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) : Brunelli, Roberto ; Poggio, Tomaso
PDF Url : ADA318849
Report Date : OCT 1995
Pagination or Media Count : 15
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.
Descriptors : *IMAGE PROCESSING, *PATTERN RECOGNITION, DATA BASES, OPTIMIZATION, SIGNAL TO NOISE RATIO, EIGENVECTORS, TARGET DISCRIMINATION, MATHEMATICAL FILTERS, NONLINEAR SYSTEMS, LEAST SQUARES METHOD, COMPUTER VISION, MATCHED FILTERS, SPATIAL FILTERING, MATCHING, CROSS CORRELATION.
Subject Categories : Cybernetics
Distribution Statement : APPROVED FOR PUBLIC RELEASE