一种安全快速的虹膜识别方法

Safe and Fast Iris Identification Method

虹膜识别技术作为一种生物特征识别手段,具有唯一性、稳定性等优点,从而成为当前模式识别和机器学习领域的一个研究热点.目前的虹膜识别方法多数是采用在图像上提取特征点,并将特征点编码为固定长度的特征数据用于匹配的方式,这种方式的特征提取算法复杂,计算量大,而且使虹膜识别系统易受到攻击.为了提高虹膜识别系统的安全性和识别速度,本文提出一种安全快速的虹膜识别方法,在活体虹膜上进行直接匹配,该算法具有识别速度快,准确率高的特点,经实验验证,识别时间为30.1ms,识别率达到98.86%,与经典算法相比较,算法简单,安全性高,具有放缩,平移、旋转不变性.

Iris recognition, as a biometric technology, has great mathematical advantages, such as variability, stability and security, thus becoming a hot topic in pattern recognition and machine learning research area. How to extract and match the feature of Iris is the key problem in iris recognition. Nowadays, most of the iris identification methods are utilizing the strategy that extracts the feature points in the iris image firstly and then encodes these points into a certain length feature data for matching. But this strategy can make the iris identification system fragile to be attack. In order to improve the security and speed of iris identification systems, an iris identification method based on normalized correlation is proposed. This method established on the living specimen iris direct match, the security is higher, and it does not need the feature extracting. Experimental results demonstrate that the accuracy is 98. 86% and the speed is 30. 1 ms. This method has the ability of translation, rotation, and scale invariant, has high accuracy and speed.