Accession Number:

ADA318849

Title:

Template Matching: Matched Spatial Filters and Beyond.

Descriptive Note:

Memorandum rept.,

Corporate Author:

MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s):

Report Date:

1995-10-01

Pagination or Media Count:

15.0

Abstract:

Template matching by means of cross-correlation is common practice in pattern recognition. However, its sensitivity to deformations of the pattern and the broad and unsharp peaks it produces are significant drawbacks. This paper reviews some results on how these shortcomings can be removed. Several techniques Matched Spatial Filters, Synthetic Discriminant Functions, Principal Components Projections and Reconstruction Residuals are reviewed and compared on a common task locating eyes in a database of faces. New variants are also proposed and compared least squares Discriminant Functions and the combined use of projections on eigenfunctions and the corresponding reconstruction residuals. Finally, approximation networks are introduced in an attempt to improve filter design by the introduction of nonlinearity.

Subject Categories:

  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE