摘要
为了提高虹膜识别的准确率,提出了一种新的基于特征选择的虹膜识别方法。在虹膜的定位上采用了弹性模板的方法,对虹膜图像进行有效定位。针对虹膜图像的纹理分布特点,采用了多尺度Gabor滤波器对虹膜的不同纹理区域进行有针对性的特征提取;然后利用遗传算法和粒子群优化算法进行特征选择,去除特征向量中的冗余信息;最后利用SVM分类模型进行虹膜的识别。为了检验方法的有效性,在CASIA虹膜数据库上进行验证,实验结果表明该方法具有较高的识别精准度。
In order to improve the accuracy of iris recognition,a novel iris recognition method based on feature selection is proposed. Using the elastic template for locating efficiently iris image. Aiming at texture distribution characteristics of iris image,multi- scale Gabor filter is used to extract feature in different texture region of iris. Then,use genetic algorithm and particle swarm optimization algorithm for feature selection,removal of redundant information in the feature vector. Finally,the SVM classification model is used for iris recognition.In order to test the validity of the method,the method is verified in the CASIA iris database,the experimental results showthat this method has high recognition accuracy.
出处
《计算机技术与发展》
2014年第12期96-100,共5页
Computer Technology and Development
基金
辽宁省社会科学规划基金项目(L13BXW006)
辽宁省社科联项目(2010lslktjyx-03)
关键词
特征选择
最优化
虹膜识别
边界定位
归一化
feature selection
optimization
iris recognition
boundary localization
normalization
