An online learning network for biometric scores fusion

详细信息    查看全文

• 作者：Youngsung Kim^a ; ^{myradio@yonsei.ac.kr}Author Vitae ; Kar-Ann Toh^a ; ^{katoh@yonsei.ac.kr}Author Vitae ; Andrew Beng Jin Teoh^a ; ^{bjteoh@yonsei.ac.kr}Author Vitae ; How-Lung Eng^b ; ^{hleng@i2r.a-star.edu.sg}Author Vitae ; Wei-Yun Yau^b ; ^{wyyau@i2r.astar.edu.sg}Author Vitae
• 关键词：Multibiometrics ; Score level fusion ; Error rate ; Online learning ; Pattern classification ; Extreme learning machine (ELM)
• 刊名：Neurocomputing
• 出版年：2013
• 出版时间：15 February, 2013
• 年：2013
• 卷：102
• 期：Complete
• 页码：65-77
• 全文大小：777 K

文摘

In design of a multibiometric system, a major concern is the learning cost in terms of computation complexity and memory usage due to large data size. In this paper, we propose an online learning network to circumvent the computational problem. Although conventional online learning algorithms can be adopted, their optimization of the fitting distance residuals does not meet the actual classification error requirement. A direct optimization to the classification performance is thus desired. Since the proposed classification-based formulation involves a class-specific weight which varies according to the total number of genuine-users and imposters, an online learning formulation becomes non-trivial. Extensive empirical evaluations on publicly available data sets show promising potential of the proposed method in terms of fusion verification accuracy and computational cost.