Fast Iris Detection and Localization Algorithm Based on AdaBoost Algorithm and Neural Networks
Zhong Bo Zhang, Si Liang Ma, Ping Zuo, Jie Ma · 2006
In this paper, we propose an iris detection and localization method based on AdaBoost algorithm and neural networks with local interconnection structures to overcome the limits in the current iris detection and localization algorithms. It has three features: Firstly, according to the features of the iris image, we design a set of local interconnection neural networks iris classifiers with different receptive fields and different complexity. Secondly, we use AdaBoost algorithm to integrate neural networks classifiers to generate a chief classifier with powerful iris detection ability. Thirdly, cascade connection structure is applied to increase the detection speed. Experimental results show that this algorithm has very high detection accuracy and speed. It can solve the iris detection and localization problems efficiently in the case of with large face region and cataract patients