Research on the classification of the paintings of 10 impressionist painters through deep learning

Abstract

Since professional Go players Lee Sedol and Jie Ke were beaten by AlphaGo which was developed by Google’s sister company Deepmind, the artificial technology be- hinds it, deep learning (DL), has been drawn attention to people all over the world. Although the goal of this research is just to simply classify paintings of 10 impressionists, by using a convolutional neural network (CNN), there is something interesting found during the research to suggest that how powerful deep learning is. For the author himself, he cannot do that and even his friends who learning impressionists. The dataset is acquired from the Kaggle (Impressionist_Classifier_Data), which helps for this research to classify Impressionist painters into 10 categories including Camille Pisarro, Childe Hassam, Claude Monet, Edgar Degas, Henri Matisse, John Singer- Sargent, Paul Cezanne, Paul Gauguin, Pierre-Auguste Renoir, Vincent van Gogh. This research starts with introducing convolutional neural networks (CNNs) including convolutional layer, filters, pooling layer, fully connected layer. Then, based on the test result of the classifier, the author shows accuracy, loss graphof the training session, accuracy, precision, recall, macro f1-score, confusion matrix and unexpected findings of the classifier. The accuracy of the classifier is around 95 percent in training, 60 percent in validation and 83 percent in testing. The author found that even though he changed color of the test painting and transfer the style of painting, the classifier can still predict correctly.