CASIA OpenIR  > 毕业生  > 博士学位论文
指纹匹配算法研究及应用
其他题名Fingerprint Matching Algorithm and Its Application
漆进
学位类型工学博士
导师王阳生
2005-04-01
学位授予单位中国科学院研究生院
学位授予地点中国科学院自动化研究所
学位专业模式识别与智能系统
关键词生物认证 指纹 细节特征 方向场 变换 匹配 Biometric Authentication Fingerprint Minutiae Feature Orientation Field
摘要近年来,自动身份认证技术成为了生产生活中的一项迫切需要的技术,其中生物特征认证技术获得了全世界的广泛关注,因其具有较高的可靠性,吸引了大批的科研人员和有实力的知名企业从事该项技术的研究和相关产品的开发。 作为生物识别技术的主流技术—指纹识别技术,得到了业界的深入研究并获得了广泛的应用。但是困扰指纹识别精度和速度的主要因素是:指纹图像的质量、特征的可靠性、匹配算法的性能。由于指纹图像的质量具有不可控性,所以对特征提取算法和匹配算法的设计是一项具有挑战性的工作。虽然人们对匹配算法进行了深入的研究,但是现有算法还不能完全满足实际需要。当今主流的指纹识别算法是基于细节点的匹配算法,这是一个有名的点模式匹配难题。 本文对指纹匹配算法进行了深入研究,创造性地提出了几种新颖的匹配算法,并做了实验,进一步分析了匹配算法的未来走向。本文的主要创造性贡献在于: 1) 创造性地提出了一种新的基于三角形框架的非校准细节点匹配方法。该算法充分利用了三角形框架的抗弹性形变性质来克服弹性形变对指纹匹配算法的影响。与常规方法不同的是,该算法不需要指纹校准步骤,因而具有较强的鲁棒性。 2) 首次提出了一种新的结合指纹方向场的细节点表示方法,并成功应用到指纹匹配算法设计中。由于巧妙地将方向场宏观信息用来描述细节点,所以该方法较好地克服了通常的仅使用细节点信息的匹配算法的局限性。实验结果表明该方法优于常规方法。 3) 创造性地设计了一种新的细节点局部结构,该结构利用了局部细节点和全局方向场,并提出了一种新的基于该结构的指纹匹配方法。由于该方法充分利用了全局方向场和邻近细节点来描述每个细节点,所以获得了较好的实验结果。 4) 首次提出了指纹级联匹配的概念,并给出了级联匹配算法设计的统一框架,提出了一种具体的指纹级联匹配算法。该算法可以合理地将多个匹配算法级联,从而形成一个更为有效的联合匹配算法。实验结果表明级联匹配算法优于单个匹配算法。
其他摘要In recent years, automatic identification technique has been an emerging approach in real life. Especially, biometric authentication has drawn much attention. Due to its strong reliability, many modern approaches have been proposed by researchers and many biometric-related products have been developed. Fingerprint identification method has been researched and applied widely as a major technique in biometric domain. But the factors limiting the performance of fingerprint verification system mainly include fingerprint image quality, reliability of fingerprint minutiae, and the performance of fingerprint matching methods. Due to the uncontrollability of fingerprint image quality, the performance of whole fingerprint authentication system is mainly determined by the minutiae extraction algorithm and the fingerprint matching methods. Although fingerprint matching methods have been explored deeply, current matching algorithms can not still satisfy the real need completely. Most of current fingerprint matching schemes are based on minutiae. It is a well-known point pattern matching problem. This paper focuses on the problem and proposes several novel matching methods. We implemented them and demonstrated their effectiveness. Main innovative contributions to fingerprint matching in our paper are as follows: 1) Proposes a novel fingerprint matching algorithm based on triangle frameworks. The algorithm utilizes the distortion-tolerant triangle frameworks to deal with the nonlinear warping when placing fingers onto the sensor’s surface. It is noted that the normal fingerprint registration step is not necessary in the matching method. 2) Innovatively give a minutia representation scheme combing orientation field estimated form fingerprint images and apply it to fingerprint matching algorithm successfully. Due to the adoption of fingerprint global orientation information in the algorithm, our algorithm works better than those fingerprint matching methods only based on minutia information. 3) Proposes a novel minutia local structure which makes use of neighboring minutiae and global orientation fields. A new fingerprint matching technique based on our proposed structure is given. Because the matching algorithm uses more rich information including neighboring minutiae and orientation field, it gets better experimental results than some matching methods used only minutiae information or orientation information. 4) Firstly gives a new conception called “fingerprint cascading match” and proposes a general strategy for fingerprint cascading match. A specific fingerprint cascading matching algorithm is given. The algorithm can cascade several matching methods to attain a more effective matching approach. The experimental results show the better performance of cascading algorithm than single algorithm.
馆藏号XWLW947
其他标识符2002
语种中文
文献类型学位论文
条目标识符http://ir.ia.ac.cn/handle/173211/5834
专题毕业生_博士学位论文
推荐引用方式
GB/T 7714
漆进. 指纹匹配算法研究及应用[D]. 中国科学院自动化研究所. 中国科学院研究生院,2005.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[漆进]的文章
百度学术
百度学术中相似的文章
[漆进]的文章
必应学术
必应学术中相似的文章
[漆进]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。