Title :
Rate-distortion theory applied to automatic object recognition
Author :
Shusterman, Eli ; Miller, Michael I. ; Rimoldi, Bixio
Author_Institution :
Orckit Commun. Ltd., Tel-Aviv, Israel
fDate :
8/1/2000 12:00:00 AM
Abstract :
We consider the problem of recognizing CAD models at arbitrary orientations observed via the projective transformation on an imaging sensor with noise. Bounds on codebook size are established through the rate-distortion curve for a distortion measure derived from the Hilbert-Schmidt norm for elements of the orthogonal group
Keywords :
CAD; computational complexity; group theory; image representation; noise; object recognition; rate distortion theory; video coding; CAD models recognition; Hilbert-Schmidt distortion measure; Hilbert-Schmidt norm; arbitrary orientations; automatic object recognition; automatic target recognition; codebook size bounds; distortion measure; error metrics; imaging sensor; noise; orthogonal group elements; projective transformation; rate-distortion curve; rate-distortion theory; representation complexity; video projection sensor; Design automation; Distortion measurement; Image recognition; Image sensors; Object recognition; Rate-distortion; Shape; Size measurement; Target recognition; Tiles;
Journal_Title :
Information Theory, IEEE Transactions on
