Signal pattern recognition apparatus comprising parameter traini

Image analysis – Learning systems – Trainable classifiers or pattern recognizers

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

382190, 382224, 395 24, 395 24, G06K 962

Patent

active

057546819

ABSTRACT:
In a signal pattern recognition apparatus, a plurality of feature transformation sections respectively transform an inputted signal pattern into vectors in a plurality of feature spaces corresponding respectively to predetermined classes using a predetermined transformation parameter corresponding to each of the classes so as to emphasize a feature of each of the classes, and a plurality of discriminant function sections respectively calculates a value of a discriminant function using a predetermined discriminant function representing a similarity measure of each of the classes for the transformed vectors in the plurality of feature spaces. Then, a selection section executes a signal pattern recognition process by selecting a class to which the inputted signal pattern belongs based on the calculated values of a plurality of discriminant functions corresponding respectively to the classes, and a training control section trains and sets a plurality of transformation parameters of the feature transformation process and a plurality of discriminant functions so that an error probability of the signal pattern recognition is minimized based on a predetermined training signal pattern.

REFERENCES:
patent: 4783802 (1988-11-01), Takebayashi et al.
patent: 5239594 (1993-08-01), Yoda
patent: 5249067 (1993-09-01), Hirosawa
patent: 5440662 (1995-08-01), Sukka
patent: 5479570 (1995-12-01), Imagawa et al.
patent: 5602938 (1997-02-01), Akiyama et al.
"Subspace Methods of Pattern Recognition", E. Oja. Research Studies Press, 1983, pp. 73-125.
"Fundamentals of Speech Recognition", L. Rabiner et al, PTR Prentice-Hall, Inc. 1993 pp. 69-123.
"New Discriminative Training Algorithms Based on the Generalized Probabilistic Descent Method", Katagiri et al, in proc. 1991 IEEE Workshop on Neural Networks for Signal Processing, pp. 299-308.
"Hidden Markov Models for Speech Recognition", X. D. Huang et al, Edinburgh University Press, 1990, pp. 166-185.
"Discriminative Learning for Minimum Error Classification", by B. H. Juang et al, IEEE Transactions on Signal Processing, vol. 40, No. 12, pp. 3043-3054, Dec. 1992.
"Pattern Classification and Scene Analysis", by R. O. Duda et al, A Wiley-Interscience Publication, pp. 10-39, and 114-121, 130-159, 1973.
"Matrix Computations", by G. H. Golub et al, The Johns Hopkins University Press, 1989, pp. 444-459.
"Segmental GPD Training of HMM Based Speech Controller", W. Chou et al, Proceedings of ICASSP 1992, IEEE, vol. 1, pp. 473-476.
"Minimum Error Classification Training of HMMs--Implementation Details and Experimental Results", Rainton, et al., Japanese Acoustic Society, vol. 13, No. 6, pp. 379-387, Nov. 1992.
"Feature Extraction Based on Minimum Classification Error/Generalized Probabilistic Descent Method", Brem et al, Proceedings of ICASSP 1993, IEEE, vol. 2, pp. 275-278, Apr. 1993.
"Pattern Recognition Engineering" by Jun-ichi Toriwaki, edited by the Institute of Television Engineers of Japan, Corona Publishing Co., Ltd., Mar. 15, 1993, pp. 24-27, 30-33, 95-99, 104-107, 224.
"Information Statistics" by Yoshiyuki Sakamoto et al, Lecture of information science A.5.5, Kyoritsu Shuppan, Jan 15, 1983, pp. 27-44.

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

Signal pattern recognition apparatus comprising parameter traini does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Signal pattern recognition apparatus comprising parameter traini, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Signal pattern recognition apparatus comprising parameter traini will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-1861507

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