Aesthetics, in the world of art and photography, refers to the principles of the nature and appreciation of beauty. Judging beauty and other aesthetic qualities of photographs is a highly subjective task. Hence, there is no unanimously agreed standard for measuring aesthetic value. In spite of the lack of firm rules, certain features in photographic images are believed, by many, to please humans more than certain others. In this paper, we treat the challenge of automatically inferring aesthetic quality of pictures using their visual content as a machine learning problem, with a peer-rated online photo sharing Website as data source. We extract certain visual features based on the intuition that they can discriminate between aesthetically pleasing and displeasing images. Automated classifiers are built using support vector machines and classification trees. Linear regression on polynomial terms of the features is also applied to infer numerical aesthetics ratings. The work attempts to explore the relationship between emotions which pictures arouse in people, and their low-level content. Potential applications include content-based image retrieval and digital photography.

I n this tutorial, we define and discuss key aspects of the problem of computational inference of aesthetics and emotion from images. We begin with a background discussion on philosophy, photography, paintings, visual arts, and psychology. This is followed by introduction of a set of key computational problems that the research community has been striving to solve and the computational framework required for solving them. We also describe data sets available for performing assessment and outline several real-world applications where research in this domain can be employed. A significant number of papers that have attempted to solve problems in aesthetics and emotion inference are surveyed in this tutorial. We also discuss future directions that researchers can pursue and make a strong case for seriously attempting to solve problems in this research domain.

We investigated how shape features in natural images influence emotions aroused in human beings. Shapes and their characteristics such as roundness, angularity, simplicity, and complexity have been postulated to affect the emotional responses of human beings in the field of visual arts and psychology.However, no prior research has modeled the dimensionality of emotions aroused by roundness and angularity.Our contributions include an in-depth statistical analysis to understand the relationship between shapes and emotions. Through experimental results on the International Affective Picture System (IAPS) dataset we provide evidence for the significance of roundness-angularity and simplicitycomplexity on predicting emotional content in images. We combine our shape features with other state-of-theart features to show a gain in prediction and classification accuracy.We model emotions from a dimensional perspective in order to predict valence and arousal ratings which have advantages over modeling the traditional discrete emotional categories. Finally, we distinguish images with strong emotional content from emotionally neutral images with high accuracy.

BackgroundAnkylosing spondylitis (AS) is an autoimmune rheumatic disease mostly affecting the axial skeleton. Currently, anti-tumour necrosis factor α (anti-TNF-α) represents an effective treatment for AS that may delay the progression of the disease and alleviate the symptoms if the diagnosis can be made early. Unfortunately, effective diagnostic biomarkers for AS are still lacking; therefore, most patients with AS do not receive timely and effective treatment. The intent of this study was to determine several key metabolites as potential biomarkers of AS using metabolomic methods to facilitate the early diagnosis of AS.MethodsFirst, we collected samples of plasma, urine, and ligament tissue around the hip joint from AS and control groups. The samples were examined by nuclear magnetic resonance spectrometry, and multivariate data analysis was performed to find metabolites that differed between the groups. Subsequently, according to the correlation coefficients, variable importance for the projection (VIP) and P values of the metabolites obtained in the multivariate data analysis, the most crucial metabolites were selected as potential biomarkers of AS. Finally, metabolic pathways involving the potential biomarkers were determined using the Kyoto Encyclopedia of Genes and Genomes (KEGG) database, and the metabolic pathway map was drawn.ResultsForty-four patients with AS agreed to provide plasma and urine samples, and 30 provided ligament tissue samples. An equal number of volunteers were recruited for the control group. Multidimensional statistical analysis suggested significant differences between the patients with AS and control subjects, and the models exhibited good discrimination and predictive ability. A total of 20 different metabolites ultimately met the requirements for potential biomarkers. According to KEGG analysis, these marker metabolites were primarily related to fat metabolism, intestinal microbial metabolism, glucose metabolism and choline metabolism pathways, and they were also probably associated with immune regulation.ConclusionsOur work demonstrates that the potential biomarkers that were identified appeared to have diagnostic value for AS and deserve to be further investigated. In addition, this work also suggests that the metabolomic profiling approach is a promising screening tool for the diagnosis of patients with AS.

No abstract