Nonlinear synthetic discriminant function filters for illumination-invariant pattern recognition

Novel nonlinear adaptive composite filters for illumination-invariant pattern recognition are presented. Pattern recognition is carried out with space-variant nonlinear correlation. The information about objects to be recognized, false objects, and a background to be rejected is utilized in an iterative training procedure to design a nonlinear adaptive correlation filter with a given discrimination capability. The designed filter during recognition process adapts its parameters to local statistics of the input image. Computer simulation results obtained with the proposed filters in nonuniformly illuminated test scenes are discussed and compared with those of linear composite correlation filters with respect to discrimination capability, robustness to input additive and impulsive noise, and tolerance to small geometric image distortions.

[1]  Philippe Réfrégier,et al.  Bayesian theory for target location in noise with unknown spectral density , 1999 .

[2]  Vitaly Kober,et al.  Adaptive synthetic discriminant function filters for pattern recognition , 2006 .

[3]  Petros Maragos.  Morphological correlation and mean absolute error criteria , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[4]  A. Taylor,et al.  Modeling of femtosecond electromagnetic pulses from large-aperture photoconductors. , 1993, Optics letters.

[5]  B Javidi,et al.  Minimum-mean-square-error filters for detecting a noisy target in background noise. , 1996, Applied optics.

[6]  Vitaly Kober,et al.  Pattern recognition with an adaptive joint transform correlator. , 2006, Applied optics.

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

[8]  D Casasent,et al.  Unified synthetic discriminant function computational formulation. , 1984, Applied optics.

[9]  B Noharet,et al.  Distortion-invariant filter for nonoverlapping noise. , 1998, Applied optics.

[10]  Liviu Singher,et al.  Adaptive multiple filtering , 2002 .

[11]  Vitaly Kober,et al.  Accuracy of location measurement of a noisy target in a nonoverlapping background , 1996 .

[12]  Rama Chellappa,et al.  Estimation of Illuminant Direction, Albedo, and Shape from Shading , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  P. Maragos.  3.3 – Morphological Filtering for Image Enhancement and Feature Detection , 2004 .

[14]  B. Kumar,et al.  Performance measures for correlation filters. , 1990, Applied optics.

[15]  Vitaly Kober,et al.  Adaptive phase-input joint transform correlator. , 2007, Applied optics.

[16]  J. Fitch,et al.  Median filtering by threshold decomposition , 1984 .

[17]  D Casasent,et al.  Multivariant technique for multiclass pattern recognition. , 1980, Applied optics.

[18]  Berthold K. P. Horn.  Height and gradient from shading , 1989, International Journal of Computer Vision.

[19]  Vitaly Kober,et al.  Nonlinear filters with spatially-connected neighborhoods , 2001 .

[20]  Carlos Ferreira,et al.  Optical implementation of the weighted sliced orthogonal nonlinear generalized correlation for nonuniform illumination conditions. , 2002, Applied optics.

[21]  Ioannis Pitas,et al.  Nonlinear Digital Filters - Principles and Applications , 1990, The Springer International Series in Engineering and Computer Science.

[22]  J Campos,et al.  Phase-only filter with improved discrimination. , 1994, Optics letters.

[23]  Joseph L. Horner,et al.  Applying the phase-only filter concept to the synthetic discriminant function correlation filter. , 1985 .

[24]  Edward J. Coyle,et al.  Rank order operators and the mean absolute error criterion , 1988, IEEE Trans. Acoust. Speech Signal Process..

[25]  Bahram Javidi,et al.  Design of filters to detect a noisy target in nonoverlapping background noise , 1994 .

[26]  Bahram Javidi,et al.  Distortion-tolerant minimum-mean-squared-error filter for detecting noisy targets in environmental degradation , 2000 .

[27]  Soo-Joong Kim,et al.  Distortion-invariant pattern recognition based on a synthetic hit-miss transform , 2004 .

[28]  A. B. Vander Lugt,et al.  Signal detection by complex spatial filtering , 1964, IEEE Trans. Inf. Theory.

[29]  Jeffrey C. Lagarias,et al.  Convergence Properties of the Nelder-Mead Simplex Method in Low Dimensions , 1998, SIAM J. Optim..

[30]  Qu Wang,et al.  Morphological fringe-adjusted joint transform correlation , 2006 .

[31]  Bahram Javidi,et al.  Minimum mean-square-error filter for pattern recognition with spatially disjoint signal and scene noise , 1993 .

[32]  B V Kumar,et al.  Tutorial survey of composite filter designs for optical correlators. , 1992, Applied optics.

[33]  Vitaly Kober,et al.  Design of correlation filters for recognition of linearly distorted objects in linearly degraded scenes. , 2007, Journal of the Optical Society of America. A, Optics, image science, and vision.

[34]  L. P. Yaroslavsky,et al.  III The Theory of Optimal Methods for Localization of Objects in Pictures , 1993 .

[35]  B Javidi,et al.  Optimum receivers for pattern recognition in the presence of Gaussian noise with unknown statistics. , 2001, Journal of the Optical Society of America. A, Optics, image science, and vision.