An Information Theory Approach to Aesthetic Assessment of Visual Patterns.

Abdullah Khalili,Hamid Bouchachia

doi:10.3390/e23020153

Abstract

The question of beauty has inspired philosophers and scientists for centuries. Today, the study of aesthetics is an active research topic in fields as diverse as computer science, neuroscience, and psychology. Measuring the aesthetic appeal of images is beneficial for many applications. In this paper, we will study the aesthetic assessment of simple visual patterns. The proposed approach suggests that aesthetically appealing patterns are more likely to deliver a higher amount of information over multiple levels in comparison with less aesthetically appealing patterns when the same amount of energy is used. The proposed approach is evaluated using two datasets; the results show that the proposed approach is more accurate in classifying aesthetically appealing patterns compared to some related approaches that use different complexity measures.

Highlights

The results suggest that the distances between the energies of the levels are more likely to be different for aesthetically appealing patterns
In the case of music, the first case will give a piece with only one note repeated many times, and the second case will produce a piece with all possible notes; in both cases, no aesthetically appealing patterns will be produced, as the first pattern will be too regular and the second one will be too random
If we arrange the aesthetically appealing pattern such that the pixels with the same values are close to each other, the gradient of the resulted pattern will produce a distribution closer to a pulse than the gradient of the original pattern, and again the distribution of the gradient of aesthetically appealing patterns represents a balance between these two extreme cases, and the closer we get to the Maxwell–Boltzmann distribution, the higher the aesthetic score of the pattern

Summary

Introduction

An Information Theory Approach to Aesthetic Assessment of Visual. Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Results

Discussion

Conclusion