Zero-Aliasing Correlation Filters for Object Recognition
- 26 November 2014
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 37 (8) , 1702-1715
Abstract
Correlation filters (CFs) are a class of classifiers that are attractive for object localization and tracking applications. Traditionally, CFs have been designed in the frequency domain using the discrete Fourier transform (DFT), where correlation is efficiently implemented. However, existing CF designs do not account for the fact that the multiplication of two DFTs in the frequency domain corresponds to a circular correlation in the time/spatial domain. Because this was previously unaccounted for, prior CF designs are not truly optimal, as their optimization criteria do not accurately quantify their optimization intention. In this paper, we introduce new zero-aliasing constraints that completely eliminate this aliasing problem by ensuring that the optimization criterion for a given CF corresponds to a linear correlation rather than a circular correlation. This means that previous CF designs can be significantly improved by this reformulation. We demonstrate the benefits of this new CF design approach with several important CFs. We present experimental results on diverse data sets and present solutions to the computational challenges associated with computing these CFs. Code for the CFs described in this paper and their respective zero-aliasing versions is available at http://vishnu.boddeti.net/projects/correlation-filters.htmlKeywords
All Related Versions
Funding Information
- US Air Force Research Laboratory
- DoD Supercomputing Resource Center
- Air Force Office of Scientific Research
- National Defense Science & Engineering Graduate Fellowship
This publication has 37 references indexed in Scilit:
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse ProblemsSIAM Journal on Imaging Sciences, 2009
- Correlation filter: an accurate approach to detect and locate low contrast character strings in complex table environmentIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- The impact of the MIT-BIH Arrhythmia DatabaseIEEE Engineering in Medicine and Biology Magazine, 2001
- The FERET evaluation methodology for face-recognition algorithmsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Optimal trade-off synthetic discriminant function filters for arbitrary devicesOptics Letters, 1994
- Minimum squared error synthetic discriminant functionsOptical Engineering, 1992
- Gaussian–minimum average correlation energy filtersApplied Optics, 1991
- Filter design for optical pattern recognition: multicriteria optimization approachOptics Letters, 1990
- Unified framework for the synthesis of synthetic discriminant functions with reduced noise variance and sharp correlation structureOptical Engineering, 1990
- Minimum average correlation energy filtersApplied Optics, 1987