No edit summary |
|||
| (21 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| + | == Definition == |
||
| ⚫ | |||
| + | |||
| + | '''Fingerprint recognition''' is |
||
| + | |||
| + | {{Quote|[a] [[biometric modality]] that uses the physical structure of an individual's [[fingerprint]] for recognition purposes. Important features used in most fingerprint recognition [[system]]s are [[minutia(e) point|minutiae point]]s that include [[bifurcation]]s and [[ridge ending]]s.<ref>[[Biometrics Identity Management Agency]], Biometrics Glossary, at 29 (Ver. 5) (Oct. 2010) ([http://www.biometrics.dod.mil/Files/Documents/Standards/BioGlossary.pdf full-text]).</ref>}} |
||
| + | |||
| + | == Overview == |
||
| + | |||
| ⚫ | Fingerprint recognition is one of the best known and most widely used [[biometric]] technologies. Automated systems have been commercially available since the early 1970s, and there are currently more than 75 fingerprint recognition technology companies. Until recently, it was used primarily in law enforcement applications. |
||
| + | |||
| + | == Historical background == |
||
| + | |||
| + | [[Fingerprint]]s have been used to identify individuals since the mid-1800s. Manual fingerprint identification systems were based on classifying prints according to general characteristics, such as predominant patterns of [[loop]]s, [[whorl]]s, or [[arch]]es in the tiny fingerprint [[ridge]]s, plus patterns of [[branch]]es and terminations of the ridges (called [[minutiae]]). [[Fingerprint]] [[file]] [[data]] were obtained by using special ink and a ten-print card; fingerprint cross-checking with local and national records was done manually. |
||
| + | |||
| + | The cross-checking process began to be automated in the late 1960s and by 1983 the [[Federal Bureau of Investigation]] ([[FBI]]) had converted all criminal [[fingerprint]] searches from manual to automated operations. |
||
| + | |||
| + | == How it works == |
||
| − | Fingerprint recognition technology extracts features from impressions made by the distinct |
+ | Fingerprint recognition technology extracts features from impressions made by the distinct [[ridge]]s on the fingertips. The [[fingerprint]]s can be either [[flat fingerprint|flat]] or [[rolled fingerprint|rolled]]. A flat print captures only an impression of the central area between the fingertip and the first knuckle; a rolled print captures [[ridge]]s on both sides of the finger. |
| + | |||
| + | [[File:Fingerprint2.jpg|thumb|300px]] |
||
| + | |||
| ⚫ | An [[image]] of the [[fingerprint]] is [[capture]]d by a [[scanner]], [[image enhancement|enhanced]], and converted into a [[template]]. [[Scanner]] technologies can be [[optical]], silicon, or [[ultrasound]] technologies. [[Ultrasound]], while potentially the most accurate, has not been demonstrated in widespread use. [[Optical scanner]]s are the most commonly used. During [[image enhancement|enhancement]], “noise” caused by such things as dirt, cuts, scars, and creases or dry, wet, or worn [[fingerprint]]s is reduced, and the definition of the [[ridge]]s is [[image enhancement|enhanced]]. [[Template]] size ranges from 250 [[byte]]s up to 1,000 [[byte]]s, depending on which [[vendor]]’s [[proprietary]] [[algorithm]] the [[system]] uses. |
||
| + | |||
| + | Approximately 80% of [[vendor]]s base their [[algorithm]]s on the [[extraction]] of [[minutia(e) point]]s relating to breaks in the [[ridge]]s of the fingertips. Other [[algorithm]]s are based on extracting [[ridge pattern]]s. |
||
| + | |||
| + | The determination of the number of fingers to be included in a set of [[fingerprint]]s is informed by the details of the specific [[implementation]] of [[biometric technology]]. While a single [[fingerprint]] might prove sufficient for one application, two [[fingerprint]]s may be required for another application. |
||
| + | |||
| + | As a general matter, ten rolled [[fingerprint]]s will always present the greatest potential for the highest [[accuracy]]. It takes longer to collect ten rolled [[fingerprint]]s and given the law enforcement community’s history of collecting this type of [[fingerprint]], there may be a certain social fear of stigma associated with “getting fingerprinted” in this way. |
||
| + | |||
| + | == References == |
||
| + | <references /> |
||
| + | |||
| + | == Sources == |
||
| + | * [[Information Security: Challenges in Using Biometrics]], at 7-8. |
||
| ⚫ | An image of the fingerprint is |
||
| + | * [[Privacy and Biometrics: Building a Conceptual Foundation]], at 14-15. |
||
== See also == |
== See also == |
||
| − | * [[ |
+ | * [[Core point]] |
| + | * [[Delta point]] |
||
| + | * [[Fingerprint identification]] |
||
| + | * [[Friction ridge]] |
||
| + | * [[Valley]] |
||
[[Category:Technology]] |
[[Category:Technology]] |
||
[[Category:Security]] |
[[Category:Security]] |
||
| + | [[Category:Biometrics]] |
||
Latest revision as of 04:57, 23 May 2012
Definition[]
Fingerprint recognition is
| “ | [a] biometric modality that uses the physical structure of an individual's fingerprint for recognition purposes. Important features used in most fingerprint recognition systems are minutiae points that include bifurcations and ridge endings.[1] | ” |
Overview[]
Fingerprint recognition is one of the best known and most widely used biometric technologies. Automated systems have been commercially available since the early 1970s, and there are currently more than 75 fingerprint recognition technology companies. Until recently, it was used primarily in law enforcement applications.
Historical background[]
Fingerprints have been used to identify individuals since the mid-1800s. Manual fingerprint identification systems were based on classifying prints according to general characteristics, such as predominant patterns of loops, whorls, or arches in the tiny fingerprint ridges, plus patterns of branches and terminations of the ridges (called minutiae). Fingerprint file data were obtained by using special ink and a ten-print card; fingerprint cross-checking with local and national records was done manually.
The cross-checking process began to be automated in the late 1960s and by 1983 the Federal Bureau of Investigation (FBI) had converted all criminal fingerprint searches from manual to automated operations.
How it works[]
Fingerprint recognition technology extracts features from impressions made by the distinct ridges on the fingertips. The fingerprints can be either flat or rolled. A flat print captures only an impression of the central area between the fingertip and the first knuckle; a rolled print captures ridges on both sides of the finger.
An image of the fingerprint is captured by a scanner, enhanced, and converted into a template. Scanner technologies can be optical, silicon, or ultrasound technologies. Ultrasound, while potentially the most accurate, has not been demonstrated in widespread use. Optical scanners are the most commonly used. During enhancement, “noise” caused by such things as dirt, cuts, scars, and creases or dry, wet, or worn fingerprints is reduced, and the definition of the ridges is enhanced. Template size ranges from 250 bytes up to 1,000 bytes, depending on which vendor’s proprietary algorithm the system uses.
Approximately 80% of vendors base their algorithms on the extraction of minutia(e) points relating to breaks in the ridges of the fingertips. Other algorithms are based on extracting ridge patterns.
The determination of the number of fingers to be included in a set of fingerprints is informed by the details of the specific implementation of biometric technology. While a single fingerprint might prove sufficient for one application, two fingerprints may be required for another application.
As a general matter, ten rolled fingerprints will always present the greatest potential for the highest accuracy. It takes longer to collect ten rolled fingerprints and given the law enforcement community’s history of collecting this type of fingerprint, there may be a certain social fear of stigma associated with “getting fingerprinted” in this way.
References[]
- ↑ Biometrics Identity Management Agency, Biometrics Glossary, at 29 (Ver. 5) (Oct. 2010) (full-text).
Sources[]
- Information Security: Challenges in Using Biometrics, at 7-8.
- Privacy and Biometrics: Building a Conceptual Foundation, at 14-15.