Texture Retrieval Using Scattering Coefficients and Probability Product Kernels

Alexander Sagel, Dominik Meyer, Hao Shen

Abstract: In this paper we introduce a content based image retrieval system that leverages the benefits of the scattering transform as a means of feature extraction. To measure similarity between feature vectors, we adapt a probability product kernel and derive an approximate version which can be implemented efficiently. The proposed approach achieves a retrieval performance superior to comparable filterbank transform systems.