手背靜脈影像邊緣特徵識別

Dorsal Hand Vein Image Edge Feature Recognition

詹閎傑(Hong-Jie Zhan) ； 莊尚仁(Shang-Jen Chuang) ； 黃煌初(Huang-Chu Huang) ； 李仁軍(Jen-Chun Lee)

《中正嶺學報》 47卷1期 (2018/05) Pp. 71-79

摘要

手背靜脈識別為一種新興生物認證技術，本研究主要目的在於提出一種強健、穩定且即時性的手背靜脈識別方法。我們將手背靜脈骨架化影像實施靜脈血管紋路骨架與邊緣相交點之特徵值擷取，於特徵比對階段提出動態模式樹加快比對速度，並配合最小距離分類器實施特徵識別。最後實驗結果經由效能評估後整體正確識別率為99.72%與其他識別方法比較下本識別方法更能快速進行特徵比對且具備極佳識別率，因此我們提出之手背靜脈識別對於生物認證領域上具有高度實用性。

關鍵字

手背靜脈識別 ； 生物認證 ； 動態模式樹 ； 最小距離分類器

並列摘要

With the increasing needs in security systems, vein recognition is one of the important and reliable solutions of identity security for biometrics-based identification systems. This paper presents a novel, local feature-based vein representation method based on minutiae features from skeleton images of venous networks. These minutiae features include end points and the arc lines between the two end points as measured along the boundary of the region of interest. In addition, we propose a dynamic pattern tree to accelerate matching performance and evaluate the discriminatory power of these feature points for verifying a person's identity. In a comparison with existing verification algorithms, the proposed method achieved the highest accuracy in the lowest tested matching time. Our results demonstrate the effectiveness of the proposed method as a promising approach to vein recognition. Therefore, we propose the dorsal hand vein recognition for the field of biometric authentication with high practicability rate.

並列關鍵字

dorsal hand vein recognition ； biometrics ； dynamic pattern tree ； minimum distance classifier