Zero-Aliasing Correlation Filters for Object Recognition

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.html

[1]  Bruce A. Draper,et al.  Visual object tracking using adaptive correlation filters , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Simon Lucey,et al.  Are Correlation Filters Useful for Human Action Recognition? , 2010, 2010 20th International Conference on Pattern Recognition.

[3]  Marios Savvides,et al.  Correlation Pattern Recognition for Face Recognition , 2006, Proceedings of the IEEE.

[4]  Rui Caseiro,et al.  Beyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant Decomposition , 2013, 2013 IEEE International Conference on Computer Vision.

[5]  Yi Li,et al.  Correlation Filter: An Accurate Approach to Detect and Locate Low Contrast Character Strings in Complex Table Environment , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  B. V. K. Vijaya Kumar,et al.  A comparative evaluation of iris and ocular recognition methods on challenging ocular images , 2011, 2011 International Joint Conference on Biometrics (IJCB).

[7]  P. Réfrégier.  Filter design for optical pattern recognition: multicriteria optimization approach. , 1990, Optics letters.

[8]  A Mahalanobis,et al.  Optimal trade-off synthetic discriminant function filters for arbitrary devices. , 1994, Optics letters.

[9]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[10]  B. V. K. Vijaya Kumar,et al.  Maximum Margin Vector Correlation Filter , 2014, ArXiv.

[11]  B. V. K. Vijaya Kumar,et al.  Correlation Pattern Recognition , 2002 .

[12]  G.B. Moody,et al.  The impact of the MIT-BIH Arrhythmia Database , 2001, IEEE Engineering in Medicine and Biology Magazine.

[13]  Andres F. Rodriguez-Perez.  Maximum Margin Correlation Filters , 2012 .

[14]  Frédéric Jurie,et al.  Groups of Adjacent Contour Segments for Object Detection , 2008, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  B. V. K. Vijaya Kumar,et al.  A Framework for Binding and Retrieving Class-Specific Information to and from Image Patterns Using Correlation Filters , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Takeo Kanade,et al.  Correlation Filters for Object Alignment , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Andy Harter,et al.  Parameterisation of a stochastic model for human face identification , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[18]  Rui Caseiro,et al.  Exploiting the Circulant Structure of Tracking-by-Detection with Kernels , 2012, ECCV.

[19]  D. Casasent,et al.  Minimum average correlation energy filters. , 1987, Applied optics.

[20]  Iqbal Gondal,et al.  Action Recognition Using Spatio-Temporal Distance Classifier Correlation Filter , 2011, 2011 International Conference on Digital Image Computing: Techniques and Applications.

[21]  Cordelia Schmid,et al.  Event Retrieval in Large Video Collections with Circulant Temporal Encoding , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Yaser Sheikh,et al.  3D Pose-by-Detection of Vehicles via Discriminatively Reduced Ensembles of Correlation Filters , 2014, BMVC.

[23]  Abhijit Mahalanobis,et al.  A Bayesian approach to activity detection in video using multi-frame correlation filters , 2011, Defense + Commercial Sensing.

[24]  Abhijit Mahalanobis,et al.  Unified framework for the synthesis of synthetic discriminant functions with reduced noise variance and sharp correlation structure , 1990 .

[25]  B. V. K. Vijaya Kumar,et al.  Dealing with circular correlation effects , 2013, Defense, Security, and Sensing.

[26]  Bruce A. Draper,et al.  Simple real-time human detection using a single correlation filter , 2009, 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance.

[27]  Hyeonjoon Moon,et al.  The FERET evaluation methodology for face-recognition algorithms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[28]  B. V. K. Vijaya Kumar,et al.  Maximum Margin Correlation Filter: A New Approach for Localization and Classification , 2013, IEEE Transactions on Image Processing.

[29]  D. Casasent,et al.  Gaussian-minimum average correlation energy filters. , 1991, Applied optics.

[30]  Yann LeCun,et al.  Fast Training of Convolutional Networks through FFTs , 2013, ICLR.

[31]  B. V. K. Vijaya Kumar,et al.  Zero-aliasing correlation filters , 2013, 2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA).

[32]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[33]  Anders P. Eriksson,et al.  Fast Convolutional Sparse Coding , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  R. Kerekes,et al.  Enhanced Video-Based Target Detection using Multi-Frame Correlation Filtering , 2009, IEEE Transactions on Aerospace and Electronic Systems.

[35]  Hiroshi Nakajima,et al.  An Effective Approach for Iris Recognition Using Phase-Based Image Matching , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  B. V. K. Vijaya Kumar,et al.  A Bayesian Approach to Deformed Pattern Matching of Iris Images , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Marc Teboulle,et al.  A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems , 2009, SIAM J. Imaging Sci..

[38]  Patrick J. Flynn,et al.  Overview of the face recognition grand challenge , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[39]  Stephen A. Dyer,et al.  Digital signal processing , 2018, 8th International Multitopic Conference, 2004. Proceedings of INMIC 2004..

[40]  J. Beveridge,et al.  Average of Synthetic Exact Filters , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[41]  Mubarak Shah,et al.  Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[42]  Koichi Ito,et al.  Phase-based image matching and its application to biometric recognition , 2013, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.

[43]  T. Higuchi,et al.  A Fingerprint Matching Algorithm Using Phase-Only Correlation(Digital Signal Processing for Pattern Recognition)( Applications and Implementations of Digital Signal Processing) , 2004 .

[44]  B. V. Kumar,et al.  Minimum squared error synthetic discriminant functions , 1992 .

[45]  Simon Lucey,et al.  Multi-channel Correlation Filters , 2013, 2013 IEEE International Conference on Computer Vision.