用CNN与小波滤波结合提升指纹识别准确率至94%。

Fingerprint recognition systems stand as pillars in the realm of biometric authentication, providing indispensable security measures across various domains. This study investigates integrating Convolutional Neural Networks (CNNs) with Gabor filters to improve fingerprint recognition accuracy and robustness. Leveraging a diverse dataset sourced from the Sokoto Coventry Fingerprint Dataset, our experiments meticulously evaluate the efficacy of different classification algorithms. Our findings underscore the supremacy of CNN-based approaches, boasting an impressive overall accuracy of 94\%. Furthermore, the amalgamation of Gabor filters with CNN architectures unveils promising strides in discerning altered fingerprints, illuminating new pathways for enhancing biometric authentication systems. While the CNN-Gabor fusion showcases commendable performance, our exploration of hybrid approaches combining multiple classifiers reveals nuanced outcomes. Despite these mixed results, our study illuminates the transformative potential of deep learning methodologies in reshaping the landscape of fingerprint recognition. Through rigorous experimentation and insightful analysis, this research not only contributes to advancing biometric authentication technologies but also sheds light on the intricate interplay between traditional feature extraction methods and cutting-edge deep learning architectures. These findings offer actionable insights for optimizing fingerprint recognition systems for real-world deployment, paving the way for enhanced security and reliability in diverse applications.