Please use this identifier to cite or link to this item: https://hdl.handle.net/10316/107208
Title: Visual complexity modelling based on image features fusion of multiple kernels
Authors: Fernandez-Lozano, Carlos
Carballal, Adrian
Machado, Penousal 
Santos, Antonino 
Romero, Juan 
Keywords: Correlation; Machine learning; Zipf's law; Compression error; Visual stimuli; Visual complexity
Issue Date: 2019
Publisher: PeerJ
Serial title, monograph or event: PeerJ
Volume: 7
Abstract: Humans' perception of visual complexity is often regarded as one of the key principles of aesthetic order, and is intimately related to the physiological, neurological and, possibly, psychological characteristics of the human mind. For these reasons, creating accurate computational models of visual complexity is a demanding task. Building upon on previous work in the field (Forsythe et al., 2011; Machado et al., 2015) we explore the use of Machine Learning techniques to create computational models of visual complexity. For that purpose, we use a dataset composed of 800 visual stimuli divided into five categories, describing each stimulus by 329 features based on edge detection, compression error and Zipf's law. In an initial stage, a comparative analysis of representative state-of-the-art Machine Learning approaches is performed. Subsequently, we conduct an exhaustive outlier analysis. We analyze the impact of removing the extreme outliers, concluding that Feature Selection Multiple Kernel Learning obtains the best results, yielding an average correlation to humans' perception of complexity of 0.71 with only twenty-two features. These results outperform the current state-of-the-art, showing the potential of this technique for regression.
URI: https://hdl.handle.net/10316/107208
ISSN: 2167-8359
DOI: 10.7717/peerj.7075
Rights: openAccess
Appears in Collections:I&D CISUC - Artigos em Revistas Internacionais

Files in This Item:
Show full item record

SCOPUSTM   
Citations

20
checked on Sep 16, 2024

WEB OF SCIENCETM
Citations

16
checked on Sep 2, 2024

Page view(s)

54
checked on Oct 9, 2024

Download(s)

30
checked on Oct 9, 2024

Google ScholarTM

Check

Altmetric

Altmetric


This item is licensed under a Creative Commons License Creative Commons