全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

改进的指纹细节特征提取算法

DOI: 10.11834/jig.2002012372

Keywords: 指纹细节特征,提取算法,纹线修复,图象细化,自动识别,图象处理

Full-Text   Cite this paper   Add to My Lib

Abstract:

指纹细节特征(minutiae)提取是指纹自动识别的核心技术之一,常规的指纹细节特征提取算法需要先采用纹线跟踪的方法对细化后的指纹图象进行纹线修复,然后再实现细节特征提取,纹线修复不仅步骤繁琐,而且比较耗时,针对这一问题,提出了一种改进的指纹细节特征提取算法,该算法首先在细化后的指纹图象上直接提取原始细节特征点集,然后分析图象中存在的各类噪声及其特点,总结伪特征点的分布规律,最后,结合局部纹线方向信息,针对不同的噪声,采用针对性的算法,将各类噪声引起的伪特征点分别予以删除,最终保留下来的特征点集即视为真正的特征点集,为验证该算法的性能,将改进算法与常规算法进行了对比实验,实验结果表明,改进算法有效地减少了计算时间,细节特征提取准确率也基本可以满足应用的需要。

References

[1]  [2]Ratha N, Ch en S, Jain A K. Adaptive flow orientation based feature extraction in fingerprint images[J]. Pattern Recognition, 1995,28(11):1657~1672.
[2]  [5]Maio D, Maltoni D. Direct gray-scale minutiae detection infingerprints [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(1) :27~40.
[3]  [7]Yu Shiaw-Shian, Tsai Wen-Hsiang. A new thinning algorithm for gray-level images by the relaxation technique [J]. Pattern Recognition, 1990,23(10) :1067~1076.
[4]  [8]Datta A, Parui S K. A robust parallel thinning algorithm for binary images [J]. Pattern Recognition, 1994, 27 (9): 1181 ~1192.
[5]  [1]Lin Hong. Automatic personal identification using fingerprints[D]. US:Michigan State University, 1998:5~46.
[6]  [3]Mehtre B. Fingerprint image analysis for automatic identification [J]. Machine Vision and Application, 1993,6 (2-3): 124 ~ 139.
[7]  [4]Hong L, Jain A K, Bolle R et al. Pankanti. Identity authentication using fingerprints [A]. In: Proc. of First Int\'l Conference on Audio and Video Based Biometric Person Authentication [C], Geneva, Switzerland, 1997:103~ 110.
[8]  [6]Fang Xu-dong, Yau Wei-Yun, Ser Wee. Detecting the fingerprint minutiae by adaptive tracing the gray-level ridge[J]. Pattern Recognition, 2001,34(5): 999~1013.
[9]  [9]Xiao Q, Raafat H. Fingerprint image processing: A combined statistical and structural approach [J]. Pattern Recognition, 1991,24(10):985~992.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133