Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published April 1998 | public
Journal Article Open

Efficient deformable filter banks

Abstract

This article describes efficient schemes for the computation of a large number of differently scaled/oriented filtered versions of an image. We generalize the well-known steerable/scalable ("deformable") filter bank structure by imposing X-Y separability on the basis filters. The resulting systems, designed by an iterative projections technique, achieve substantial reduction of the computational cost. To reduce the memory requirement, we adopt a multirate implementation. Due to the inner sampling rate alteration, the resulting structure is not shift invariant. We introduce a design criterion for multirate deformable structures that jointly controls the approximation error and the shift variance.

Additional Information

© Copyright 1993 IEEE. Reprinted with permission. Manuscript received February 15, 1997; revised November 30, 1997. This work was supported by NSF Grant IRI 9306155 on Geometry Driven Diffusions, NSF Research Initiation Grant IRI 9211651, ONR Grant N00014-93-1-0990, an NSF National Young Investigator Award to P. Perona, the Center for Neuromorphic Systems Engineering as a part of the National Science Foundation Engineering Research Center Program, and the California Trade and Commerce Agency, Office of Strategic Technology. The associate editor coordinating the review of this paper and approving it for publication was Dr. Henrique Malvar. The Matlab software to design the filter banks described in this paper may be found at http://www.vision.caltech.edu/manduchi/def.tar.Z.

Files

MANieeetsp98.pdf
Files (239.4 kB)
Name Size Download all
md5:5a0bbeede5d28dc2008753c236f12836
239.4 kB Preview Download

Additional details

Created:
August 22, 2023
Modified:
October 13, 2023