English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Assessing Aesthetics of Generated Abstract Images Using Correlation Structure

Khajehabdollahi, S., Martius, G., & Levina, A. (2019). Assessing Aesthetics of Generated Abstract Images Using Correlation Structure. In 2019 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 306-313). Piscataway, NJ, USA: IEEE.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0007-9B46-C Version Permalink: http://hdl.handle.net/21.11116/0000-0007-9B47-B
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Khajehabdollahi, S, Author
Martius, G., Author              
Levina, A1, Author              
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Can we generate abstract aesthetic images without bias from natural or human selected image corpi? Are aesthetic images singled out in their correlation functions? In this paper we give answers to these and more questions. We generate images using compositional pattern-producing networks with random weights and varying architecture. We demonstrate that even with the randomly selected weights the correlation functions remain largely determined by the network architecture. In a controlled experiment, human subjects picked aesthetic images out of a large dataset of all generated images. Statistical analysis reveals that the correlation function is indeed different for aesthetic images.

Details

show
hide
Language(s):
 Dates: 2019-12
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1109/SSCI44817.2019.9002779
 Degree: -

Event

show
hide
Title: IEEE Symposium Series on Computational Intelligence (SSCI 2019)
Place of Event: Xiamen, China
Start-/End Date: 2019-12-06 - 2019-12-09

Legal Case

show

Project information

show

Source 1

show
hide
Title: 2019 IEEE Symposium Series on Computational Intelligence (SSCI)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ, USA : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 306 - 313 Identifier: ISBN: 978-1-7281-2485-8