Shimon Ullman
The Ruth and Samy Cohn Professor of Computer Sciences
My general area of research is the
study of vision — including the processing of visual information by the human
visual system, and computer vision. The goals of this research are to understand
how our own visual system operates, and how to construct artificial systems
with visual capabilities. The focus of my research in on object recognition,
classification, image segmentation, and the biological modeling of information
processing in the visual cortex.
The current work attempts to develop a unified approach to visual classification, recognition and segmentation. The approach is based on representing shapes within a class by a hierarchy of shared sub-structures called fragments. The fragments are sub-images selected automatically, by maximizing the mutual information of the fragments and the class they represent. For the task of individual recognition, these fragments are generalized to become extended fragments, which are equivalence sets of fragments, representing the same object part under different viewing conditions. Image segmentation into an object and background is combined in this approach with the classification process. This is in contrast with the more common view, in which image segmentation is performed first, in a bottom-up manner, followed by object recognition.
Recent publications
- [with E. Borenstein] Class specific top down-segmentation. Proceedings of the European Conference on Computer Vision (2002) 110-122.
- [with M. Vidal-Naquet] Object Recognition with Informative Features and Linear Classification. Proceedings of the 9th International Conference on Computer Vision (2003) 281-288.
- [with E. Bart] Recognition invariance obtained by extended and invariant features. Neural Networks, in press.