Benchmark area:
Fingerprint Matching (ISO)
|
This benchmark area contains fingerprint matching benchmarks using a standard minutiae-based template format [ISO/IEC 19794-2 (2005)]. Algorithms submitted to these benchmarks are required to compare ISO fingerprint templates to determine whether they are impressions of the same finger or not (one-to-one comparisons). No fingerprint enrollment (feature extraction) is required, only the minutiae matching algorithms are evaluated by these benchmarks.
|
Benchmarks
Currently, this benchmark area contains the following benchmarks:
- FMISO-TEST: A simple dataset useful to test algorithm compliancy
with the testing protocol
(results obtained on this benchmark are only visible in the participant
private area and cannot be published).
- FMISO-STD-1.0:
Contains ISO templates created from fingerprint images acquired in operational conditions using high-quality optical scanners. Results should reflect the expected accuracy in large-scale fingerprint-based applications.
- FMISO-HARD-1.0:
Contains a relevant number of difficult cases (noisy images, distorted impressions, etc.) that makes fingerprint verification more challenging. Results do not necessarily reflect the expected accuracy in real applications but allow to better discriminate the performance of various fingerprint recognition algorithms.
The table below reports the main characteristics of each benchmark:
Benchmark |
Scanner Type |
Resolution |
Minimum Template Size |
Maximum Template Size |
Genuine Attempts |
Impostor Attempts |
FMISO-TEST |
Optical |
500 dpi |
440x500 |
440x500 |
280 |
45 |
FMISO-STD-1.0 |
Optical |
500 dpi |
440x500 |
440x500 |
27720 |
87990 |
FMISO-HARD-1.0 |
Optical |
500 dpi |
260x374 |
448x500 |
19320 |
20850 |
The following sections report the testing protocol and the performance
indicators common to all benchmarks in this area.
Protocol
Each participant is required to submit, for each algorithm, an executable
in the form of Win32 console application.
- The executable (match.exe) will take the input from command-line arguments and will
append the output to a text file. It matches two ISO templates and
produces a similarity score; the command-line syntax is:
match.exe <ISOtemplatefile1> <ISOtemplatefile2>
<outputfile>
where:
ISOtemplatefile1 |
the first input ISO template pathname |
ISOtemplatefile2 |
the second input ISO template pathname |
outputfile |
the output text-file, where a log string (of the form
ISOtemplatefile1 ISOtemplatefile2 result similarity)
must be appended; result
is "OK" if the matching can be performed or "FAIL" if the matching cannot be
executed by the algorithm; similarity is a
floating point value ranging from 0 to 1 which indicates the similarity between
the two templates: 0 means no similarity, 1 maximum similarity |
- The executable has to
operate only on the explicitly-given inputs, without exploiting any
learning technique or template consolidation/update based on previous
matches.
- C, C# and Matlab language skeletons for match.exe are available in the
download page to reduce the participants
implementation efforts.
Constraints
During test execution the following constraints will be enforced:
Benchmark |
Maximum time for each match |
Memory allocation limit for match process |
FMISO-TEST |
3 seconds |
No limit |
FMISO-STD-1.0 |
3 seconds |
No limit |
FMISO-HARD-1.0 |
3 seconds |
No limit |
Each matching attempt that violates one of the above constraints
results in a failure to match.
The following time breaks are enforced between two consecutive submissions to the
same benchmark by the same participant.
Benchmark |
Minimum break |
FMISO-TEST |
12 hour(s)
|
FMISO-STD-1.0 |
30 day(s)
|
FMISO-HARD-1.0 |
30 day(s)
|
Performance Evaluation
For each algorithm, genuine (matching two ISO
templates of
the same finger) and impostor (matching two ISO
templates originating from different
fingers) attempts are performed to compute False Non
Match Rate FNMR (also referred as False Rejection Rate - FRR) and
False Match Rate FMR (also referred as False
Acceptance Rate - FAR).
For each algorithm the following performance indicators are reported:
- REJNGRA (Number of rejected
fingerprints during genuine matches)
- REJNIRA (Number of rejected
fingerprints during impostor matches)
- EER (equal-error-rate)
- FMR100 (the lowest FNMR for FMR≤1%)
- FMR1000 (the lowest FNMR for FMR≤0.1%)
- FMR10000 (the lowest FNMR for FMR≤0.01%)
- ZeroFMR (the lowest FNMR for FMR=0%)
- ZeroFNMR (the lowest FMR for FNMR=0%)
- Average matching time
- Maximum amount of memory allocated
- Impostor and
Genuine score distributions
- FMR(t)/FNMR(t) curves, where t is the
acceptance threshold
- DET(t) curve
|