the ratings and the extracted features, we utilized machine learning algorithms to evaluate the efficiency of such representations in a harmony classification problem. The best performing model (SVM) achieved 80% accuracy in distinguishing between harmonic and disharmonic images, which reinforces the assumption that concept of harmony can be expressed in a mathematical way that can be assessed by humans.

KW - Artistic Compositions

KW - Feature Extraction

KW - Machine Learning

U2 - 10.5220/0010244901870195

DO - 10.5220/0010244901870195

M3 - Conference article in proceeding

SN - 978-989-758-484-8

VL - 2

SP - 187

EP - 195

BT - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - (Volume 2)

A2 - Rocha, Ana Paula

A2 - Steels, Luc

A2 - van den Herik, Jaap

T2 - 13th International Conference on Agents and Artificial Intelligence

Y2 - 4 February 2021 through 6 February 2021

ER -

Can we detect harmony in artistic compositions? A machine learning approach

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this