Color component transformations for optical pattern recognition

Several elementwise component transformations performed over primary color image components (RGB) before optical multichannel correlations are proposed to improve real-time multispectral pattern recognition. The first transformation is deduced from the theory of the optimal filter for object location and recognition extended to multispectral images. Several modifications of this transformation are studied. We investigate these transformations in terms of noise robustness and discrimination capability. Computer simulation with noisy input images for various kinds of correlation filter are presented to illustrate improvement of color pattern recognition by using the proposed transformations. Experimental results are also presented.

[1]  Toshio Honda,et al.  Color image correlation for spatial/spectral recognition and increased selectivity , 1988 .

[2]  S Maze,et al.  Noise robustness of optical correlation for amplitude or phase modulation of the input image. , 1992, Optics letters.

[3]  J Campos,et al.  Color pattern recognition with circular component whitening. , 1996, Optics letters.

[4]  J García,et al.  Color encoding for polychromatic single-channel optical pattern recognition. , 1995, Applied optics.

[5]  Juan Campos,et al.  New arrangement for limited intensity invariance pattern recognition with high diffraction efficiency , 1995 .

[6]  Francis T. S. Yu.  White-light optical signal processing , 1985 .

[7]  Francis T. S. Yu.  Color Image Recognition By Spectral-Spatial Matched Filtering , 1984 .

[8]  Toshio Honda,et al.  Color image correlation , 1987 .

[9]  Leonid P. Iaroslavskii.  Is the phase-only filter and its modifications optimal in terms of the discrimination capability in pattern recognition? , 1992 .

[10]  Dennis H. Goldstein,et al.  Phase-encoding input images for optical pattern recognition , 1994 .

[11]  S K Case,et al.  Pattern recognition with wavelength-multiplexed filters. , 1979, Applied optics.

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

[13]  Yoichi Miyake,et al.  Color character recognition method based on human perception , 1993 .

[14]  Francis T. S. Yu,et al.  Real-time joint spectral-spatial matched filtering , 1984 .

[15]  Carlos Ferreira,et al.  Experimental results in color pattern recognition by multichannel matched filtering , 1992 .

[16]  J Campos,et al.  Different strategies in optical recognition of polychromatic images. , 1992, Applied optics.

[17]  J. Horner,et al.  Phase-only matched filtering. , 1984, Applied optics.

[18]  M J Yzuel,et al.  Optical pattern recognition based on color vision models. , 1995, Optics letters.

[19]  G. W. Snedecor.  Statistical Methods , 1964 .

[20]  Carlos Ferreira,et al.  Matched filter and phase only filter performance in colour image recognition , 1989 .