| 基于独立成分分析和核向量机的虹膜识别方法 |
| |
| 引用本文： | 程国建,彭中亚,王莹.基于独立成分分析和核向量机的虹膜识别方法[J].计算机工程与设计,2010,31(5). |
| |
| 作者姓名： | 程国建 彭中亚 王莹 |
| |
| 作者单位： | 1. 西安石油大学计算机学院,陕西,西安,710065
2. 中国石油东方地球物理公司信息技术中心,北京,100007 |
| |
| 基金项目： | 国家自然科学基金项目 |
| |
| 摘 要： | 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.
|
| 关 键 词： | 虹膜识别 独立成分分析 核向量机 支持向量机 最小包围球 |
Iris recognition based on independent component analysis and core vector machines |
| |
| CHENG Guo-jian,PENG Zhong-ya,WANG Ying.Iris recognition based on independent component analysis and core vector machines[J].Computer Engineering and Design,2010,31(5). |
| |
| Authors: | CHENG Guo-jian PENG Zhong-ya WANG Ying |
| |
| Affiliation: | CHENG Guo-jian1,PENG Zhong-ya1,WANG Ying2 (1. School of Computer Science,Xi\'an Shiyou University,Xi\'an 710065,China,2. Center for Information Technology,Bureau of Geophysical Prospecting,Beijing 100007,China) |
| |
| Abstract: | 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 en-hancement is used to process the iris position which is located in the eye images. Independent component analysis is used to extract stati-stical independent feature and a good result will be received by selecting right feature numbers. The core vector m... |
| |
| Keywords: | iris recognition independent component analysis core vector machines support vector machines minimum enclosing ball |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
