在本論文的研究中，我們提出一個以小波轉換及Teager能量運算子 (Teager energy operator) 做指紋影像強化的方法。首先，我們對輸入的灰階指紋影像以指定的平均值及變異數作正規化 (normalization)，以改善影像中指紋凹凸紋路對比不足的問題。其次，我們根據影像中指紋紋路的區域方向性，估算並找出紋路走向圖 (orientation image)，以作為下一步有向濾波 (directional filtering) 的根據。接著我們對影像做小波轉換，利用小波轉換的多重解析度特性，分別針對不同解析度的高頻係數，以小波收縮 (wavelet shrinkage) 去除雜訊，再利用之前求得的紋路走向圖，以有向Teager能量運算子作用於低頻係數以強化影像中指紋凹凸紋路的清晰度。最後，我們再做小波反轉換，以求得經強化過後的指紋影像，做自動指紋辨識 (automated fingerprint identification)。在實驗中，我們使用正確性指數 (goodness index) 及指紋辨識系統來評估本研究所提出方法的效能。根據實驗結果，本研究所提出的指紋影像強化方法，確實可以有效強化指紋影像的品質，並做為後續自動指紋辨識系統之用。 Biometric recognition refers to the use of distinctive physiological and behavioral characteristics (e.g., fingerprints, face, hand geometry, iris, gait, and signature) called biometric identifiers or simply biometrics. Among these biometric identifiers, fingerprints are the oldest and most widely used form. Most automatic recognition systems are based on minutiae matching, hence, a critical step in such systems is to automatically and reliably extract minutiae from the fingerprint images. However, the performance of a minutiae extraction algorithm heavily relies on the quality of the fingerprint images. In order to ensure well performance of the ridge and minutiae extraction algorithms in poor quality fingerprint images, an enhancement algorithm is necessary to improve the clarity of the ridge structure. In this thesis, we propose a fingerprint enhancement algorithm based on the Teager energy operator in the wavelet domain to improve the clarity of ridge and valley structures of fingerprint images. We have evaluated the performance of the image enhancement algorithm using the goodness index of the extracted minutiae and the accuracy of a fingerprint identification system. Experimental results show that the proposed enhancement algorithm really improves both the goodness index and the verification accuracy.
