Method and apparatus for implementation of neural networks for f

Image analysis – Learning systems – Neural networks

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

382118, 382280, 359561, 359559, 364822, G06K 962, G06K 936, G02B 2746, G06E 300

Patent

active

056994494

ABSTRACT:
A method and apparatus for implementation of neural networks for face recognition is presented. A nonlinear filter or a nonlinear joint transform correlator (JTC) employs a supervised perceptron learning algorithm in a two-layer neural network for real-time face recognition. The nonlinear filter is generally implemented electronically, while the nonlinear joint transform correlator is generally implemented optically. The system implements perception learning to train with a sequence of facial images and then classifies a distorted input image in real-time. Computer simulations and optical experimental results show that the system can identify the input with the probability of error less than 3%. By using time multiplexing of the input image under investigation, that is, using more than one input image, the probability of error for classification can be reduced to zero.

REFERENCES:
patent: 4832447 (1989-05-01), Javidi
patent: 4959532 (1990-09-01), Owechko
patent: 5040140 (1991-08-01), Horner
patent: 5111515 (1992-05-01), Javidi
patent: 5119443 (1992-06-01), Javidi et al.
patent: 5367579 (1994-11-01), Javidi et al.
patent: 5485312 (1996-01-01), Horner et al.
"A Technique for optically convolving two functions", by C.S. Weaver and J.W. Goodman, Appl. Opt. vol. 5, pp. 1248-1249, 1966.
"Nonlinear Joint Transform Correlation: An Optimal Solution For Adaptive Image Discrimination and Input Noise Robustness", by P. Refregier, V. Laude and B. Javidi, Opt. Lett. vol. 19, No. 6, pp. 405-407, 1994.
"Experiments on nonlinear joint transform correlator using an optically addresses spatial light modulator in the Fourier plane", by B. Javidi, Q. Tang, D.A. Gregory and T.D. Hudson, Appl. Opt., vol. 30, No. 14, pp. 1772-1776, 1991.
"1-f Binary Joint Correlator", by K.ll. Fielding and J.L. Horner, Opt. Eng. vol. 29, pp. 1081 1087, 1990.
"Sensitivity of the nonlinear joint transform correlator: experimental investigations", by Q. Tang and B. Javidi, Appl. Opt. vol. 31, No. 20, pp. 4016-4024, Jul. 1992.
"Design elements of binary joint transform correlation and selected optimization techniques", by W.B. Hahn and D.L. Flannery, Opt. Eng. vol. 31, pp. 896-905, 1992.
"Single spatial light modulator joint transform correlator", by Bahram Javidi and Joseph L. Horner, Appl. Opt. vol. 28, No. 5, pp. 1027-1029, Mar. 1989.
"Nonlinear joint power spectrum based optical correlation", by Bahram Javidi, Appl. Opt., vol. 28, No. 12, pp. 2358-2367, Jun. 1989.
"Optical fingerprint identification by binary joint transform correlation", by Kenneth H. Fielding, Joseph L. Horner and Charles Makekau, Optical Eng., Dec. 1991, vol. 30, No. 12.

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

Method and apparatus for implementation of neural networks for f does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method and apparatus for implementation of neural networks for f, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for implementation of neural networks for f will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-214824

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