A Finger Print is an impression of the friction ridges of all or any part of the finger. A friction ridge is a raised portion of the epidermis on the palmar (palm and fingers) or plantar (sole and toes) skin, consisting of one or more connected ridge units of friction ridge skin. These ridges are sometimes known as "dermal ridges" or "dermal papillae".

Identification

Finger Print identification (sometimes referred to as dactyloscopy) is the process of comparing questioned and known friction skin ridge impressions from fingers to determine if the impressions are from the same finger. The flexibility of friction ridge skin means that no two finger or palm prints are ever exactly alike (never identical in every detail), even two impressions recorded immediately after each other.

Finger Print identification (also referred to as individualization) occurs when an expert (or an expert computer system operating under threshold scoring rules) determines that two friction ridge impressions originated from two fingers are entirely different.

Finger Prints are unique property of any human being and can be used to identify who is who. It can help industries in many ways, in form of Recognition and Access Control solutions.

Finger Print Recognition Algorithms

A Finger Print recognition algorithm is a method of identifying a person using his/her Finger Prints. Currently, the most frequently used Finger Print recognition algorithms are:

§          Characterization algorithm

The characterization algorithm evaluates the quality of Finger Print images acquired by the Finger Print recognition sensor to determine their usability, and analyzes the character points of the Finger Prints. This is the most frequently used Finger Print recognition algorithm.

§          Finger Print -matching algorithm

The Finger Print -matching algorithm is a process of arranging two comparable Finger Prints to analyze their common characteristics, and calculating the degree of similarity between the two Finger Prints.

BioAXS Algorithms

The Finger Print recognition algorithm follows the commonly accepted Finger Print identification scheme, Characterization algorithm which uses a set of specific Finger Print points (minutiae). However, it contains many proprietary algorithmic solutions, which enhance the system performance and reliability. Some of them are listed below:

The adaptive image filtration algorithm:

It allows to eliminate noises, ridge ruptures and stuck ridges, and extract minutiae reliably even from poor quality Finger Prints, with a processing time of about 0.2 - 0.4 seconds (all times are given for a Pentium 4, 3 GHz processor).

§  Functions can be used in 1:1 matching (verification), as well as 1:N mode (identification).

• Algorithm includes a fast template matching algorithm that is tolerant to Finger Print translation, rotation and deformation.

§      Algorithm does not require the presence of the Finger Print core or delta points in the image, and can recognize a Finger Print from any part of it.

§      Algorithm can use database entries which were pre-sorted using certain global features. Finger Print matching is performed first with the database entries having global features most similar to those of the test Finger Print . If matching within this group yields no positive result, then the next record with most similar global features is selected, and so on, until the matching is successful or the end of the database is reached. In most cases there is a fairly good chance that the correct match will be found at the beginning of the search. As a result, the number of comparisons required to achieve Finger Print identification decreases drastically, and correspondingly, the matching speed increases.

§      Algorithm has the Finger Print enrollment with features generalization mode. This mode generates the collection of the generalized Finger Print features from a set of Finger Prints of the same finger. Each Finger Print image is processed and features are extracted. Then the features collection set is analyzed and combined into a single generalized features collection, which is written to the database. This way, the enrolled features are more reliable and the Finger Print recognition quality considerably increases.

§     Algorithm modes that help to achieve better results for specific scanner. Modes are following:

o         Universal

o         DigitalPersona U.are.U family scanners

o         Cross Match Verifier 300 scanners

o         Futronic FS80 scanner

o         NITGEN Fingkey Hamster and Fingkey Hamster II scanners

o         SecuGen Hamster III scanner

o         Testech Bio-i scanner

o         Startek FM200 scanner

o         Tacoma CMOS scanner

o         Fujitsu MBF200 scanner

o         Identix DFR-2090 scanner

o         UPEK TouchChip scanners

o         Digent Izzix FD1000 scanner

o         BiometriKa FX 2000 and FX 3000 scanners

o         AuthenTec AES2501B sensor

o         AuthenTec AES4000 and AF-S2 sensors

o         LighTuning LTT-C500 sensor

o         Atmel FingerChip sensor