Improving biometric recognition by means of score ratio, the likelihood ratio for non‐probabilistic classifiers. A benchmarking study
Abstract One of the ever present goals in biometrics research is to improve system performance. Herein, an alternative method is proposed that is independent of the biometric characteristic and the system, as this proposal, Score Ratio, is applied to the output (comparison score) of the classifier....
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-03-01
|
| Series: | IET Biometrics |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/bme2.12011 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832546696370847744 |
|---|---|
| author | Carlos Vivaracho‐Pascual Arancha Simon‐Hurtado Esperanza Manso‐Martinez |
| author_facet | Carlos Vivaracho‐Pascual Arancha Simon‐Hurtado Esperanza Manso‐Martinez |
| author_sort | Carlos Vivaracho‐Pascual |
| collection | DOAJ |
| description | Abstract One of the ever present goals in biometrics research is to improve system performance. Herein, an alternative method is proposed that is independent of the biometric characteristic and the system, as this proposal, Score Ratio, is applied to the output (comparison score) of the classifier. The Likelihood Ratio is widely used with probabilistic classifiers because it performs well in these circumstances. However, when the classifiers are non‐probabilistic, then this ratio is not used. This is our proposal: with non‐probabilistic classifier based systems, the decision is taken solely through the score, supposing that the biometric feature, X, belongs to the Claimant (H0 hypothesis), here, it is also proposed to make use of the score considering that X does not belong to the Claimant (H1 hypothesis); more specifically, using the ratio between these two scores: the Score Ratio. For more objective results, benchmarking and reproducibility are used in the experiments, applying our proposal with third‐party (benchmarking) experimental protocols, databases, classifiers and performance measures for fingerprint, iris and finger vein recognition. Statistically significant improvements have been obtained when the Score Ratio is used with regard to not using it in all cases tested. |
| format | Article |
| id | doaj-art-c26b5b00e06748499b8edbb103709254 |
| institution | Kabale University |
| issn | 2047-4938 2047-4946 |
| language | English |
| publishDate | 2021-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj-art-c26b5b00e06748499b8edbb1037092542025-02-03T06:47:28ZengWileyIET Biometrics2047-49382047-49462021-03-0110212714110.1049/bme2.12011Improving biometric recognition by means of score ratio, the likelihood ratio for non‐probabilistic classifiers. A benchmarking studyCarlos Vivaracho‐Pascual0Arancha Simon‐Hurtado1Esperanza Manso‐Martinez2Computer Science Department University of Valladolid Valladolid SpainComputer Science Department University of Valladolid Valladolid SpainComputer Science Department University of Valladolid Valladolid SpainAbstract One of the ever present goals in biometrics research is to improve system performance. Herein, an alternative method is proposed that is independent of the biometric characteristic and the system, as this proposal, Score Ratio, is applied to the output (comparison score) of the classifier. The Likelihood Ratio is widely used with probabilistic classifiers because it performs well in these circumstances. However, when the classifiers are non‐probabilistic, then this ratio is not used. This is our proposal: with non‐probabilistic classifier based systems, the decision is taken solely through the score, supposing that the biometric feature, X, belongs to the Claimant (H0 hypothesis), here, it is also proposed to make use of the score considering that X does not belong to the Claimant (H1 hypothesis); more specifically, using the ratio between these two scores: the Score Ratio. For more objective results, benchmarking and reproducibility are used in the experiments, applying our proposal with third‐party (benchmarking) experimental protocols, databases, classifiers and performance measures for fingerprint, iris and finger vein recognition. Statistically significant improvements have been obtained when the Score Ratio is used with regard to not using it in all cases tested.https://doi.org/10.1049/bme2.12011biometrics (access control)feature extractionfingerprint identificationiris recognitionpattern classificationvein recognition |
| spellingShingle | Carlos Vivaracho‐Pascual Arancha Simon‐Hurtado Esperanza Manso‐Martinez Improving biometric recognition by means of score ratio, the likelihood ratio for non‐probabilistic classifiers. A benchmarking study IET Biometrics biometrics (access control) feature extraction fingerprint identification iris recognition pattern classification vein recognition |
| title | Improving biometric recognition by means of score ratio, the likelihood ratio for non‐probabilistic classifiers. A benchmarking study |
| title_full | Improving biometric recognition by means of score ratio, the likelihood ratio for non‐probabilistic classifiers. A benchmarking study |
| title_fullStr | Improving biometric recognition by means of score ratio, the likelihood ratio for non‐probabilistic classifiers. A benchmarking study |
| title_full_unstemmed | Improving biometric recognition by means of score ratio, the likelihood ratio for non‐probabilistic classifiers. A benchmarking study |
| title_short | Improving biometric recognition by means of score ratio, the likelihood ratio for non‐probabilistic classifiers. A benchmarking study |
| title_sort | improving biometric recognition by means of score ratio the likelihood ratio for non probabilistic classifiers a benchmarking study |
| topic | biometrics (access control) feature extraction fingerprint identification iris recognition pattern classification vein recognition |
| url | https://doi.org/10.1049/bme2.12011 |
| work_keys_str_mv | AT carlosvivarachopascual improvingbiometricrecognitionbymeansofscoreratiothelikelihoodratiofornonprobabilisticclassifiersabenchmarkingstudy AT aranchasimonhurtado improvingbiometricrecognitionbymeansofscoreratiothelikelihoodratiofornonprobabilisticclassifiersabenchmarkingstudy AT esperanzamansomartinez improvingbiometricrecognitionbymeansofscoreratiothelikelihoodratiofornonprobabilisticclassifiersabenchmarkingstudy |