com.machinezoo.sourceafis

Class FingerprintMatcher

java.lang.Object

com.machinezoo.sourceafis.FingerprintMatcher

public class FingerprintMatcher
extends Object

Fingerprint template representation optimized for fast 1:N matching. FingerprintMatcher maintains data structures that improve matching speed at the cost of some RAM. It can efficiently match one probe fingerprint to many candidate fingerprints.

New matcher is created by passing probe fingerprint template to index(FingerprintTemplate) on an empty fingerprint matcher instantiated with FingerprintMatcher() constructor. Candidate fingerprint templates are then passed one by one to match(FingerprintTemplate).

See Also:

SourceAFIS overview, FingerprintTemplate

Constructor Summary

Constructors

Constructor and Description
FingerprintMatcher() Instantiate an empty fingerprint matcher.

Method Summary

Modifier and Type	Method and Description
FingerprintMatcher	index(FingerprintTemplate probe) Build search data structures over probe fingerprint template.
double	match(FingerprintTemplate candidate) Match candidate fingerprint to probe fingerprint and calculate similarity score.
FingerprintMatcher	transparency(FingerprintTransparency transparency) Enable algorithm transparency.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

FingerprintMatcher

public FingerprintMatcher()

Instantiate an empty fingerprint matcher. Empty matcher does not match any FingerprintTemplate passed to match(FingerprintTemplate). You can call index(FingerprintTemplate) to index probe fingerprint and match(FingerprintTemplate) to match it to some candidate fingerprint.

See Also:

index(FingerprintTemplate)

Method Detail

transparency

public FingerprintMatcher transparency(FingerprintTransparency transparency)

Enable algorithm transparency. Subsequent operations on this matcher will report intermediate data structures created by the algorithm to the provided FingerprintTransparency instance.

Parameters:

transparency - target FingerprintTransparency or null to disable algorithm transparency

Returns:

this (fluent method)

See Also:

FingerprintTransparency

index

public FingerprintMatcher index(FingerprintTemplate probe)

Build search data structures over probe fingerprint template. Once this method is called, it is possible to call match(FingerprintTemplate) to compare fingerprints.

This method is heavy in terms of RAM footprint and CPU usage. Initialized FingerprintMatcher should be reused for multiple match(FingerprintTemplate) calls in 1:N matching.

Parameters:

probe - probe fingerprint template to be matched to candidate fingerprints

Returns:

this (fluent method)

See Also:

match(FingerprintTemplate)

match

public double match(FingerprintTemplate candidate)

Match candidate fingerprint to probe fingerprint and calculate similarity score. Candidate fingerprint in candidate parameter is matched to probe fingerprint previously passed to index(FingerprintTemplate).

Returned similarity score is a non-negative number that increases with similarity between probe and candidate fingerprints. Application should compare the score to a threshold with expression (score >= threshold) to arrive at boolean match/non-match decision. Threshold 10 corresponds to FMR (false match rate) of 10%, threshold 20 to FMR 1%, threshold 30 to FMR 0.1%, and so on.

Recommended threshold is 40, which corresponds to FMR 0.01%. Correspondence between threshold and FMR is approximate and varies with quality of fingerprints being matched. Increasing threshold rapidly reduces FMR, but it also slowly increases FNMR (false non-match rate). Threshold must be tailored to the needs of the application.

This method is thread-safe. Multiple threads can match candidates against single FingerprintMatcher.

Parameters:

candidate - fingerprint template to be matched with probe fingerprint indexed by this FingerprintMatcher

Returns:

similarity score between probe and candidate fingerprints

See Also:

index(FingerprintTemplate)