In recent years, Convolutional Neural Networks (CNNs) have gained huge popularity among computer vision researchers. In this paper, we investigate how features learned by these networks in a supervised manner can be used to define a measure of self-similarity, an image feature that characterizes many images of natural scenes and patterns, and is also associated with images of artworks. Compared to a previously proposed method for measuring self-similarity based on oriented luminance gradients, our approach has two advantages. Firstly, we fully take color into account, an image feature which is crucial for vision. Secondly, by using higher-layer CNN features, we define a measure of selfsimilarity that relies more on image content than on basic local image features, such as luminance gradients.
Anselm Brachmann, Christoph Redies, "Defining Self-Similarity of Images Using Features Learned by Convolutional Neural Networks" in Proc. IS&T Int’l. Symp. on Electronic Imaging: Human Vision and Electronic Imaging, 2017, pp 188 - 194, https://doi.org/10.2352/ISSN.2470-1173.2017.14.HVEI-142