Tuesday, 20 July 2004, 2pm:

<CENTER><B>Visual patterns with matching subband statistics</B>

<P>
Joshua Gluckman<BR>
Dept. of Computer Science, Brooklyn Polytechnic University

</CENTER>

Statistical representations of visual patterns are commonly used in
computer vision, image processing and pattern recognition. One such
representation is a statistical distribution measured from the output
of a bank of filters (Gaussian, Laplacian, Gabor, wavelet etc). Both
marginal and joint distributions of filter responses have been
advocated and effectively used for a variety of vision tasks
including: image retrieval, object recognition, texture analysis and
texture synthesis.  We begin by examining the ability of these
statistical representations to discriminate between an arbitrary pair
of visual stimuli. Examples of patterns are derived that provably
possess the same statistical properties, yet are visually distinct. We
further analyze these representations by studying classes of patterns
with matching statistical properties. In particular, we show that
these representations are effectively blind to certain phase
correlations. Finally, we derive higher order whitening
transformations that remove statistical redundancies from
images. These transformations effectively remove any information from
the marginal and joint subband statistics. Thus, they demonstrate what
image properties these subband statistics dont see.