Biometric & Security

The lines which create a fingerprint pattern are called ridges and the spaces between the ridges are called valleys. It is through the pattern of these ridges and valleys that a unique fingerprint is matched for verification and authorization. Fingerprint is a unique feature to an individual. It stays with a person throughout his or her life.

This makes the fingerprint the most reliable kind of personal identification because it cannot be forgotten, misplaced, or stolen. Fingerprint authorization is potentially the most affordable and convenient method of verifying a person’s identity.

The fingerprint pattern is captured by fingerprint sensors. Fingerprint sensors work by taking a snapshot of a fingerprint and saving it into an image file. From the image, fingerprint recognition algorithm extracts unique features of each fingerprint and saves them in the database. For fingerprint verification, features of an input fingerprint are compared to the features of a specific fingerprint data in the database.

By comparing similarity between two feature sets, it is decided whether the two fingerprints match or not.

Suprema provides complete support to third-party developers in wide application areas from standalone access control equipments to network based security systems.

Relative links about fingerprint

Fingerprint Enhancement Algorithm

The Classification of Fingerprint

The Optimal Registration

A TactileSense device uses an electro-optical polymer film that transforms a fingerprint into a high-resolution optical image. That digitized image is passed to the PC host, where software processes, stores, and compares the fingerprint, thus identifying the individual and providing access to appropriate information.

Biometric start-up Who Vision Systems next week will unveil its security technology that uses fingerprint sensors to safeguard corporate data and limit access to specific individuals.

The fingerprint scanner company has a deal with Taiwan manufacturer MAG Group to embed 35 million fingerprint readers into computer monitors over the next four years, plus a partnership with security software vendor Entegrity to enable corporate networks to use Who Vision’s TactileSense technology.

Who Vision also is working with Microsoft, Computer Associates, and certificate authority company Entrust to make the devices work with their enterprise software, Windows NT for Microsoft and Unicenter for CA.

Who Vision thinks its technology suits the consumer market as well–for home users that want to block certain Internet sites for children or limit access to a family’s online bank accounts. It also is exploring opportunities to build its sensors into special-purpose information appliances for online services, home banking, or online brokerages.

“Companies are being forced to tell employees they have to use complicated, arbitrarily assigned passwords and to change them at regular intervals,” said Alex Dickinson, Who Vision’s chief executive. That means employees write down their passwords (a breach of security) or can share them with others.

“Using fingerprints gets rid of those issues,” he added, noting that the most common call to corporate help desks involves lost or forgotten passwords. In the TactileSense system, a digital fingerprint replaces a password or personal identification number (PIN) to verify a user’s identity, making it much more difficult for unauthorized users to get at information.

With a fingerprint sensor, a user simply puts their finger on the reader, which is about the size of a postage stamp and can be built into PC monitors, keyboards, smart-card readers–even, potentially, automated teller machines.

“In general, the problem is getting [biometric technologies] out into the infrastructure,” Machevsky said. “All these manufactures have been talking about working with monitor vendors and keyboard vendors. I’m waiting to see the PC OEMs come out and offer them.”

Who Vision’s effort to popularize its fingerprint system when rivals have struggled relies heavily on the price of its hardware device–$25 today and perhaps as little as $10 in volume production. That compares to prices as high as $200 for some competitors.

A year ago, notes analyst Ira Machevsky of Giga Information Group, the breakthrough for biometrics–technologies that recognize human attributes such as voice, face, fingerprints, even body odors–was a $600 device from National Registry.

Fingerprint readers could complement smart cards, which are plastic cards similar to credit cards that contain a chip. But smart cards haven’t caught on in the United States, although the enthusiasm for chip cards has been growing among security-conscious companies. A fingerprint sensor could replace a smart card PIN as a second means of identification.

Fingerprint readers, which unlike smart cards are mostly one-purpose technologies, could serve as a security alternative if smart-card adoption remains slow.

Beyond its hardware strategy, Who Vision also must get support for its devices built into software before they can be used, and that’s where the Entegrity pact is important.

“To the best of our knowledge, it’s the first time a software company has done a negotiated deal with a fingerprint hardware company,” Dickinson said.

Who Vision said it has an unannounced deal with a major manufacturer of PC keyboards. MAG, which is building a new factory to make the finger sensors, said it will resell 100,000 units this year. Who Vision hopes its sensor will begin showing up in PCs by the end of 1998.

Relative links about fingerprint

Fingerprint Enhancement Algorithm

The Classification of Fingerprint

Finger Print Matching

The Optimal Registration

Biometric Technology for Security

Public safety has become a centerpiece of our global society since a series consequences of recent events.

Motorola’s relevant expertise in fingerprint identification, based on more than a 30-year history of successful development and worldwide deployment, constitutes one element of the larger public safety enterprise. Work is under way to extend this technology by including other biometric and investigative information sources for delivery not only to desktops but also wirelessly through Motorola’s seamless mobility technology.

The computation of a fingerprint image quality map, segmentation, and ridge-flow direction image, the automatic detection of its singularities, the characterization and compensation of image distortion, and minutiae registration, matching, and scoring are a few examples. Mathematica is being used to design interactive applications for gathering ground truth data to support subsequent investigations and to evaluate the quality of automatically detected data. Mathematica movies have also provided invaluable visual insight into the functionality of underlying algorithms. This and much more is being done on a backdrop of an experimental system containing a large variety of fingerprint data, organized along with a collection of Mathematica notebooks in a structured multidirectory Mac OS X system.

While this evolution continues, the demand for accurate and rapid identification of fingerprints is rising in various civil scenarios. In response, Motorola has been directing serious efforts to extend the state of the art by exploring advanced image processing, feature extraction, and other analytical methods in order to achieve greater accuracy under the added requirement of improved speed.
For over four years, Motorola’s Biometrics Advanced Technology Group has been using Mathematica to efficiently formulate and evaluate analytical techniques applicable to various aspects of fingerprint identification.

Periodic reports of work accomplished is recorded in informative, executable Mathematica notebooks and distributed in PDF format. While much progress has been made to date, there are some very difficult problems that remain to be addressed more successfully-image enhancement, background isolation, separation of overlapped prints, maximum likelihood exploitation of detected features having limited quality and observability, analytic image continuation based on distortion models or knowledge of complex-plane singularities, classification, and so on. These and other related open issues are most clearly and efficiently addressed in Mathematica, the natural platform for the task. But Mathematica’s potential goes beyond its apparent function as an analytical testbed. With the upcoming release of Mathematica 6, the possibility of developing useful interactive fingerprint applications, such as a Latent Examiner’s Workstation, is just over the horizon. Even more intriguing is the very real possibility that, by virtue of its existing SQL database interface, Mathematica could support the essential functionality of an Automated Fingerprint Identification System, if not a more extensive Biometrics Identification System, not only as a platform for mathematically disciplined development but also as one capable of limited deployment.

Relative links about fingerprint

Fingerprint Enhancement Algorithm

The Classification of Fingerprint

Biometric Technology for Security

Fingerpirnt Security for PC

A critical step in automatic fingerprint matching is to automatically and reliably extract minutiae from the input fingerprint images. However, the performance of a minutiae extraction algorithm relies heavily on the quality of the input fingerprint images.

In order to ensure that the performance of an automatic fingerprint identification/verification system will be robust with respect to the quality of the fingerprint images, it is essential to incorporate a fingerprint enhancement algorithm in the minutiae extraction module. We have developed a fast fingerprint enhancement algorithm, which can adaptively improve the clarity of ridge and furrow structures of input fingerprint images based on the estimated local ridge orientation and frequency. We have evaluated the performance of the image enhancement algorithm using the goodness index of the extracted minutiae and the accuracy of an online fingerprint verification system. Experimental results show that incorporating the enhancement algorithms improves both the goodness index and the verification accuracy.

Relative links about fingerprint

The Classification of Fingerprint

Finger Print Matching

The Optimal Registration

Biometric Technology for Security

Large volumes of fingerprints are collected and stored everyday in a wide range of applications including forensics, access control, and driver license registration. An automatic recognition of people based on fingerprints requires that the input fingerprint be matched with a large number of fingerprints in a database (FBI database contains approximately 70 million fingerprints!). To reduce the search time and computational complexity, it is desirable to classify these fingerprints in an accurate and consistent manner so that the input fingerprint is required to be matched only with a subset of the fingerprints in the database.

Fingerprint classification is a technique to assign a fingerprint into one of the several pre-specified types already established in the literature which can provide an indexing mechanism. Fingerprint classification can be viewed as a coarse level matching of the fingerprints. An input fingerprint is first matched at a coarse level to one of the pre-specified types and then, at a finer level, it is compared to the subset of the database containing that type of fingerprints only. We have developed an algorithm to classify fingerprints into five classes, namely, whorl, right loop, left loop, arch, and tented arch. The algorithm separates the number of ridges present in four directions (0 degree, 45 degree, 90 degree, and 135 degree) by filtering the central part of a fingerprint with a bank of Gabor filters. This information is quantized to generate a FingerCode which is used for classification. Our classification is based on a two-stage classifier which uses a K-nearest neighbor classifier in the first stage and a set of neural networks in the second stage. The classifier is tested on 4,000 images in the NIST-4 database. For the five-class problem, classification accuracy of 90% is achieved. For the four-class problem (arch and tented arch combined into one class), we are able to achieve a classification accuracy of 94.8%. By incorporating a reject option, the classification accuracy can be increased to 96% for the five-class classification and to 97.8% for the four-class classification when 30.8% of the images are rejected.

Relative links about fingerprint

Fingerpirnt Security for PC

Fingerprint Enhancement Algorithm

Finger Print Matching

The Optimal Registration

Biometric Technology for Security

Among all the biometric techniques, fingerprint-based identification is the oldest method which has been successfully used in numerous applications. Everyone is known to have unique, immutable fingerprints. A fingerprint is made of a series of ridges and furrows on the surface of the finger. The uniqueness of a fingerprint can be determined by the pattern of ridges and furrows as well as the minutiae points. Minutiae points are local ridge characteristics that occur at either a ridge bifurcation or a ridge ending.

Fingerprint matching techniques can be placed into two categories: minutae-based and correlation based. Minutiae-based techniques first find minutiae points and then map their relative placement on the finger.  However, there are some difficulties when using this approach. It is difficult to extract the minutiae points accurately when the fingerprint is of low quality. Also this method does not take into account the global pattern of ridges and furrows. The correlation-based method is able to overcome some of the difficulties of the minutiae-based approach.  However, it has some of its own shortcomings. Correlation-based techniques require the precise location of a registration point and are affected by image translation and rotation.

Fingerprint matching based on minutiae has problems in matching different sized (unregistered) minutiae patterns. Local ridge structures can not be completely characterized by minutiae. We are trying an alternate representation of fingerprints which will capture more local information and yield a fixed length code for the fingerprint. The matching will then hopefully become a relatively simple task of calculating the Euclidean distance will between the two codes.

We are developing algorithms which are more robust to noise in fingerprint images and deliver increased accuracy in real-time. A commercial fingerprint-based authentication system requires a very low False Reject Rate (FAR) for a given False Accept Rate (FAR). This is very difficult to achieve with any one technique. We are investigating methods to pool evidence from various matching techniques to increase the overall accuracy of the system. In a real application, the sensor, the acquisition system and the variation in performance of the system over time is very critical. We are also field testing our system on a limited number of users to evaluate the system performance over a period of time.

Relative links about fingerprint

Fingerpirnt Security for PC

Fingerprint Enhancement Algorithm

The Optimal Registration

Biometric Technology for Security

The Classification of Fingerprint

The “registration pattern” between two fingerprints is the optimal registration of each part of one fingerprint with respect to the other fingerprint.

Registration patterns generated from imposter’s matching attempts are different from those patterns from genuine matching attempts, although they may share some similarities in the aspect of minutiae. This paper presents an algorithm that utilizes minutiae, associate ridges and orientation fields to determine the registration pattern between two fingerprints and their similarity.

The proposed matching scheme has two stages. An offline training stage derives a genuine registration pattern base from a set of genuine matching attempts. Then, an online matching stage registers the two fingerprints and determines the registration pattern. Only if the pattern makes a genuine one, a further fine matching is conducted. The genuine registration pattern base is derived using a set of fingerprints extracted from the NIST Special Database 24. Experimental results on the second FVC2002 database demonstrate the performance of the propose.

Relative links about fingerprint

Fingerpirnt Security for PC

Fingerprint Enhancement Algorithm

The Classification of Fingerprint

Finger Print Matching

Biometric Technology for Security

Since the war on terrorism began, the

The USA Patriot Act and Border Security Act direct that the Attorney General and the Secretary of State jointly, through the National Institute of Standards and Technology, “develop and certify a technology standard, including appropriate biometric identifier standards, that can be used to verify the identity of persons applying for a

A biometric is a physical characteristic that is unique to an individual. The standards would be used in all documents issued to foreigners by the State Department and the Immigration and Naturalisation Service, including student visas, green cards and border-crossing cards.Foreigners from about 180 countries require an immigrant or non-immigrant visa to enter the