Exploring Scale-Induced Feature Hierarchies in Natural Images
Recently there has been considerable interest in topic models based on the bag-of-features representation of images. The strong independence assumption inherent in the bag-of-features representation is not realistic however: patches often overlap and share underlying image structures. Moreover, important information with respect to relative scales of the features is completely ignored, for the sake of scale invariance. Considering both spatial and scalebased constraints one can derive spatially constrained natural feature hierarchies within images. We explore the use of topic models that build such spatially constrained scaleinduced hierarchies of the features in an unsupervised fashion. Our model uses standard topic models as a starting point. We then incorporate information about the hierarchical and spatial relations of the features into the model. We illustrate the hierarchical nature of the resulting models using datasets of natural images, including the MSRC2 dataset as well as a challenging set of images of trees collected from the Internet.