Classification and Aesthetic Evaluation of Paintings and Artworks

Abstract

Painters and Artists have contributed to the field of art over the years with their exceptional talent and skills. The Internet is full of their creativity and imagination where one can find most of their work. Like any other information present on the Internet, paintings are also not well organized. In this paper, a method is proposed to classify paintings with the help of support vector machine classifier using features extracted by a pre trained convolutional neural network-AlexNet. A painting is not only an art on paper but is a medium to arouse emotions and sense of pleasure within the audience. Aesthetic Evaluation aims at evaluation/rating a painting or an artwork on the basis of various parameters like style, topic, emotional engagement etc. which cannot be done by a machine alone. So we cannot leave behind the human inputs while determining the aesthetic value of a painting or an artwork. In this paper we also propose a method to judge or evaluate the aesthetic value of a painting by training a regression model with several image features, like Local Binary Pattern for texture, color histogram for color, Histogram of Oriented Gradients for edges and GIST for scene recognition in the painting, against human ratings for each painting. A dataset constituting of 1225 digital images of paintings of 7 categories is used for classifying and evaluating the aesthetic value. The classification phase was found to have 92.73% accuracy and the evaluation phase performed with an accuracy of 64.15%.