Abstract

This paper addresses the task of natural texture and appearance clas- si fication. Our goal is to develop a simple and intuitive method that performs at state of the art on datasets ranging from homogeneous texture (e.g., material texture), to less homogeneous texture (e.g., the fur of animals), and to inhomo- geneous texture (the appearance patterns of vehicles). Our method uses a bag- of-words model where the features are based on a dictionary of active patches. Active patches are raw intensity patches which can undergo spatial transforma- tions (e.g., rotation and scaling) and adjust themselves to best match the image regions. The dictionary of active patches is required to be compact and represen- tative, in the sense that we can use it to approximately reconstruct the images that we want to classify. We propose a probabilistic model to quantify the quality of image reconstruction and design a greedy learning algorithm to obtain the dic- tionary. We classify images using the occurrence frequency of the active patches. Feature extraction is fast (about 100 ms per image) using the GPU. The experi- mental results show that our method improves the state of the art on a challenging material texture benchmark dataset (KTH-TIPS2). To test our method on less ho- mogeneous or inhomogeneous images, we construct two new datasets consisting of appearance image patches of animals and vehicles cropped from the PASCAL VOC dataset. Our method outperforms competing methods on these datasets.