 |
|
|
|
|
|
 Title: |
US6118890:
System and method for broad classification of biometric patterns
[ Derwent Title ]
|
| Country: |
US United States of America
|
| |
| Inventor: |
Senior, Andrew William; White Plains, NY
|
| Assignee: |
International Business Machines Corporation, Armonk, NY
other patents from INTERNATIONAL BUSINESS MACHINES CORPORATION (280070) (approx. 44,393)
News, Profiles, Stocks and More about this company
|
| Published / Filed: |
2000-09-12
/ 1997-11-12
|
| Application Number: |
US1997000968403
|
| IPC Code: |
Advanced:
G06K 9/00;
Core:
more...
IPC-7:
G06K 9/50;
|
| ECLA Code: |
G06K9/00A3;
|
| U.S. Class: |
Current:
382/125;
382/228;
Original:
382/125;
382/228;
|
| Field of Search: |
382/115-127,193,201,215,224,228,227
340/825.34
356/071
704/256
|
| Priority Number: |
| 1997-11-12 |
US1997000968403 |
|
| Abstract: |
A computer implemented method may be used in classifying and identifying finger prints. Dab prints are analyzed according to intersections with fiducial lines. A two-dimensional Hidden Markov Model is then used to correspond states of data based on the intersections.
|
| Attorney, Agent or Firm: |
Whitham, Curtis & Whitham ;
Percello, Esq., Louis J. ;
|
| Primary / Asst. Examiners: |
Boudreau, Leo H.; Werner, Brian P.
|
| INPADOC Legal Status: |
Show legal status actions
|
| Parent Case: |
CROSS-REFERENCE TO RELATED APPLICATION
This application is related in subject matter to application Ser. No. 08/837,069 filed Apr. 11, 1997, by R. M. Bolle et al. for "System and Method for Determining Ridge Counts in Fingerprint Image Processing" and assigned to a common assignee herewith. The disclosure of application Ser. No. 08/837,069 is incorporated herein by reference.
|
| Family: |
None
|
First Claim:
Show all 7 claims |
I claim:
1. A system for classifying images, comprising:
- a computer with one or more central processing units, one or more memories, and one or more input devices;
- an input device that captures one or more images of an object, said images having one or more image lines corresponding to the object;
- a line generator function running on the computer that constructs a plurality of fiducial lines, said fiducial lines being a set of lines crossing the image, each said fiducial line crossing one or more of said image lines at one or more feature points, determining one or more metrics each said feature point, organizing said feature points as an ordered plurality of one-dimensional, ordered series of metrics, wherein each said ordered series of metrics corresponds to feature points along one fiducial line; and
- a two-dimensional hidden Markov model function running on the computer that uses said ordered plurality of one-dimensional ordered series of metrics to determine a probability that the image belongs to one or more categories and places the image in the category with highest probability, said two-dimensional hidden Markov model including a hierarchy of one-dimensional hidden Markov models operating in orthogonal directions.
|
| Background / Summary: |
Show background / summary
|
| Drawing Descriptions: |
Show drawing descriptions
|
| Description: |
Show description
|
| Forward References: |
Show 23 U.S. patent(s) that reference this one
|
|
|
|
|
|
|
| Foreign References: |
None
|
| Other References: |
Andrew Senior, A Hidden Markov Model Fingerprint Classifier, IEEE publication, 1998.
Krishna Nathan et al., Initialization of Hidden Markov Models for Unconstrained On-Line Handwriting Recognition, IEEE publication, 1996.
Andrew W. Senior et al., An Off-Line Cursive Handwriting Recognition System, IEEE publication, 1998.
Andrew Senior, Duration Modeling Results for an On-Line Handwriting Recognizer, IEEE publication, 1996.
Yang He et al., 2-D Shape Classification Using Hidden Markov Model, IEEE Transactions on Pattern Analysis and Machine Vision, vol. 13, No. 11, pp. 1172-1184, Nov. 1991.
(13 pages)
[ISI abstract]
O. Agazzi et al., "Connected and Degraded text recognition Using Planar Hidden Markov Models", IEEE, Apr. 1993, vol. V, pp. 113-116.
L.R. Rabiner, et al. "An Introduction to Hidden Markov Models", IEEE, Jan. 1986, pp. 4-16.
N. Ratha, et al., "A Real-Time Matchind System for Large Fingerprint Databases", IEEE, vol. 18, No. 8, Aug. 1996, pp. 799-813.
(15 pages)
Cited by 18 patents
[ISI abstract]
K. Karu, et al., "Fingerprint Classification", Pattern Recognition, vol. 29, No. 3, pp. 389-404, 1996.
(16 pages)
[ISI abstract]
A.P. Fitz et al., "Fingerprint Classification Using a Hexagonal Fast Fourier Transform", Pattern Recognition, vol. 29, No. 10, pp. 1587-1597, 1996.
(11 pages)
Cited by 2 patents
[ISI abstract]
G. T. Candela et al., "PCASYS--A Pattern-level Classification Automation System for Fingerprints", U.S. Department of Commerce, Aug. 1, 1995.
J.L. Blue et al., "Evaluation of Pattern Classifiers for Fingerprint and OCR Applications", Pattern Recognition, vol. 27, pp. 485-501, 1994.
(17 pages)
[ISI abstract]
M. Kawagoe et al., "Fingerprint Pattern Classification", Pattern Recognition, vol. 17, No. 3, pp. 295-303, 1984.
(9 pages)
Cited by 4 patents
C.L. Wilson et al., "Neural Network Fingerprint Classification", J. Artificial Neural Networks, vol. 1, No. 2, 1993.
|
|
 Nominate this for the Gallery...
|
|
