Optimizing Fingerprint Identification: CNNs With Raw Images Versus Handcrafted Features for Real-Time Systems
Fingerprint identification is a cornerstone in various domains such as security, forensics, and authentication. Despite progress, existing systems still face challenges with noise, database differences, and real-time speed. This study investigates the balance between accuracy and computational effic...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11037729/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849417635291201536 |
|---|---|
| author | Shaik Salma Tauheed Ahmed Garimella Ramamurthy |
| author_facet | Shaik Salma Tauheed Ahmed Garimella Ramamurthy |
| author_sort | Shaik Salma |
| collection | DOAJ |
| description | Fingerprint identification is a cornerstone in various domains such as security, forensics, and authentication. Despite progress, existing systems still face challenges with noise, database differences, and real-time speed. This study investigates the balance between accuracy and computational efficiency(thereby speed) by comparing two approaches: training a Convolutional Neural Network (CNN) with raw fingerprint images and training a CNN using handcrafted fingerprint features. Comprehensive evaluations were conducted across multiple benchmark datasets FVC2000, FVC2002, FVC2004, and NIST SD27, using both single-run and multi-run experiments. Single-run experiments assessed performance across epochs; multi-run cross-validation on FVC2000 ensured consistent and reliable results. A similarity-based matching mechanism with an optimal threshold of 0.8, determined through Receiver Operating Characteristic (ROC) curve analysis, was employed for classification. Experimental results on NVIDIA DGX A100 GPU demonstrate that CNN training with handcrafted features consistently achieves superior accuracy (99.80%) compared to CNN training with raw images approach accuracy (95.59%) on the FVC2000 dataset, while significantly reducing computation time from 1465 to 203 seconds. This performance was consistent across all experimental runs. Similar trends appeared across datasets, with handcrafted features reaching 96-99% accuracy versus 91-96% for raw images data. Statistical analyses (t-tests, ANOVA, and F-statistics) confirmed the significance of these performance differences (<inline-formula> <tex-math notation="LaTeX">${p} \lt 0.01$ </tex-math></inline-formula>) and demonstrated the model’s reliability, robustness, and consistency. This proposed method outperforms recent methods in accuracy and speed, validated by ROC, precision-recall, F1-score, and accuracy metrics in real-world scenarios. Our approach provides experimental confirmation that CNNs fed with features provide improvements in accuracy and speed of classification. |
| format | Article |
| id | doaj-art-6647972d64f9448ca28100356463ca39 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6647972d64f9448ca28100356463ca392025-08-20T03:32:42ZengIEEEIEEE Access2169-35362025-01-011310819210821110.1109/ACCESS.2025.358043811037729Optimizing Fingerprint Identification: CNNs With Raw Images Versus Handcrafted Features for Real-Time SystemsShaik Salma0https://orcid.org/0000-0002-7341-4154Tauheed Ahmed1https://orcid.org/0000-0003-0447-7343Garimella Ramamurthy2https://orcid.org/0000-0002-5669-1846Department of Computer Science and Engineering, École Centrale School of Engineering, Mahindra University, Hyderabad, Telangana, IndiaDepartment of Computer Science and Engineering, École Centrale School of Engineering, Mahindra University, Hyderabad, Telangana, IndiaDepartment of Computer Science and Engineering, École Centrale School of Engineering, Mahindra University, Hyderabad, Telangana, IndiaFingerprint identification is a cornerstone in various domains such as security, forensics, and authentication. Despite progress, existing systems still face challenges with noise, database differences, and real-time speed. This study investigates the balance between accuracy and computational efficiency(thereby speed) by comparing two approaches: training a Convolutional Neural Network (CNN) with raw fingerprint images and training a CNN using handcrafted fingerprint features. Comprehensive evaluations were conducted across multiple benchmark datasets FVC2000, FVC2002, FVC2004, and NIST SD27, using both single-run and multi-run experiments. Single-run experiments assessed performance across epochs; multi-run cross-validation on FVC2000 ensured consistent and reliable results. A similarity-based matching mechanism with an optimal threshold of 0.8, determined through Receiver Operating Characteristic (ROC) curve analysis, was employed for classification. Experimental results on NVIDIA DGX A100 GPU demonstrate that CNN training with handcrafted features consistently achieves superior accuracy (99.80%) compared to CNN training with raw images approach accuracy (95.59%) on the FVC2000 dataset, while significantly reducing computation time from 1465 to 203 seconds. This performance was consistent across all experimental runs. Similar trends appeared across datasets, with handcrafted features reaching 96-99% accuracy versus 91-96% for raw images data. Statistical analyses (t-tests, ANOVA, and F-statistics) confirmed the significance of these performance differences (<inline-formula> <tex-math notation="LaTeX">${p} \lt 0.01$ </tex-math></inline-formula>) and demonstrated the model’s reliability, robustness, and consistency. This proposed method outperforms recent methods in accuracy and speed, validated by ROC, precision-recall, F1-score, and accuracy metrics in real-world scenarios. Our approach provides experimental confirmation that CNNs fed with features provide improvements in accuracy and speed of classification.https://ieeexplore.ieee.org/document/11037729/Convolutional neural networkhandcrafted feature vectorsgenuine matchingimpostor matchingminutiae-based features |
| spellingShingle | Shaik Salma Tauheed Ahmed Garimella Ramamurthy Optimizing Fingerprint Identification: CNNs With Raw Images Versus Handcrafted Features for Real-Time Systems IEEE Access Convolutional neural network handcrafted feature vectors genuine matching impostor matching minutiae-based features |
| title | Optimizing Fingerprint Identification: CNNs With Raw Images Versus Handcrafted Features for Real-Time Systems |
| title_full | Optimizing Fingerprint Identification: CNNs With Raw Images Versus Handcrafted Features for Real-Time Systems |
| title_fullStr | Optimizing Fingerprint Identification: CNNs With Raw Images Versus Handcrafted Features for Real-Time Systems |
| title_full_unstemmed | Optimizing Fingerprint Identification: CNNs With Raw Images Versus Handcrafted Features for Real-Time Systems |
| title_short | Optimizing Fingerprint Identification: CNNs With Raw Images Versus Handcrafted Features for Real-Time Systems |
| title_sort | optimizing fingerprint identification cnns with raw images versus handcrafted features for real time systems |
| topic | Convolutional neural network handcrafted feature vectors genuine matching impostor matching minutiae-based features |
| url | https://ieeexplore.ieee.org/document/11037729/ |
| work_keys_str_mv | AT shaiksalma optimizingfingerprintidentificationcnnswithrawimagesversushandcraftedfeaturesforrealtimesystems AT tauheedahmed optimizingfingerprintidentificationcnnswithrawimagesversushandcraftedfeaturesforrealtimesystems AT garimellaramamurthy optimizingfingerprintidentificationcnnswithrawimagesversushandcraftedfeaturesforrealtimesystems |