Aesthetic preference for art emerges from a weighted integration over hierarchically structured visual features in the brain (original) (raw)
Related papers
Lecture Notes in Computer Science, 2016
Understanding the underlying processes of aesthetic perception is one of the ultimate goals in empirical aesthetics. While deep learning and convolutional neural networks (CNN) already arrived in the area of aesthetic rating of art and photographs, only little attempts have been made to apply CNNs as the underlying model for aesthetic perception. The information processing architecture of CNNs shows a strong match with the visual processing pipeline in the human visual system. Thus, it seems reasonable to exploit such models to gain better insight into the universal processes that drives aesthetic perception. This work shows first results supporting this claim by analyzing already known common statistical properties of visual art, like sparsity and self-similarity, with the help of CNNs. We report about observed differences in the responses of individual layers between art and non-art images, both in forward and backward (simulation) processing, that might open new directions of research in empirical aesthetics.
Artificial intelligence has emerged as a powerful computational tool to create artworks. One application is Neural Style Transfer, which allows to transfer the style of one image, such as a painting, onto the content of another image, such as a photograph. In the present study, we ask how Neural Style Transfer affects objective image properties and how beholders perceive the novel (style-transferred) stimuli. In order to focus on the subjective perception of artistic style, we minimized the confounding effect of cognitive processing by eliminating all representational content from the input images. To this aim, we transferred the styles of 25 diverse abstract paintings onto 150 colored random-phase patterns with six different Fourier spectral slopes. This procedure resulted in 150 style-transferred stimuli. We then computed eight statistical image properties (complexity, self-similarity, edge-orientation entropy, variances of neural network features, and color statistics) for each image. In a rating study, we asked participants to evaluate the images along three aesthetic dimensions (Pleasing, Harmonious, and Interesting). Results demonstrate that not only objective image properties, but also subjective aesthetic preferences transferred from the original artworks onto the styletransferred images. The image properties of the style-transferred images explain 50-69% of the variance in the ratings. In the multidimensional space of statistical image properties, participants considered style-transferred images to be more Pleasing and Interesting if they were closer to a "sweet spot" where traditional Western paintings (JenAesthetics dataset) are represented. We conclude that NST is a useful tool to create novel artistic stimuli that preserve the image properties of the input style images. In the novel stimuli, we found a strong relationship between statistical image properties and subjective ratings, suggesting a prominent role of perceptual processing in the aesthetic evaluation of abstract images.
Brain-Inspired Deep Networks for Image Aesthetics Assessment
ArXiv, 2016
Image aesthetics assessment has been challenging due to its subjective nature. Inspired by the scientific advances in the human visual perception and neuroaesthetics, we design Brain-Inspired Deep Networks (BDN) for this task. BDN first learns attributes through the parallel supervised pathways, on a variety of selected feature dimensions. A high-level synthesis network is trained to associate and transform those attributes into the overall aesthetics rating. We then extend BDN to predicting the distribution of human ratings, since aesthetics ratings are often subjective. Another highlight is our first-of-its-kind study of label-preserving transformations in the context of aesthetics assessment, which leads to an effective data augmentation approach. Experimental results on the AVA dataset show that our biological inspired and task-specific BDN model gains significantly performance improvement, compared to other state-of-the-art models with the same or higher parameter capacity.
Towards a framework for the study of the neural correlates of aesthetic preference
Aiming to provide a tentative framework for the study of the neural correlates of aesthetic preference, we review three recent neuroimaging studies carried out with the purpose of locating brain activity associated with decisions about the beauty of visual stimuli (Cela-Conde et al., 2004; Kawabata and Zeki, 2004; Vartanian and Goel, 2004). We find that the results of the three studies are not in line with previous neuropsychological data. Moreover, there are no coincidences among their results. However, when they are mapped on to Chatterjee’s (2003) neuropsychological model of aesthetic preference it becomes clear that neuroimaging data are not contradictory, but complementary, and their interpretation is enriched. The results of these studies suggest that affective processes have an important role in aesthetic preference, and that they are integrated with cognitive processes to reach a decision regarding the beauty of visual stimuli. Future studies must aim to clarify whether certain methodological procedures are better suited to study any of the particular cognitive operations involved in aesthetic preference, and ascertain the extent to which the proposed framework is compatible with the aesthetic appreciation of musical stimuli. Keywords: Brain; fMRI; MEG; aesthetic preference; beauty.
Comparing Neural and Attractiveness-based Visual Features for Artwork Recommendation
Proceedings of the 2nd Workshop on Deep Learning for Recommender Systems, 2017
Advances in image processing and computer vision in the latest years have brought about the use of visual features in artwork recommendation. Recent works have shown that visual features obtained from pre-trained deep neural networks (DNNs) perform extremely well for recommending digital art. Other recent works have shown that explicit visual features (EVF) based on a ractiveness can perform well in preference prediction tasks, but no previous work has compared DNN features versus speci c a ractivenessbased visual features (e.g. brightness, texture) in terms of recommendation performance. In this work, we study and compare the performance of DNN and EVF features for the purpose of physical artwork recommendation using transactional data from UGallery, an online store of physical paintings. In addition, we perform an exploratory analysis to understand if DNN embedded features have some relation with certain EVF. Our results show that DNN features outperform EVF, that certain EVF features are more suited for physical artwork recommendation and, nally, we show evidence that certain neurons in the DNN might be partially encoding visual features such as brightness, providing an opportunity for explaining recommendations based on visual neural models.
2020
Neural style transfer is a popular deep learning algorithm to generate images to mimic human artistry. This work applies the psychological method of the two-alternative forced choice (2afc) task to measure aesthetic preferences for neural style generated images. Portrait photos of three popular celebrities were generated by varying three parameters of neural style transfer in five configuration levels. Participants had to choose the image they preferred aesthetically from all pairwise combinations of configurations per style. The rate of being chosen was calculated for each neural style transfer configuration level. The findings show a differentiated picture of aesthetic preferences. On the one side, they indicate that people prefer images rendered with 500 iterations and a learning rate of 2e1, i.e. configurations that allow them to recognize the structure of the portrait image despite the stylization. On the other side, aesthetic preferences peak for two distinctly different conte...
Journal of Information and Telecommunication, 2019
This research introduces a learning model that estimates the cognitive perception of aesthetics. Taking psychology into account, this bridges the gap between human and machine. The goal is to build a machine-learning model that can estimate beauty in images perceived by human eyes. We have summand our research [Firoze, A., Osman, T., Psyche, S. S., & Rahman, R. M. (2018). Scoring photographic rule of thirds in a large MIRFLICKR dataset: A showdown between machine perception and human perception of image aesthetics. Asian Conference on Intelligent Information and Database Systems (pp. 466–475), Springer; Osman, T., Psyche, S. S., Deb, T., Firoze, A., & Rahman, R. M. (2018). Differential color harmony: A robust approach for extracting Harmonic Color features and perceive aesthetics in a large dataset. International Conference on Big Data and Cloud Computing, Springer] together with the idea of humans’ personal preferences and achieved higher than state of the art performances. An exte...
Acta Psychologica
While global image properties (GIPs) relate to preference ratings in many categories of visual stimuli, this relationship is typically not seen for abstract art paintings. Using computational network science and empirical methods, we further investigated GIPs and subjective preferences. First, we replicated the earlier observation that GIPs do not relate to preferences for abstract art. Next, we estimated the network structure of abstract art paintings using two approaches: the first was based on verbal descriptions and the second on GIPs. We examined the extent to which network measures computed from these two networks (1) related to preference for abstract art paintings and (2) determined affiliation of images to specific art styles. Only semantic-based network predicted the subjective preference ratings and art style. Finally, preference and GIPs differed for subgroups of abstract art paintings. Our results demonstrate the importance of verbal descriptors in evaluating abstract art, and that it is not useful in empirical aesthetics to treat abstract art paintings as a single category. 1.2. Global image properties and evaluation of images Formalist approaches focus on objective psychophysical image properties. One family of such objective properties is Global Image Properties (GIP), i.e. objective features that refer to the entire image
Cognitive Systems Research
With the increased sophistication of AI techniques, the application of these systems has been expanding to ever newer fields. Increasingly, these systems are being used in modeling of human aesthetics and creativity, e.g. how humans create artworks and design products. Our lab has developed one such AI creativity deep learning system that can be used to create artworks in the form of images and videos. In this paper, we describe this system and its use in studying the human visual system and the formation of aesthetic experiences. Specifically, we show how time-based AI created media can be used to explore the nature of the dual-pathway neuro-architecture of the human visual system and how this relates to higher cognitive judgments such as aesthetic experiences that rely on these divergent information streams. We propose a theoretical framework for how the movement within percepts such as video clips, causes the engagement of reflexive attention and a subsequent focus on visual information that are primarily processed via the dorsal stream, thereby modulating aesthetic experiences that rely on information relayed via the ventral stream. We outline our recent study in support of our proposed framework, which serves as the first study that investigates the relationship between the two visual streams and aesthetic experiences.