Next Article in Journal
Limitations to Estimating Mutual Information in Large Neural Populations
Next Article in Special Issue
Gaze Information Channel in Van Gogh’s Paintings
Previous Article in Journal
Useful Dual Functional of Entropic Information Measures
Open AccessArticle

Comparison of Outlier-Tolerant Models for Measuring Visual Complexity

1
CITIC-Research Center of Information and Communication Technologies, University of A Coruña, 15071 A Coruña, Spain
2
Department of Computer Science and Information Technologies, Faculty of Computer Science, University of A Coruña, Campus Elviña s/n, 15071 A Coruña, Spain
3
Department of Computer Science and Information Technologies, Faculty of Communication Science, University of A Coruña, Campus Elviña s/n, 15071 A Coruña, Spain
*
Author to whom correspondence should be addressed.
Entropy 2020, 22(4), 488; https://doi.org/10.3390/e22040488
Received: 20 February 2020 / Revised: 18 April 2020 / Accepted: 23 April 2020 / Published: 24 April 2020
Providing the visual complexity of an image in terms of impact or aesthetic preference can be of great applicability in areas such as psychology or marketing. To this end, certain areas such as Computer Vision have focused on identifying features and computational models that allow for satisfactory results. This paper studies the application of recent ML models using input images evaluated by humans and characterized by features related to visual complexity. According to the experiments carried out, it was confirmed that one of these methods, Correlation by Genetic Search (CGS), based on the search for minimum sets of features that maximize the correlation of the model with respect to the input data, predicted human ratings of image visual complexity better than any other model referenced to date in terms of correlation, RMSE or minimum number of features required by the model. In addition, the variability of these terms were studied eliminating images considered as outliers in previous studies, observing the robustness of the method when selecting the most important variables to make the prediction. View Full-Text
Keywords: machine learning; sisual complexity; visual stimuli; correlation; human-computer interaction; compression error; psychiatry and psychology machine learning; sisual complexity; visual stimuli; correlation; human-computer interaction; compression error; psychiatry and psychology
Show Figures

Figure 1

MDPI and ACS Style

Carballal, A.; Fernandez-Lozano, C.; Rodriguez-Fernandez, N.; Santos, I.; Romero, J. Comparison of Outlier-Tolerant Models for Measuring Visual Complexity. Entropy 2020, 22, 488. https://doi.org/10.3390/e22040488

AMA Style

Carballal A, Fernandez-Lozano C, Rodriguez-Fernandez N, Santos I, Romero J. Comparison of Outlier-Tolerant Models for Measuring Visual Complexity. Entropy. 2020; 22(4):488. https://doi.org/10.3390/e22040488

Chicago/Turabian Style

Carballal, Adrian; Fernandez-Lozano, Carlos; Rodriguez-Fernandez, Nereida; Santos, Iria; Romero, Juan. 2020. "Comparison of Outlier-Tolerant Models for Measuring Visual Complexity" Entropy 22, no. 4: 488. https://doi.org/10.3390/e22040488

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop