---------------------------------------------------------------------------


		     B O S T O N   U N I V E R S I T Y

			Computer Science Department

			    C O L L O Q U I U M


		       Image Retrieval by Appearance
			
			     Raghavan Manmatha
				     
	       Center for Intelligent Information Retrieval
			Computer Science Department
		   University of Massachusetts, Amherst.

			   Wednesday, October 7
				  3:00pm

			 (Coffee served at 2:45pm)

			  Seminar Room / MCS 135




The  retrieval  of images based on  their  visual similarity to  an example
image is  an important and  fascinating area of research.   In this talk, I
will    discuss how  to characterize   visual   appearance for  determining
similarity between images.

We represent visual  appearance using local  features  computed at multiple
scales. Such local features may include the outputs of images filtered with
Gaussian derivatives, differential invariants  or geometric quantities like
curvature  and phase. Two images   may be said  to be  similar if they have
similar distributions of such  features.  Global similarity may, therefore,
be deduced  by comparing histograms   of such features.   This can  be done
rapidly.  Histograms cannot be used to  compute local similarity.  Instead,
the constraint that  the spatial relationship between  the features in  the
query be similar to  the spatial relationship  between the features  of its
matching counterparts in the database  provides a means for computing local
similarity. 

This is joint work with S. Chandu Ravela

Host: Prof. Stan Sclaroff (sclaroff@bu.edu)

----------------------------------------------------------------------------
  For colloquium info and directions, see http://www.cs.bu.edu/colloquium
----------------------------------------------------------------------------