Image analysis – Applications – Personnel identification
Reexamination Certificate
1999-04-29
2001-07-24
Bella, Matthew C. (Department: 2621)
Image analysis
Applications
Personnel identification
C382S124000, C382S173000, C382S194000, C356S071000
Reexamination Certificate
active
06266433
ABSTRACT:
FIELD OF THE INVENTION
This invention relates to the field of image processing. More specifically, the invention relates to a system and method for processing fingerprint images.
BACKGROUND OF THE INVENTION
There exist systems for accomplishing automatic authentication or identification of a person using his/her fingerprint. A fingerprint of a person comprises a distinctive and unique ridge pattern structure. For authentication or identification purposes, this ridge pattern structure can be characterized by endings and bifurcations of the individual ridges. These features are popularly known as minutiae.
An example fingerprint is shown in FIG.
1
A. The minutiae for the fingerprint shown in
FIG. 1A
are shown in
FIG. 1B
as being enclosed by “boxes.” For example, box
101
B shows a bifurcation minutiae of a bifurcated ridge
101
A and box
103
B shows a ridge ending minutiae of ridge
103
A. Note that minutiae on the ridges in fingerprints have directions (also called orientations)
105
associated with them. The direction of a minutiae at a ridge end
103
B is the direction in which the end of the ridge points. The direction of a bifurcation minutiae
101
B is the direction in which the bifurcated ridge points. Minutiae also have locations which are the positions, with respect to some coordinate system, of the minutiae on the fingerprint.
One of the prevalent methods of fingerprint authentication and identification methods is based on minutiae features. These systems need to process the fingerprint images to obtain accurate and reliable minutiae features to effectively determine the identity of a person.
FIG. 2
is a flow chart showing the steps generally performed by a typical prior art system
200
.
In step
210
, the image is acquired. This acquisition of the image could either be through a CCD camera and framegrabber interface or through a document scanner communicating with the primary computing equipment.
Once the image is acquired into the computer memory or disk, relevant minutiae features are extracted (
220
). Not all of the features thus extracted are reliable; some of the unreliable features are optionally edited or pruned (step
230
), e.g., by manual editing. The resultant reliable features are used for matching the fingerprint images (step
240
).
In semi-automatic systems, the unreliable features could be manually pruned by a human expert visually inspecting the extracted features before the minutiae are used for matching (step
240
). The following reference mentions such a manual pruning system incorporated into an automatic fingerprint identification system:
Advances in Fingerprint Technology,
Edited by Henry C. Lee, R. E. Gaensslen,
Published by CRC press, Ann Arbor,
Chapter on Automated Fingerprint Identification Systems,
I. North American Morpho Systems,
Section on Fingerprint Processing Functions.
This reference is herein incorporated by reference in its entirety.
The fingerprint feature extraction
220
, pruning
230
, and matching system
240
constitute the primary backbone
250
of a typical minutiae-based automatic fingerprint identification systems (AFIS). The matching results are typically verified by a human expert (step
260
). The verification may also be performed automatically. The following reference describes examples of the state of the prior art:
Nalini K. Ratha and Shaoyun Chen and Anil K. Jain,
Adaptive flow orientation based texture extraction in fingerprint images,
Pattern Recognition,
vol. 28, no. 11, pp. 1657-1672, November, 1995.
This reference is herein incorporated by reference in its entirety.
FIG. 3
is a flow chart showing the prior art steps performed by a feature extraction process
220
that are similar to some of the feature extraction methods proposed by Ratha, Jain, and Chen in the article incorporated above.
It is often not desirable to directly use the input fingerprint image for feature extraction. The fingerprint image might need an enhancement or preprocessing before one could further extract minutiae. Typically, a smoothing process is employed to reduce the pixel-wise noise (step
305
).
After the preprocessing stages, prior art systems find the directions of the ridge flow (step
310
). The next important step in the processing is finding the exact location of the finger in the image. To accomplish this a process referred to as the foreground/background segmentation (step
315
) separates the finger part of the image from the background part of the image. Once the finger part is localized, i.e., segmented to define its location, the next step is to extract the ridges from the fingerprint image (step
320
). The ridges thus extracted are thick and might contain some noisy artifacts which do not correspond to any meaningful structures on the finger. These small structures, i.e., the noisy artifacts, can be safely removed and longer structures are smoothed (step
325
). The longer structures are thinned to one-pixel width and then processed to remove any other artifacts using morphological operators (step
330
). The locations and orientations of ridge endings and bifurcations are then extracted from the thinned structures (step
335
) to obtain the minutiae. In some systems, a “cleanup” or post-processing
340
is performed. Here, based on certain criteria, undesirable minutiae are removed.
STATEMENT OF PROBLEMS WITH THE PRIOR ART
Since the human skin is elastic, the image capture process might result in different distortions of the finger skin with each different capture of the fingerprint as it is being placed on the fingerprint capture station. This results in an identical pair of the features (say, minutiae) at different distances apart from each other in the different prints of the same finger captured at different times. Some prior art systems use Euclidean (geometric) metric features for fingerprint image processing. Such systems cannot identify two differently distorted prints of the same fingers as identical.
FIG. 4
is a prior art drawing of two typical prints
410
(
FIG. 4A
) and
420
(
FIG. 4B
) of the same finger. The fingerprints were captured with shear in different directions. As the fingerprint itself is distorted, the minutiae-based features located on the fingers are differently displaced from their original position. Consequently, it is difficult to match these prints based on a matching strategy using features which are purely Euclidean (geometric), e.g., distance between minutiae. For instance, it is typical to have fingerprint features displaced 5-20% from their original position due to varying magnitude and direction of pressure of the finger on the glass plate (in case of livescan fingerprint process) and on paper (in case of inked fingerprints). To illustrate, the distance between minutiae
401
and
402
in
FIG. 4A
is d
1
, whereas the distance between these minutiae (
401
,
402
) in
FIG. 4B
, the same fingerprint with a different shear, is d
2
, a different difference. When the distance between the same minutiae differ in different images of the same fingerprint, it is difficult to determine that these images should be matched.
OBJECTS OF THE INVENTION
An object of this invention is an improved fingerprint image processing system.
An object of this invention is to improve the accuracy and reliability of a fingerprint image matching system by automating a metric which is less sensitive to the pressure and shear variance in fingerprint images.
SUMMARY OF THE INVENTION
The invention provides an automatic pressure/shear invariant metric of measuring the distances of features on the fingerprint. This metric uses ridge counts to measure these distances. A ridge count between any two points on the fingerprint is defined as the number of ridges running between the two points on the fingerprint. Given two points in the fingerprint image, the present ridge count process determines the length of the line (or bar) joining the points in terms of number of ridge distances, i.e., the number of times the lines crosses the ridges. Since the ridge count is invariant to the elastic distortions of
Bolle Rudolf Maarten
Colville Scott Eric
Pankanti Sharathchandra U.
Bella Matthew C.
Chawan Sheela
International Business Machines - Corporation
Percello Louis J.
Perman & Green LLP
LandOfFree
System and method for determining ridge counts in... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for determining ridge counts in..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for determining ridge counts in... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2553201