Edge-Orientation Entropy Predicts Preference for Diverse Types of Man-Made Images

Abstract

We recently found that luminance edges are more evenly distributed across orientations in large subsets of traditional artworks, i.e., artworks are characterized by a relatively high entropy of edge orientations, when compared to several categories of other (non-art) images. In the present study, we asked whether edge-orientation entropy is associated with aesthetic preference in a wide variety of other man-made visual patterns and scenes. In the first (exploratory) part of the study, participants rated the aesthetic appeal of simple shapes, artificial ornamental patterns, facades of buildings, scenes of interior architecture, and music album covers. Results indicated that edge-orientation entropy predicts aesthetic ratings for these stimuli. However, the magnitude of the effect depended on the type of images analyzed, on the range of entropy values encountered, and on the type of aesthetic rating (pleasing, interesting, or harmonious). For example, edge-orientation entropy predicted about half of the variance when participants rated facade photographs for pleasing and interesting, but only for 3.5% of the variance for harmonious ratings of music album covers. We also asked whether edge-orientation entropy relates to the well-established human preference for curved over angular shapes. Our analysis revealed that edge-orientation entropy was as good or an even better predictor for the aesthetic ratings than curvilinearity. Moreover, entropy could substitute for shape, at least in part, to predict the aesthetic ratings. In the second (experimental) part of this study, we generated complex line stimuli that systematically varied in their edge-orientation entropy and curved/angular shape. Here, edge-orientation entropy was a more powerful predictor for ratings of pleasing and harmonious than curvilinearity, and as good a predictor for interesting. Again, the two image properties shared a large portion of variance between them. In summary, our results indicate that edge-orientation entropy predicts aesthetic ratings in diverse man-made visual stimuli. Moreover, the preference for high edge-orientation entropy shares a large portion of predicted variance with the preference for curved over angular stimuli.

Aesthetic Perception of Line Patterns: Effect of Edge-Orientation Entropy and Curvilinear Shape

“…Because straight lines represent exactly one orientation and curved lines comprise many orientations, Entropy and curved/angular shape relate to each other. Grebenkina et al (2018) reported that the two features share a large portion of predicted variance for preference ratings. For ratings of how pleasing and harmonious particular stimuli are, edge orientation entropy turned out to be a more powerful predictor than curvilinearity; in other words, shape was not the decisive feature that determined the aesthetic rating, but it was partially overridden by edge-orientation entropy.…”

Global Image Properties Predict Ratings of Affective Pictures

“…Second, a larger 1st-order entropy of edge orientations coincides with higher arousal ratings in all datasets. This measure assumes high values in traditional artworks (Redies et al, 2017) and is positively correlated with ratings for pleasing and interesting in photographs of building facades, but less so in other visual patterns, such as music CD covers (Grebenkina et al, 2018). Third, the left/right and up/down symmetry ratings correlate with valence and arousal ratings in all datasets, underlining the importance of (a)symmetry in esthetic perception (Jacobsen and Höfel, 2002;Gartus and Leder, 2013;Wright et al, 2017).…”

“…For example, in the study by Sidhu et al (2018), predicted variances ranged from 4% (for beauty ratings of abstract art) to 30% (for liking rating of representational art). Grebenkina et al (2018) reported predicted variances between 5% (for pleasing ratings of CD album covers) and 55% (for liking ratings of building facade photographs). Schwabe et al (2018) analyzed abstract artworks and non-artistic images and obtained predicted variances that ranged from 27 to 46% for ratings of how harmonious and ordered the images were, respectively.…”

“…Values for both entropies are high in some photographs of natural objects (for example, lichen growth patterns) and in artworks of different cultural provenance (Redies et al, 2017). Moreover, the edge-orientation entropies are predictors for esthetic ratings in diverse other types of man-made visual stimuli, for example, photographs of building facades or artificial geometrical and line patterns (Grebenkina et al, 2018). We calculated the two entropies by the method described in detail by Redies et al (2017).…”

“…Because natural and visually pleasing images share some formal characteristics, it has been speculated that efficient processing might be the basis of esthetic perception as well (Redies, 2007;Renoult et al, 2016). A causal link between some of the image properties and visual preference has been established experimentally (Schweinhart and Essock, 2013;Jacobs et al, 2016;Spehar et al, 2016;Nascimento et al, 2017;Grebenkina et al, 2018;Menzel et al, 2018). Interestingly, human observers often perceive images with Fourier spectra that deviate from natural (scale-invariant) statistics as unpleasant (Juricevic et al, 2010;O'Hare and Hibbard, 2011).…”