think of cctv? think of Guardtech

Finger Print Section

Finger Print Overview
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 lines that 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.

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.

Finger Print Algorithm

Suprema has developed a fingerprint verification algorithm, which has been proven to be one of the most advanced technologies in Fingerprint verification contest (FVC). It is the core technology of our company, which can be applied to the embedded module, PC authentication library, and various application products.

Advanced Minutiae Based Algorithm
Our algorithm is based on the minutiae, such as ending, bifurcation, and singular points in the fingerprint images, which have been known to be effective clues for fingerprint verification. Moreover, global ridge information is also utilized to overcome the shortcomings of local minutiae features, resulting in the outstanding verification performance. The algorithm is divided into two major processing components, feature extractor and matcher.

Feature Extractor
Input fingerprint images captured from the sensors are noisy, in poor contrast, containing much flaw and smudge. Based on intensive analysis of the image characteristics, powerful image enhancement technique is developed, yielding high quality ridge image. Moreover, a lot of erroneous features are efficiently removed by noisy area reduction technique.

Image Enhancement 1

Image Enhancement 2

Generally, there are tradeoffs between matching speed and discriminating performance in conventional technologies. Our matching engine provides both fast matching speed and outstanding matching performance on noisy features, so that our algorithm is easily applied to the embedded systems, controlled by low-cost slow processors. And it also has the merit in searching large database.

Platform interoperability
Our algorithm is platform independent, enabled by low memory constraint, fast verification speed, and simple standard operations. This functionality enables the customers to integrate various platforms, such as PC and various controller or DSP based embedded modules.

Sensor interoperability
Our algorithm is interoperable on different sensor images. For example, the customer can enroll finerprints on PC using SFR300-S scanner and can download to the standalone modules using different sensors like TC (Upek's TouchChip) or FL (AuthenTec's AF-S2).

Example Captured Fingerpoint Images from Various Sensor

Verification Result


The Fingerprint Philosophy

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: minute-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.

Fingerprint Classification

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.

Fingerprint Image Enhancement

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.

Fingerprint Vertification Competition (FVC)

The FVC is the world's largest evaluation of fingerprint matching technologies. It is an international competition for fingerprint verification algorithms held biannually and organized by the 3rd party research labs of Italy and USA. In the most recent two events, FVC2004 and FVC2006, Suprema's fingerprint recognition algorithm ranked top among worldwide participants.

In FVC2004 and FVC2006, Suprema's fingerprint recognition algorithm ranked top among participants in light and open category, respectively. In FVC2006, Suprema ranked No.1 in medal ranking of open category by winning 7 gold medals. In FVC2004, Suprema ranked No.1 in light category with the lowest error rate. Suprema is the only company who has won both categories (open and light) of the last two events, FVC2004 and FVC2006.

* Additional information on FVC2006 is available on the Web at

FVC2004 (Average results of Light Category)

Avg EER = Average Equal Error Rate(when FMR is equal to FNMR)
* Additional information on FVC2004 is available on the Web at

The aim of the FVC is to track recent advances in fingerprint verification and to benchmark the state-of-the-art in fingerprint technology.

The Open category has no limits on memory requirements and template size. The Light category limits on verification time, memory usage and template size.

For fair comparison, database were collected by using the following sensors/technologies.



For fair comparison, database were collected by using the following sensors/technologies :

43 participants (29 industrial, 6 academic, and 8 independent developers) 67 algorithms submitted (41 in the Open Category and 26 in the Light Category)

53 participants (27 industrial, 13 academic, and 13 independent developers) 70 algorithms submitted (44 in the Open Category and 26 in the Light Category)