Image processing method for object recognition and dynamic...

Image analysis – Image transformation or preprocessing – Fourier transform

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C708S405000, C702S077000, C370S210000, C345S427000

Reexamination Certificate

active

07664339

ABSTRACT:
Provided is a method for digital image representation based upon Discrete Projective Fourier Transform (DPFT) constructed in the noncompact (DNPFT) and compact (DCPFT) realizations of geometric Fourier analysis on SL(2,C) groups. Novel characteristics are that the model is well adapted to perspective image transformations and well adapted to the retinotopic (conformal) mapping of the biological visual system. To compute the DPFT of a digital image by Fast Fourier transform (FFT), an image is re-sampled with a non-uniform log-polar sampling geometry. A “deconformalization” procedure corrects the “conformal lens optics” of the conformal camera to render image perspective transformations. DNPFT computes the convolution in the noncompact realization defined over 2-dimensional rotations in the image plane and dilations while the DCPFT computes the convolution in the compact realization (which is defines over all 3-dimensional rotations) and therefore provides basis for developing projectively invariant under all rotations object matching.

REFERENCES:
patent: 5579444 (1996-11-01), Dalziel et al.
patent: 5911035 (1999-06-01), Tsao
patent: 6282300 (2001-08-01), Bloom et al.
patent: 6430431 (2002-08-01), De Yoe
patent: 6704869 (2004-03-01), Rhoads et al.
patent: 7054850 (2006-05-01), Matsugu
patent: 2003/0039377 (2003-02-01), Rhoads et al.
patent: 2004/0218815 (2004-11-01), Iizuka
patent: 2007/0019884 (2007-01-01), Jojic et al.
Peters, It et al.: “Centering Peripheral Features in an Indoor Environment Using a Binocaler Log-Polar 4DOF Camera Head:” Robotics and Autornous Systems vol. 18, pp, 271-281: 1996.
Bernardino et al.; “A Binocular Stereo Algorithm for Log-polar Foveated Systems;” 2nd Workshop on Biological Motivated Computer Vision; Tuebingen, Germany; Nov. 2002,.
Traver et al.; “Designing the Lattice or Log-Polar Images;” DGCI 2003 LNCS 2886; pp. 164-173, 2003.
Turski; “Harmonic Anatysis on SL(2,C) and Projectively Adapted Pattern Representation;” Journie of Fourier Analysis and Applications: vol, 4, pp. 67-91; 1998.
Turski; “Geometric Fourier Analysis tor Computation Vision,” Journal of Fourier Analysis and Applications: ISSN 1069-5869; © 2004.
Bernardino at al.; “Foveated Active Tracking with Redundant 2D Motion Parameters;” Robotics and Autonomous Systems 39, pp. 205-221; 2002.
Turski; “Projective Fourier Anaiysis for Patterns;” Pattern Recognition 33 pp. 2033-2043, 2000.
Turski; “Geometric Fourier Analysis of the Conformal Camera for Active Vision:” SIAM Review, vol. 46, pp. 230-265; 2004.
Pardo et al.; “Design of a Foveated Log-Polar Image Sensor in Standard CMOS Technology;” Design of Itegratad Circuits end Systems, pp. 1-6. Spain, 1996,.
Ho et al.: “Sensor Geometry and ampling Methods for Space-Variant Image Processing;” Pattern Analysis & Applications; pp. 369-384, 2002.
Ferrari et al.: “Space Varieant Imaging;” Sensor Review. vol. 15. n. 2, pp. 17-20, 1995.
Turski; “Projective Fourier Analysis in Computer Vision: Theory and Computer Simulations;” SPIE, Vol. 3168, pp. 124-135, 1997.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Image processing method for object recognition and dynamic... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Image processing method for object recognition and dynamic..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Image processing method for object recognition and dynamic... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-4203886

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.