Classification of Photo and Sketch Images Using Convolutional Neural Networks

In this study we propose a Convolutional Neural Network(CNN) which can classify hand drawn sketch images. Though CNN is known to be very effective on classification of realistic images, there are few studies on CNN dealing with nonphotorealistic images and even more images those types are mixing. Classifying non-photorealistic images is difficult mainly because there are no large datasets. In this paper, to classify sketch images using CNN, we propose the simple method to make training datasets from photo and illustration images. We also made several training datasets and compared the accuracy of the trained CNN models. Our proposed method is shown to be effective on classification task of not only sketch images but also the mixed dataset of photo and sketch images.