卓越研究

本系哲學博士生陳健生榮獲IAPRICB 2006最佳論文獎亞軍

陳健生先生憑名為「用於以指紋特徵點為基礎的自動指紋辨識系統(AFVSs)的統計模型」的論文,於2006年的第二屆生物辨識技術國際會議中,榮獲摩托羅拉最佳論文獎亞軍。在生物識別技術研究中, IAPRICB 2006是個地位舉足輕重的會議。

 

陳健生先生為本系哲學博士生,由蒙耀生教授指導。論文中,陳健生先生提出了一個統計模型,該模型用於以指紋特徵點為基礎的自動指紋 辨識系統(AFVSs),籍此模型,AFVSs的辨識表現之計量可以數學方式表達。此模型有助提高評估AFVSs效率,同時亦有助AFVSs的理論分析。

 

論文摘要:

Evaluation of the reliability of an Automatic Fingerprint Verification System (AFVS) is usually performed by applying it to a fingerprint database to get the verification accuracy. However, such an evaluation process might be quite time consuming especially for big fingerprint databases. This may prolong the developing cycles of AFVSs and thus increase the cost. Also, comparison of the reliability of different AFVSs may be unfair if different fingerprint databases are used. In this paper, we propose a solution to solve these problems by creating an AFVS evaluation model which can be used for verification accuracy prediction and fair reliability comparison. Experimental results show that our model can predict the performance of a real AFVS pretty satisfactorily.

 


從左至右:
陳健生先生及美國摩托羅拉生物識別技術業務部Behnam Bavarian博士