An Approach of SVM-Based Iris Recognition for Embedded System
Support Vector Machine (SVM) is a promising classification method with solid mathematical foundations. In this paper, we develop an Iris recognition system using SVM to classify the acquired features series. Even though the SVM outperforms most other classifiers, it works slowly, which may hinder its application in embedded system, where usually the resources are limited. To make the SVM more applicable in embedded system, we make several optimizations, including active learning, kernel selection and negative samples reuse. Experimental data shows that the method presented is amenable:the speed is 33.4 times faster and the correct recognition rate is almost the same as the basic SVM. This work makes iris recognition more feasible in embedded system. Also, the optimized SVM can be widely applied in other similar fields.
Hongying Gu Yueting Zhuang Yunhe Pan Bo Chen
Institute of Artificial Intelligence, Zhejiang University, 310027, Hangzhou, P.R.China Software College, Zhejiang University of Technology, 310032, Hangzhou, P.R.China
国际会议
首届嵌入式软件与系统国际会议(Proceedings of the First International Conference on Embedded Software and System)
杭州
英文
61-67
2004-12-09（万方平台首次上网日期，不代表论文的发表时间）