Late Deep Fusion of Color Spaces to Enhance Finger Photo Presentation Attack Detection in Smartphones
Finger photo recognition represents a promising touchless technology that offers portable and hygienic authentication solutions in smartphones, eliminating physical contact. Public spaces, such as banks and staff-less stores, benefit from contactless authentication considering the current public hea...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/22/11409 |
| _version_ | 1797466063796961280 |
|---|---|
| author | Emanuela Marasco Anudeep Vurity |
| author_facet | Emanuela Marasco Anudeep Vurity |
| author_sort | Emanuela Marasco |
| collection | DOAJ |
| description | Finger photo recognition represents a promising touchless technology that offers portable and hygienic authentication solutions in smartphones, eliminating physical contact. Public spaces, such as banks and staff-less stores, benefit from contactless authentication considering the current public health sphere. The user captures the image of their own finger by using the camera integrated in a mobile device. Although recent research has pushed boundaries of finger photo matching, the security of this biometric methodology still represents a concern. Existing systems have been proven to be vulnerable to print attacks by presenting a color paper-printout in front of the camera and photo attacks that consist of displaying the original image in front of the capturing device. This paper aims to improve the performance of finger photo presentation attack detection (PAD) algorithms by investigating deep fusion strategies to combine deep representations obtained from different color spaces. In this work, spoofness is described by combining different color models. The proposed framework integrates multiple convolutional neural networks (CNNs), each trained using patches extracted from a specific color model and centered around minutiae points. Experiments were carried out on a publicly available database of spoofed finger photos obtained from the IIITD Smartphone Finger photo Database with spoof data, including printouts and various display attacks. The results show that deep fusion of the best color models improved the robustness of the PAD system and competed with the state-of-the-art. |
| first_indexed | 2024-03-09T18:30:46Z |
| format | Article |
| id | doaj.art-e860716299494845a483b6b42a6a957b |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T18:30:46Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e860716299494845a483b6b42a6a957b2023-11-24T07:34:53ZengMDPI AGApplied Sciences2076-34172022-11-0112221140910.3390/app122211409Late Deep Fusion of Color Spaces to Enhance Finger Photo Presentation Attack Detection in SmartphonesEmanuela Marasco0Anudeep Vurity1Center for Secure Information Systems, George Mason University, Fairfax, VA 22030, USACenter for Secure Information Systems, George Mason University, Fairfax, VA 22030, USAFinger photo recognition represents a promising touchless technology that offers portable and hygienic authentication solutions in smartphones, eliminating physical contact. Public spaces, such as banks and staff-less stores, benefit from contactless authentication considering the current public health sphere. The user captures the image of their own finger by using the camera integrated in a mobile device. Although recent research has pushed boundaries of finger photo matching, the security of this biometric methodology still represents a concern. Existing systems have been proven to be vulnerable to print attacks by presenting a color paper-printout in front of the camera and photo attacks that consist of displaying the original image in front of the capturing device. This paper aims to improve the performance of finger photo presentation attack detection (PAD) algorithms by investigating deep fusion strategies to combine deep representations obtained from different color spaces. In this work, spoofness is described by combining different color models. The proposed framework integrates multiple convolutional neural networks (CNNs), each trained using patches extracted from a specific color model and centered around minutiae points. Experiments were carried out on a publicly available database of spoofed finger photos obtained from the IIITD Smartphone Finger photo Database with spoof data, including printouts and various display attacks. The results show that deep fusion of the best color models improved the robustness of the PAD system and competed with the state-of-the-art.https://www.mdpi.com/2076-3417/12/22/11409finger photo presentation attack detectioncolor spacesdeep fusion |
| spellingShingle | Emanuela Marasco Anudeep Vurity Late Deep Fusion of Color Spaces to Enhance Finger Photo Presentation Attack Detection in Smartphones Applied Sciences finger photo presentation attack detection color spaces deep fusion |
| title | Late Deep Fusion of Color Spaces to Enhance Finger Photo Presentation Attack Detection in Smartphones |
| title_full | Late Deep Fusion of Color Spaces to Enhance Finger Photo Presentation Attack Detection in Smartphones |
| title_fullStr | Late Deep Fusion of Color Spaces to Enhance Finger Photo Presentation Attack Detection in Smartphones |
| title_full_unstemmed | Late Deep Fusion of Color Spaces to Enhance Finger Photo Presentation Attack Detection in Smartphones |
| title_short | Late Deep Fusion of Color Spaces to Enhance Finger Photo Presentation Attack Detection in Smartphones |
| title_sort | late deep fusion of color spaces to enhance finger photo presentation attack detection in smartphones |
| topic | finger photo presentation attack detection color spaces deep fusion |
| url | https://www.mdpi.com/2076-3417/12/22/11409 |
| work_keys_str_mv | AT emanuelamarasco latedeepfusionofcolorspacestoenhancefingerphotopresentationattackdetectioninsmartphones AT anudeepvurity latedeepfusionofcolorspacestoenhancefingerphotopresentationattackdetectioninsmartphones |