基于独立成分分析和核向量机的虹膜识别方法

Iris recognition based on independent component analysis and core vector machines

针对虹膜识别过程中的特征提取及识别问题,提出了用独立成分分析提取虹膜特征,用核向量机进行识别的方法。从采集到的人眼图像中定位虹膜,并对其进行归一化处理和图像增强处理。用独立成分分析提取统计独立的特征,通过选择合适的特征个数可以达到较高的识别准确率。在得到虹膜特征编码后,用核向量机进行分类判决,核向量机是一种适合大规模数据集的快速支持向量机训练算法,并将结果与支持向量机的分类结果进行了对比。实验结果表明了该方法的可行性和有效性。

To solve the feature extraction problem and recognition problem in the process of iris recognition, an algorithm is proposed, which adopts independent component analysis to extract iris feature and core vector machines to recognize. Normalization and image enhancement is used to process the iris position which is located in the eye images. Independent component analysis is used to extract statistical independent feature and a good result will be received by selecting right feature numbers. The core vector machine is used to classify the iris feature and it can handle large data sets more quickly by compared to support vector machines. Experimental results show that the algorithm is feasible and suitable for iris recognition.