Local feature encoding for unknown presentation attack detection: An analysis of different local feature descriptors
Abstract In spite of the advantages of using fingerprints for subject authentication, several works have shown that fingerprint recognition systems can be easily circumvented by means of artificial fingerprints or presentation attack instruments (PAIs). In order to address that threat, the existing...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-07-01
|
| Series: | IET Biometrics |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/bme2.12023 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832546725673304064 |
|---|---|
| author | Lázaro J. González‐Soler Marta Gomez‐Barrero Jascha Kolberg Leonardo Chang Airel Pérez‐Suárez Christoph Busch |
| author_facet | Lázaro J. González‐Soler Marta Gomez‐Barrero Jascha Kolberg Leonardo Chang Airel Pérez‐Suárez Christoph Busch |
| author_sort | Lázaro J. González‐Soler |
| collection | DOAJ |
| description | Abstract In spite of the advantages of using fingerprints for subject authentication, several works have shown that fingerprint recognition systems can be easily circumvented by means of artificial fingerprints or presentation attack instruments (PAIs). In order to address that threat, the existing presentation attack detection (PAD) methods have reported a high detection performance when materials used for the fabrication of PAIs and capture devices are known. However, for more complex and realistic scenarios where one of those factors remains unknown, these PAD methods are unable to correctly separate a PAI from a real fingerprint (i.e. bona fide presentation). In this article, a new PAD approach based on the Fisher Vector technique, which combines local and global information of several local feature descriptors in order to improve the PAD generalisation capabilities, was proposed. The experimental results over unknown scenarios taken from LivDet 2011 to LivDet 2017 show that our proposal reduces the top state‐of‐the‐art average classification error rates by up to four times, thereby making it suitable in real applications demanding high security. In addition, the best single configuration achieved the best results in the LivDet 2019 competition, with an overall accuracy of 96.17%. |
| format | Article |
| id | doaj-art-40df8d9b32ba448c9ec5ba7848f4ee43 |
| institution | Kabale University |
| issn | 2047-4938 2047-4946 |
| language | English |
| publishDate | 2021-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj-art-40df8d9b32ba448c9ec5ba7848f4ee432025-02-03T06:47:18ZengWileyIET Biometrics2047-49382047-49462021-07-0110437439110.1049/bme2.12023Local feature encoding for unknown presentation attack detection: An analysis of different local feature descriptorsLázaro J. González‐Soler0Marta Gomez‐Barrero1Jascha Kolberg2Leonardo Chang3Airel Pérez‐Suárez4Christoph Busch5Biometrics and Internet Security Research Group Hochschule Darmstadt Darmstadt GermanyDepartment of Computer Science Hochschule Ansbach Ansbach GermanyBiometrics and Internet Security Research Group Hochschule Darmstadt Darmstadt GermanyTecnológico de Monterrey Campus Estado de México Estado de México MéxicoAdvanced Technologies Application Center (CENATAV) La Habana CubaBiometrics and Internet Security Research Group Hochschule Darmstadt Darmstadt GermanyAbstract In spite of the advantages of using fingerprints for subject authentication, several works have shown that fingerprint recognition systems can be easily circumvented by means of artificial fingerprints or presentation attack instruments (PAIs). In order to address that threat, the existing presentation attack detection (PAD) methods have reported a high detection performance when materials used for the fabrication of PAIs and capture devices are known. However, for more complex and realistic scenarios where one of those factors remains unknown, these PAD methods are unable to correctly separate a PAI from a real fingerprint (i.e. bona fide presentation). In this article, a new PAD approach based on the Fisher Vector technique, which combines local and global information of several local feature descriptors in order to improve the PAD generalisation capabilities, was proposed. The experimental results over unknown scenarios taken from LivDet 2011 to LivDet 2017 show that our proposal reduces the top state‐of‐the‐art average classification error rates by up to four times, thereby making it suitable in real applications demanding high security. In addition, the best single configuration achieved the best results in the LivDet 2019 competition, with an overall accuracy of 96.17%.https://doi.org/10.1049/bme2.12023authorisationcomputer crimefeature extractionfingerprint identificationimage classificationvectors |
| spellingShingle | Lázaro J. González‐Soler Marta Gomez‐Barrero Jascha Kolberg Leonardo Chang Airel Pérez‐Suárez Christoph Busch Local feature encoding for unknown presentation attack detection: An analysis of different local feature descriptors IET Biometrics authorisation computer crime feature extraction fingerprint identification image classification vectors |
| title | Local feature encoding for unknown presentation attack detection: An analysis of different local feature descriptors |
| title_full | Local feature encoding for unknown presentation attack detection: An analysis of different local feature descriptors |
| title_fullStr | Local feature encoding for unknown presentation attack detection: An analysis of different local feature descriptors |
| title_full_unstemmed | Local feature encoding for unknown presentation attack detection: An analysis of different local feature descriptors |
| title_short | Local feature encoding for unknown presentation attack detection: An analysis of different local feature descriptors |
| title_sort | local feature encoding for unknown presentation attack detection an analysis of different local feature descriptors |
| topic | authorisation computer crime feature extraction fingerprint identification image classification vectors |
| url | https://doi.org/10.1049/bme2.12023 |
| work_keys_str_mv | AT lazarojgonzalezsoler localfeatureencodingforunknownpresentationattackdetectionananalysisofdifferentlocalfeaturedescriptors AT martagomezbarrero localfeatureencodingforunknownpresentationattackdetectionananalysisofdifferentlocalfeaturedescriptors AT jaschakolberg localfeatureencodingforunknownpresentationattackdetectionananalysisofdifferentlocalfeaturedescriptors AT leonardochang localfeatureencodingforunknownpresentationattackdetectionananalysisofdifferentlocalfeaturedescriptors AT airelperezsuarez localfeatureencodingforunknownpresentationattackdetectionananalysisofdifferentlocalfeaturedescriptors AT christophbusch localfeatureencodingforunknownpresentationattackdetectionananalysisofdifferentlocalfeaturedescriptors |