Performance Evaluation of Image Enhancement Techniques on Transfer Learning for Touchless Fingerprint Recognition

2024-11-12

2024 7th International Conference on Signal Processing and Information Security (ICSPIS)

AI Summary

To address poor image quality and weak model generalization in contactless fingerprint recognition, this study systematically investigates the impact of image enhancement on transfer learning performance. Using the IIT-Bombay contact/contactless fingerprint database, we employ pretrained models—including VGG-16, VGG-19, Inception-V3, and ResNet-50—combined with preprocessing techniques such as contrast enhancement, denoising, and sharpening to establish an enhancement–transfer co-optimization framework. For the first time, quantitative experiments demonstrate that image enhancement acts as an “indirect regularization” mechanism, significantly improving the robustness and recognition accuracy of transfer learning. Specifically, VGG-16 achieves 98% training accuracy and 93% test accuracy on enhanced images—exceeding the unenhanced baseline by over seven percentage points. These results validate both the effectiveness and broad applicability of the proposed paradigm.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Adversarial Attacks & Robustness
• Search and Optimization: Learning to Search

Application Category

• Security and Privacy: Privacy-enhancing technologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Fingerprint recognition remains one of the most reliable biometric technologies due to its high accuracy and uniqueness. Traditional systems rely on contact-based scanners, which are prone to issues such as image degradation from surface contamination and inconsistent user interaction. To address these limitations, contactless fingerprint recognition has emerged as a promising alternative, providing non-intrusive and hygienic authentication. This study evaluates the impact of image enhancement techniques on the performance of pre-trained deep learning models using transfer learning for touchless fingerprint recognition. The IIT-Bombay Touchless and Touch-Based Fingerprint Database, containing data from 200 subjects, was employed to test the performance of deep learning architectures such as VGG-16, VGG19, Inception-V3, and ResNet-50. Experimental results reveal that transfer learning methods with fingerprint image enhancement (indirect method) significantly outperform those without enhancement (direct method). Specifically, VGG-16 achieved an accuracy of 98% in training and 93% in testing when using the enhanced images, demonstrating superior performance compared to the direct method. This paper provides a detailed comparison of the effectiveness of image enhancement in improving the accuracy of transfer learning models for touchless fingerprint recognition, offering key insights for developing more efficient biometric systems.

Problem

• Evaluates image enhancement impact on touchless fingerprint recognition
• Compares transfer learning models with and without image enhancement
• Uses IIT-Bombay database for deep learning model performance testing

Innovation

• Transfer learning for touchless fingerprint recognition
• Image enhancement boosts deep learning accuracy
• VGG-16 achieves 98% training accuracy