Method of Synthesized Phase Objects in the Optical Pattern Recognition Problem

To solve the pattern recognition problem, a method of synthesized phase objects (SPOmethod) is suggested. The essence of the suggested method is that synthesized phase objects are used instead of real amplitude objects. The former is object-dependent phase distributions calculated using the iterative Fourier transform algorithm. The method is experimentally studied with an optical-digital Vanderlugt and joint Fourier transform 4F-correlators. The development of the SPO-method for the rotation invariant pattern recognition is considered as well. We present the comparative analysis of recognition results with the use of the conventional and proposed methods, estimate the sensitivity of the latter to distortions of the structure of objects, and determine the applicability limits. It is demonstrated that the SPO-method allows one: (a) to simplify the procedure of choice of recognition signs (criteria); (b) to obtain one-type δ-like recognition signals irrespective of the type of objects; and (c) to improve the signal-to-noise ratio for correlation signals by 20–30 dB on the average. To introduce recognition objects in a correlator, we use SLM LC-R 2500 and SLM HEO 1080 Pluto devices.

[1]  Michel Defrise,et al.  Symmetric Phase-Only Matched Filtering of Fourier-Mellin Transforms for Image Registration and Recognition , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

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

[3]  J. Goodman,et al.  A technique for optically convolving two functions. , 1966, Applied optics.

[4]  D. Casasent,et al.  SCALE INVARIANT OPTICAL CORRELATION USING MELLIN TRANSFORMS , 1976 .

[5]  William Turin,et al.  On‐line handwritten signature verification using stroke direction coding , 1996 .

[6]  A V Lugt.  Practical considerations for the use of spatial carrier-frequency filters. , 1966, Applied optics.

[7]  H H Arsenault,et al.  Rotation invariant phase-only and binary phase-only correlation. , 1989, Applied optics.

[8]  H. Arsenault,et al.  Experiments on pattern recognition using invariant Fourier-Mellin descriptors. , 1986, Journal of the Optical Society of America. A, Optics and image science.

[9]  P. McWhorter,et al.  Scale invariant amplitude modulated phase-only filtering , 2000 .

[10]  T. N. Smirnova,et al.  Synthesized phase objects used instead of real ones for optical-digital recognition systems: experiment , 2006, International Conference on Correlation Optics.

[11]  Yung-Chang Chen,et al.  New approach for scale, rotation, and translation invariant pattern recognition , 1997 .

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

[13]  Ezra Silvera,et al.  Adaptive pattern recognition with rotation, scale, and shift invariance. , 1995, Applied optics.

[14]  Alexander P. Ostroukh,et al.  Method of synthesized phase objects for pattern recognition with rotation invariance , 2015, International Conference on Correlation Optics.

[15]  R. Gerchberg.  A practical algorithm for the determination of phase from image and diffraction plane pictures , 1972 .

[16]  J W Goodman,et al.  Optimal binary phase-only matched filters. , 1988, Applied optics.

[17]  Danny Roberge,et al.  Optimal trade-off filter for the correlation of fingerprints , 1999 .

[18]  J Shamir,et al.  Application of the projection-onto-constraint-sets algorithm for optical pattern recognition. , 1991, Optics letters.

[19]  J Shamir,et al.  Circular harmonic phase filters for efficient rotationinvariant pattern recognition. , 1988, Applied optics.

[20]  J Shamir,et al.  Entropy optimized filter for pattern recognition. , 1990, Applied optics.

[21]  David Casasent,et al.  GENERAL METHODOLOGY FOR SIMULTANEOUS REPRESENTATION AND DISCRIMINATION OF MULTIPLE OBJECT CLASSES , 1998 .

[22]  Ph. Réfrégier.  Application of the stabilizing functional approach to pattern-recognition filters , 1994 .

[23]  Pavel V. Yezhov,et al.  Synthesized phase objects instead of real ones for optical-digital recognition systems , 2004, International Conference on Correlation Optics.

[24]  Pierre-André Farine,et al.  Low complexity RST invariant image recognition using Fourier Mellin Transform , 2011, 2011 19th European Signal Processing Conference.

[25]  Jan Flusser,et al.  Pattern recognition by affine moment invariants , 1993, Pattern Recognit..

[26]  E Ochoa,et al.  Experimental use of iteratively designed rotation invariant correlation filters. , 1987, Applied optics.

[27]  Pavel V. Yezhov,et al.  Method of synthesized phase objects for pattern recognition: matched filtering. , 2012, Optics express.

[28]  H H Arsenault,et al.  Optical binary phase-only filters for circular harmonic correlations. , 1991, Applied optics.

[29]  P. Karivaratha Rajan,et al.  Design of synthetic estimation filters using correlation energy minimization , 1994, Defense, Security, and Sensing.

[30]  N. C. Gallagher,et al.  Method for Computing Kinoforms that Reduces Image Reconstruction Error. , 1973, Applied optics.