Daniel Sharvit's Home Page

	Daniel Sharvit dsharv@yahoo.com Address1 Address2 Cambridge, MA zipcode 617-xxx-xxxx (voice - home) 617-xxx-xxxx (voice - work) 617-xxx-xxxx (fax) 514-xxx-xxxx (Montreal) ICQ: 12080xxx

Principal Investigations: Computer Vision / Computer Graphics

The use of shape as a cue for indexing into pictorial databases has been traditionally based on global invariant statistics and deformable templates, on the one hand, and local edge correlation on the other. We have proposed an intermediate approach based on a characterization of the symmetry in edge maps. The use of symmetry matching as a joint correlation measure between pairs of edge elements further constrains the comparison of edge maps. In addition, a natural organization of groups of symmetry into a hierarchy leads to a graph-based representation of relational structure of components of shape that allows for deformations by changing attributes of this relational graph. (latest database results ~50k)

Publications:

D.Sharvit, J.Chan, H.Tek, and B.B.Kimia, Symmetry-based Indexing of Image Databases, IEEE Workshop on Content-Based Access of Image and Video Libraries, June 1998.

D.Sharvit, J.Chan, H.Tek, and B.B.Kimia, Symmetry-based Indexing of Image Databases, Journal of Visual Communication and Image Representation, Dec. 1998.

S.Tirthapura, D.Sharvit, P.Klein, B.B.Kimia, Indexing Based on Edit-Distance Matching of Shape Graphs, SPIE Proceedings on Multimedia Storage and Archiving Systems III, pages 25-36, Nov. 1998.

Shape Indexing of Image Databases

Sketch in Perspective

Here are some cool images generated with my ray-tracer: Image1, Image2

Daniel Sharvit

Graduate Students Page

People Page

LEMS Home Page