Visual Graph Modeling for Image Categorization and Robot Localization

Image analysis and retrieval may need to consider several types of visual features and spatial information between them (e.g. different points of views of an image). This paper presents a novel approach that exploits an extension of the language modeling approach from information retrieval to the problem of graph-based image retrieval and categorization. Such versatile graph model is needed to represent the multiple points of views of images. A language model is defined on such graphs to handle a fast graph matching. We present the experiments achieved with several instances of the proposed model on two collections of images (one composed of 3849 touristic images and one composed of 3633 images captured by a mobile robot), and show that the results obtained using visual graph model improve the accuracies of the results.