Recognizing surreal compositions in digitized paintings

This paper addresses the problem of recognizing illogical object juxtaposing in the specific form of classifying digitized paintings in art movements. More precisely we distinguish between realism and surrealism movements. We propose a system based on feature extraction and machine learning that is able to understand the scene in the digitized paintings and to classify the art works from the two movements. We will show that global GIST features being able to access the image content, complemented by random forest classifier, give good accuracy for this task.