Scholarlink

<p>Recent advancements have highlighted the effectiveness of combining deep learn-ing models with attention mechanisms for fingerprint recognition. However, existing approaches often struggle to achieve high accuracy when processing low-quality or latent fingerprint images, as they fail to capture important critical ridge and valley patterns. To address this limitation, we propose a Multi-head Self-Attention based EfficientNetB4 model with advanced preprocessing techniques for enhanced fingerprint matching, leveraging the efficient feature extraction capability of EfficientNet. The proposed approach consists of three key components: advanced preprocessing techniques, feature extraction using EfficientNet, and a Multi-Head Self-Attention (MHSA) mechanism to enhance feature representation. Preprocessing steps include image augmentation to increase data diversity, Contrast Limited Adaptive Histogram Equalization for improving contrast, and Enhanced Super-Resolution Generative Adversarial Network for super-resolution enhancement, ensuring the clarity of fingerprint patterns even in noisy or distorted images. EfficientNet processes these preprocessed images to extract spatial and structural features, while the MHSA mechanism assigns varying importance to different features, enabling the network to focus on key fingerprint details. Hyperparameter tuning was employed to optimize model performance and ensure adaptability across diverse datasets. To validate the performance of ENET-EMHSA, experiments were conducted on benchmark datasets, including FVC 2000, FVC 2002, and FVC 2004. The proposed ENET-EMHSA model demonstrated state-of-the-art accuracy, achieving 99.57%, 99.72%, and 99.86% on the respective datasets, while maintaining a notably lower Equal Error Rate (EER) across all evaluations, thereby outperforming existing fingerprint matching methods. The ENET-EMHSA demonstrates the capability to differentiate fine-grained fingerprint patterns, improving the accuracy and robustness of biometric identification systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhanced fingerprint matching using convolutional neural network and MultiHead self attention

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月20日

查看全文
  • Syeda Fatima Zohra Sajjad,
  • Bushra Zafar,
  • Nouman Ali,
  • Abdul Rehman,
  • Yazeed Yasin Ghadi,
  • Hend Khalid Alkahtani

摘要

Recent advancements have highlighted the effectiveness of combining deep learn-ing models with attention mechanisms for fingerprint recognition. However, existing approaches often struggle to achieve high accuracy when processing low-quality or latent fingerprint images, as they fail to capture important critical ridge and valley patterns. To address this limitation, we propose a Multi-head Self-Attention based EfficientNetB4 model with advanced preprocessing techniques for enhanced fingerprint matching, leveraging the efficient feature extraction capability of EfficientNet. The proposed approach consists of three key components: advanced preprocessing techniques, feature extraction using EfficientNet, and a Multi-Head Self-Attention (MHSA) mechanism to enhance feature representation. Preprocessing steps include image augmentation to increase data diversity, Contrast Limited Adaptive Histogram Equalization for improving contrast, and Enhanced Super-Resolution Generative Adversarial Network for super-resolution enhancement, ensuring the clarity of fingerprint patterns even in noisy or distorted images. EfficientNet processes these preprocessed images to extract spatial and structural features, while the MHSA mechanism assigns varying importance to different features, enabling the network to focus on key fingerprint details. Hyperparameter tuning was employed to optimize model performance and ensure adaptability across diverse datasets. To validate the performance of ENET-EMHSA, experiments were conducted on benchmark datasets, including FVC 2000, FVC 2002, and FVC 2004. The proposed ENET-EMHSA model demonstrated state-of-the-art accuracy, achieving 99.57%, 99.72%, and 99.86% on the respective datasets, while maintaining a notably lower Equal Error Rate (EER) across all evaluations, thereby outperforming existing fingerprint matching methods. The ENET-EMHSA demonstrates the capability to differentiate fine-grained fingerprint patterns, improving the accuracy and robustness of biometric identification systems.