Classification of Paintings by Artistic Style Using Color and Texture Features

Abstract

In this paper, an approach for the classification of paintings by artistic style using color and texture features is proposed. Our approach automatically extracts a set of visual features that effectively discriminate among diverse artistic styles. Additionally, our proposal performs an effective selection of the most relevant features to be used in an artificial neural network architecture. Using the most important features allows our system to achieve an efficient learning process. The proposed system analyzes digitized paintings using acombination of color and texture features, which have shown to be highly discriminatory. Our approach consists of two main stages: training and testing. Firstly, in the training stage, the features from seven artistic styles are extracted to train a multi-layer perceptron. Secondly, the learned model is utilized to determine the artistic style of a given incoming painting to our system. The experimental results, on an extensive dataset of digitized paintings, show that our method obtains a higher accuracy in comparison with those obtained by the state-of-the-art methods. Moreover, our proposal attains a higher accuracy rate using fewer features descriptors.