Automated synthesis of distortion-invariant filters: AutoMinace

This paper presents our automated filter-synthesis algorithm for the minimum noise and correlation energy (MINACE) distortion-invariant filter (DIF). We discuss use of this autoMinace filter in face recognition and automatic target recognition (ATR), in which we consider both true-class object classification and rejection of non-database objects (impostors in face recognition and confusers in ATR). We use at least one Minace filter per object class to be recognized; a separate Minace filter or a set of Minace filters is synthesized for each object class. The Minace parameter c trades-off distortion-tolerance (recognition) versus discrimination (impostor/confuser/clutter rejection) performance. Our automated Minace filter-synthesis algorithm (autoMinace) automatically selects the Minace filter parameter c and selects the training set images to be included in the filter, so that we achieve both good recognition and good impostor/confuser and clutter rejection performance; this is achieved using a training and validation set. No impostor/confuser, clutter or test set data is present in the training or validation sets. Use of the peak-to-correlation energy (PCE) ratio is found to perform better than the correlation peak height metric. The use of circular versus linear correlations is addressed; circular correlations require less storage and fewer online computations and are thus preferable. Representative test results for three different databases - visual face, IR ATR, and SAR ATR - are presented. We also discuss an efficient implementation of Minace filters for detection applications, where the filter template is much smaller than the input target scene.

[1]  B. V. K. Vijaya Kumar,et al.  Performance of composite correlation filters in fingerprint verification , 2004 .

[2]  B. V. K. Vijaya Kumar,et al.  Improving the false alarm capabilities of the maximum average correlation height correlation filter , 2000 .

[3]  David Casasent,et al.  Synthetic aperture radar detection, recognition, and clutter rejection with new minimum noise and correlation energy filters , 1997 .

[4]  Terence Sim,et al.  The CMU Pose, Illumination, and Expression (PIE) database , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[5]  D. Casasent,et al.  Minimum noise and correlation energy optical correlation filter. , 1992, Applied optics.

[6]  B. V. K. Vijaya Kumar,et al.  Efficient design of advanced correlation filters for robust distortion-tolerant face recognition , 2003, Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003..

[7]  Michael Lee Bryant,et al.  Standard SAR ATR evaluation experiments using the MSTAR public release data set , 1998, Defense, Security, and Sensing.

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

[9]  David Casasent,et al.  Face recognition with illumination and pose variations using MINACE filters , 2005, SPIE Optics East.

[10]  David Casasent,et al.  Confuser rejection performance of EMACH filters for MSTAR ATR , 2006, SPIE Defense + Commercial Sensing.

[11]  David Casasent,et al.  MSTAR object classification and confuser and clutter rejection using Minace filters , 2006, SPIE Defense + Commercial Sensing.

[12]  David Casasent,et al.  Illumination invariant face recognition and impostor rejection using different MINACE filter algorithms , 2005, SPIE Defense + Commercial Sensing.

[13]  David Casasent,et al.  Automated distortion-invariant filter synthesis and training set selection (auto-Minace) , 2006, SPIE Defense + Commercial Sensing.