Hierarchical Object Groups for Scene Classification

The hierarchical structures that exist in natural scenes have been utilized for many tasks in computer vision. The basic idea is that instead of using strictly low level features it is possible to combine them into higher level hierarchical structures. These higher level structures provide a more specific feature and can thus lead to better results in classification or detection. Although most previous work has focused on hierarchical combinations of low level features, hierarchical structures exist on higher levels as well. In this work we attempt to automatically discover these higher level structures by finding meaningful object groups using the Minimum Description Length (MDL) principle. We then use these structures for scene classification and show that we can achieve a higher accuracy rate using them.

Fig 1. Given a labeled image (a) we can construct a graph which represents the different objects and their spatial relationships in the image (b). We then use the MDL principle to discover groups of objects which are able to compress the graph by replacing them with a single node (c). These object groups represent higher order concepts in the image, and therefore we predict they will be useful for different tasks. In this paper we show their usefulness for the task of scene classification (d).

Publication:

A. Sadovnik and T. Chen, “Hierarchical Object Groups for Scene Classification“, IEEE International Conference on Image Processing (ICIP)2012.