Image analysis – Pattern recognition – Classification
Reexamination Certificate
1998-11-30
2001-11-13
Boudreau, Leo (Department: 2621)
Image analysis
Pattern recognition
Classification
C382S115000, C382S159000, C382S160000, C382S181000, C382S224000, C382S227000, C706S020000
Reexamination Certificate
active
06317517
ABSTRACT:
FIELD OF THE INVENTION
The present invention generally relates to pattern recognition and, more specifically, to statistical pattern recognition capable of reducing the dimensionality of real-life data. This invention was made with Government support under Contract No. W-7405-ENG-36 awarded by the U.S. Department of Energy. The Government has certain rights in the invention.
REFERENCE TO MICROFICHE APPENDIX
The Appendix to this application contains a computer listing in the C
++
language that is used in the practice of the invention. Included are eight (8) microfiche, containing seventy-two (72) frames.
BACKGROUND OF THE INVENTION
The advent of improved pattern recognition procedures in recent years has opened a plethora of applications for this technique. Among these applications are medical diagnoses, biological categorization, financial market prediction, credit card fraud detection, retail transactions, insurance applications, and personal identification.
Statistical pattern recognition is theoretically well-founded when based on Bayes' decision rule. In practical applications, however, Bayes' decision rule is difficult to implement because real-world data is complex and multi-dimensional. This causes the amount of training data for statistical pattern recognition to rise exponentially with each additional data dimension.
It is well known that the dimension of real-life data can be reduced because these types of data often are highly redundant, and many of its components are irrelevant. The present invention addresses these issues and provides a statistical pattern recognition method that overcomes these problems through a combination of processes.
It is therefore an object of the present invention to provide a method of statistical pattern recognition that can identify relevant feature components.
It is another object of the present invention to provide a statistical pattern recognition method that capable of reducing the computer time required to run pattern recognition processes.
Additional objects, advantages and novel features of the invention will be set forth in part in the description which follows, and in part will become apparent to those skilled in the art upon examination of the following or may be learned by practice of the invention. The objects and advantages of the invention may be realized and attained by means of the instrumentalities and combinations particularly pointed out in the appended claims.
SUMMARY OF THE INVENTION
To achieve the foregoing and other objects, a method of statistical pattern recognition in a set of data having predetermined dimensions comprises the steps of performing feature selection on the set of data to determine a selected feature; performing pattern recognition using the set of data with the selected feature to determine a recognized pattern; and outputting the recognized pattern.
REFERENCES:
patent: 5255342 (1993-10-01), Nitta
patent: 5287275 (1994-02-01), Kimura
patent: 5754681 (1998-05-01), Watanabe et al.
patent: 5828776 (1998-10-01), Lee et al.
patent: 5841669 (1998-11-01), Purvis et al.
patent: 5946415 (1999-08-01), Su et al.
patent: 5982912 (1999-11-01), Fukui et al.
patent: 5982929 (1999-11-01), Ilan et al.
patent: 6038337 (2000-03-01), Lawrence et al.
patent: 6101275 (2000-08-01), Coppersmith et al.
Comon, et al. “ultimate performace of QEM classifiers”, IEEE, pp. 1535-1537, 1996.*
Coifman, et al. “selection of best bases for classification and regression”, IEEE p. 51, 1994.
Boudreau Leo
Mariam Daniel G.
Regents of the University of California
Wyrick Milton D.
LandOfFree
Statistical pattern recognition does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Statistical pattern recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Statistical pattern recognition will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2592561