Evaluating Photo Aesthetics Using Machine Learning

In this paper we propose a method for automatic assessment of aesthetic appeal of photographs. We identify significant parameters that distinguish high quality photography from low quality snapshots. On the basis of these parameters, we defined calculable features for automatic assessment of photography aesthetics using machine learning methods. The calculation of features depends heavily on the identification of the subject in photographs. With the subject identified, we defined and implemented various features to analyze various aspects of a photograph. The features were tested on two datasets. First dataset was obtained from Flickr and manually labeled for evaluation. Second dataset was based on photographs from DPChallenge portal where subjects were identied with a face detection algorithm. Both experiments showed some promising results. In this article we specify the features which contribute to a successful classication of photographs, analyze their in influence and discuss the results. In conclusion, we offer some suggestions for further research.