一種利用灰階強度微分值之指紋方向場估算法

Abstract

在現今社會指紋識別技術已被廣泛應用於各種領域，包括門禁系統、法醫調查和海關管控等。然而低品質的指紋影像可能會影響指紋特徵識別的準確度。因此需要利用指紋影像增強技術來克服這個問題，比如Gabor濾波器就是最常見指紋影像增強技術，而Gabor濾波器需要可靠的方向場估算來確保影像增強的效果。在這篇論文中，我們介紹一種利用灰階強度微分值之指紋方向場估算法，並利用高斯模糊和高斯雜訊降低指紋影像品質，來檢驗所提出的演算法的準確性和可靠性。實驗結果顯示，在低品質的指紋影像中，本文所提演算法在指紋方向場估算的可靠性方面比基於梯度演算法和基於功率頻譜密度演算法更好。尤其是在有雜訊的指紋影像中，本文演算法指紋方向場估算可靠性比基於梯度演算法和基於功率頻譜密度演算法分別提高了6.46％和32.93％。

Fingerprint identification technologies are widely used for various applications, including access control systems, forensic investigations, and border security. However, low-quality fingerprint images may affect the accuracy of fingerprint identification. Therefore, fingerprint image enhancement, such as the Gabor filter, is necessary and the Gabor filter requires a reliable orientation field estimation to ensure the result of image enhancement. In this study, we introduce an orientation field estimation algorithm based on differential values of grayscale intensity and examine the accuracy and reliability of the proposed algorithm by applying it to fingerprint images processed using the Gaussian blurring and the Gaussian white noise process. The experimental results indicate that the orientation field estimation reliability of the proposed algorithm is higher than the gradient-based method and the power spectrum density-based method in low quality fingerprints. The proposed algorithm is especially useful in noisy fingerprint images, where the orientation field estimation reliability of the algorithm is 6.46% and 32.93% higher than the gradient-based method and the power spectrum density-based method, respectively.