Refereed full papers (journals, book chapters, international conferences)

2004

@inproceedings{TuY2004,
	vgclass =	{refpap},
	author =	{Zhuowen Tu and Alan L. Yuille},
	title =	{Shape Matching and Recognition---Using Generative Models
	and Informative Features},
	booktitle =	{Proceedings of the Eighth European Conference on Computer
	Vision (ECCV 2004)},
	address =	{Prague, Czech Republic},
	pages =	{195--209},
	month =	{May~11--14},
	year =	{2004},
	url =	{http://www.springerlink.com/link.asp?id=5elnhnd65x2kynel},
	abstract =	{We present an algorithm for shape matching and recognition
	based on a generative model for how one shape can be generated by the
	other. This generative model allows for a class of transformations,
	such as affine and non-rigid transformations, and induces a similarity
	measure between shapes. The matching process is formulated in the EM
	algorithm. To have a fast algorithm and avoid local minima, we show how
	the EM algorithm can be approximated by using informative features,
	which have two key properties�invariant and representative. They are
	also similar to the proposal probabilities used in DDMCMC [13]. The
	formulation allows us to know when and why approximations can be made
	and justifies the use of bottom-up features, which are used in a wide
	range of vision problems. This integrates generative models and
	feature-based approaches within the EM framework and helps clarifying
	the relationships between different algorithms for this problem such as
	shape contexts [3] and softassign [5]. We test the algorithm on a
	variety of data sets including MPEG7 CE-Shape-1, Kimia silhouettes, and
	real images of street scenes. We demonstrate very effective performance
	and compare our results with existing algorithms. Finally, we briefly
	illustrate how our approach can be generalized to a wider range of
	problems including object detection.},
}