A Hybrid Deep Learning Approach for Secure Biometric Authentication Using Fingerprint Data
Despite significant advancements in fingerprint-based authentication, existing models still suffer from challenges such as high false acceptance and rejection rates, computational inefficiency, and vulnerability to spoofing attacks. Addressing these limitations is crucial for ensuring reliable biome...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/14/5/178 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850257897921970176 |
|---|---|
| author | Abdulrahman Hussian Foud Murshed Mohammed Nasser Alandoli Ghalib Aljafari |
| author_facet | Abdulrahman Hussian Foud Murshed Mohammed Nasser Alandoli Ghalib Aljafari |
| author_sort | Abdulrahman Hussian |
| collection | DOAJ |
| description | Despite significant advancements in fingerprint-based authentication, existing models still suffer from challenges such as high false acceptance and rejection rates, computational inefficiency, and vulnerability to spoofing attacks. Addressing these limitations is crucial for ensuring reliable biometric security in real-world applications, including law enforcement, financial transactions, and border security. This study proposes a hybrid deep learning approach that integrates Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks to enhance fingerprint authentication accuracy and robustness. The CNN component efficiently extracts intricate fingerprint patterns, while the LSTM module captures sequential dependencies to refine feature representation. The proposed model achieves a classification accuracy of 99.42%, reducing the false acceptance rate (FAR) to 0.31% and the false rejection rate (FRR) to 0.27%, demonstrating a 12% improvement over traditional CNN-based models. Additionally, the optimized architecture reduces computational overheads, ensuring faster processing suitable for real-time authentication systems. These findings highlight the superiority of hybrid deep learning techniques in biometric security by providing a quantifiable enhancement in both accuracy and efficiency. This research contributes to the advancement of secure, adaptive, and high-performance fingerprint authentication systems, bridging the gap between theoretical advancements and real-world applications. |
| format | Article |
| id | doaj-art-9d899da149a244718cd60db9f1ba5d28 |
| institution | OA Journals |
| issn | 2073-431X |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj-art-9d899da149a244718cd60db9f1ba5d282025-08-20T01:56:17ZengMDPI AGComputers2073-431X2025-05-0114517810.3390/computers14050178A Hybrid Deep Learning Approach for Secure Biometric Authentication Using Fingerprint DataAbdulrahman Hussian0Foud Murshed1Mohammed Nasser Alandoli2Ghalib Aljafari3Department of Computer Science, Faculty of Computer and Information Technology, Sana’a University, Sanaa 37444, YemenDepartment of Computer Science, Faculty of Computer and Information Technology, Sana’a University, Sanaa 37444, YemenFaculty of Computing, Multimedia University, Cyberjaya 63100, MalaysiaDepartment of Computer Science, Faculty of Computer and Information Technology, Sana’a University, Sanaa 37444, YemenDespite significant advancements in fingerprint-based authentication, existing models still suffer from challenges such as high false acceptance and rejection rates, computational inefficiency, and vulnerability to spoofing attacks. Addressing these limitations is crucial for ensuring reliable biometric security in real-world applications, including law enforcement, financial transactions, and border security. This study proposes a hybrid deep learning approach that integrates Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks to enhance fingerprint authentication accuracy and robustness. The CNN component efficiently extracts intricate fingerprint patterns, while the LSTM module captures sequential dependencies to refine feature representation. The proposed model achieves a classification accuracy of 99.42%, reducing the false acceptance rate (FAR) to 0.31% and the false rejection rate (FRR) to 0.27%, demonstrating a 12% improvement over traditional CNN-based models. Additionally, the optimized architecture reduces computational overheads, ensuring faster processing suitable for real-time authentication systems. These findings highlight the superiority of hybrid deep learning techniques in biometric security by providing a quantifiable enhancement in both accuracy and efficiency. This research contributes to the advancement of secure, adaptive, and high-performance fingerprint authentication systems, bridging the gap between theoretical advancements and real-world applications.https://www.mdpi.com/2073-431X/14/5/178deep learninghybrid modelCNNLSTMfingerprint recognitionbiometric security |
| spellingShingle | Abdulrahman Hussian Foud Murshed Mohammed Nasser Alandoli Ghalib Aljafari A Hybrid Deep Learning Approach for Secure Biometric Authentication Using Fingerprint Data Computers deep learning hybrid model CNN LSTM fingerprint recognition biometric security |
| title | A Hybrid Deep Learning Approach for Secure Biometric Authentication Using Fingerprint Data |
| title_full | A Hybrid Deep Learning Approach for Secure Biometric Authentication Using Fingerprint Data |
| title_fullStr | A Hybrid Deep Learning Approach for Secure Biometric Authentication Using Fingerprint Data |
| title_full_unstemmed | A Hybrid Deep Learning Approach for Secure Biometric Authentication Using Fingerprint Data |
| title_short | A Hybrid Deep Learning Approach for Secure Biometric Authentication Using Fingerprint Data |
| title_sort | hybrid deep learning approach for secure biometric authentication using fingerprint data |
| topic | deep learning hybrid model CNN LSTM fingerprint recognition biometric security |
| url | https://www.mdpi.com/2073-431X/14/5/178 |
| work_keys_str_mv | AT abdulrahmanhussian ahybriddeeplearningapproachforsecurebiometricauthenticationusingfingerprintdata AT foudmurshed ahybriddeeplearningapproachforsecurebiometricauthenticationusingfingerprintdata AT mohammednasseralandoli ahybriddeeplearningapproachforsecurebiometricauthenticationusingfingerprintdata AT ghalibaljafari ahybriddeeplearningapproachforsecurebiometricauthenticationusingfingerprintdata AT abdulrahmanhussian hybriddeeplearningapproachforsecurebiometricauthenticationusingfingerprintdata AT foudmurshed hybriddeeplearningapproachforsecurebiometricauthenticationusingfingerprintdata AT mohammednasseralandoli hybriddeeplearningapproachforsecurebiometricauthenticationusingfingerprintdata AT ghalibaljafari hybriddeeplearningapproachforsecurebiometricauthenticationusingfingerprintdata |