A Fast Method for Iris Image Quality Assessment

快速紅膜影像質量評價方法

蘇有(Yu Su)

《中華印刷科技年報》 2014 (2014/04) Pp. 129-137

摘要

現今安全系統需求日益增加，在以生物特徵為基礎的識別系統中，虹膜辨識方法為其最重要的解決方案之一。然而，並非設備所截取的虹膜影像均有足夠的銳利清晰度而得以辨識，因此，虹膜影像的品質將相當程度的影響虹膜辨識的準確度。而虹膜影像影造成虹膜辨識困難的因素有：離焦模糊，動態模糊，眼瞼閉合及睫毛遮擋等。本文中提出了一種快速的方法來完成虹膜影像質量評價，進而可從一影像序列中挑出具有較高品質的虹膜影像。文中實驗所用的虹膜影像為CASIA及UBIRIS數據庫所提供的公開免費影像，而從實驗結果顯示，文中所提出的評價系統可確實反映出每張虹膜影像的實際品質進而顯著提升虹膜影像辨識系統的整體效能。

關鍵字

虹膜影像質量評價

並列摘要

With the increasing needs in security systems, iris recognition is relied as one of the most important solutions for biometrics-based identification systems. However, not all of the iris images acquired from the device are clear and sharp enough for recognition. Thus, the quality of iris images is important to the accuracy of iris recognition. Sometimes these images are not good enough due to a variety of factors: defocus blur, motion blur, eyelid occlusion and eyelash occlusion. This paper presents a fast approach for iris image quality assessment which can select the high quality iris images from the image sequences. Experiments used the public and free iris images taken from the CASIA and UBIRIS databases. The results showed that this evaluation system actually reflected the real quality of iris images and significantly improved the overall performance of the iris recognition system.

並列關鍵字

iris image quality assessment

參考文獻

Yanushkevich, S. N.(2006).Synthetic Biometrics: A Survey.International Joint Conference on Neural Networks.(International Joint Conference on Neural Networks).

Miller, B.(1994).Vital Signs of Identity.IEEE Spectrum.31(2),22-30.

International Biometric Group(2005).Independent Testing of Iris Recognition Technology: Final Report.,未出版.

Ma, L.,Tan, T.,Wang, Y.,Zhang, D.(2003).Personal Identification Based on Iris Texture Analysis.IEEE Transactions on Pattern Analysis and Machine Intelligence.25(12),1519-1533.

Daugman, J.(2004).How Iris Recognition Works.IEEE Transactions on Circuits and Systems for Video Technology.14(1),21-30.