Analysis and Extraction of Fingerprint Minutiae Based on Improved GPL Principal Curve Algorithm
ZHANG HongYun, MIAO DuoQian, FU WenJie
Department of Computer Science and Technology,Tongji University, Shanghai 200092 Tongji Branch of National Engineering and Technology Center of High Performance Computer, Shanghai 200092
Abstract：Based on the analysis of GPL principal curve algorithm and the specialties of fingerprint, the principal curve is used to reflect the structure of fingerprint. The original GPL principal curve algorithm is improved to get better skeletonization of fingerprint and the minutiae extraction based on the principal curves is applied. The experimental results show that the improved principal curve algorithm is more efficient and its skeletonization is much better than those of the original ones. The accuracy of minutiae extraction based on the principal curves is also higher than some traditional methods, which has higher value in application.
张红云，苗夺谦，傅文杰. 基于改进的GPL主曲线算法的指纹特征分析与提取*[J]. 模式识别与人工智能, 2007, 20(6): 763-769.
ZHANG HongYun, MIAO DuoQian, FU WenJie. Analysis and Extraction of Fingerprint Minutiae Based on Improved GPL Principal Curve Algorithm. , 2007, 20(6): 763-769.
[1] Lin Hong. Automatic Personal Identification Using Fingerprints. Ph.D Dissertation. Michigan, USA: Michigan State University. East Lansing, 1998: 227236 [2] Hastie T. Principal Curves and Surfaces. Technical Report, SLARR276, Stanford, USA: Stanford University. Laboratory for Computational Statistics, 1984 [3] Zhang Junping, Wang Jue. An Overview of Principal Curves. Chinese Journal of Computers, 2003, 26(2): 129146 (in Chinese) (张军平,王 珏.主曲线研究综述.计算机学报, 2003, 26(2): 129146) [4] Zhang Hongyun, Miao Duoqian. Automatic Recognition System of Bills Based on Principal Curves. Journal of Information and Computational Science, 2004, 1(2): 199204 [5] Zhang Hongyun, Miao Duoqian. Zhang Dongxing. Analysis and Extraction of Structural Features of OffLine Handwritten Digits Based on Principal Curves. Journal of Computer Research and Development, 2005, 42(8): 13441349 (in Chinese) (张红云,苗夺谦,张东星.基于主曲线的脱机手写数字特征分析与选取.计算机研究与发展, 2005, 42(8): 13441349) [6] Yin Yilong, Ning Xinbao, Zhang Xiaomei. An Improved Algorithm for Minutiae Extraction in Fingerprint Images. Journal of Image and Graphics, 2002, 7(12): 13021306 (in Chinese) (尹义龙,宁新宝,张晓梅.改进的指纹细节特征提取算法. 中国图象图形学报, 2002, 7(12): 13021306) [7] Wang Furong, Cheng Peng, Zou Xuan. A Novel Improved Approach of Direct Minutia Extraction from GrayLevel Fingerprint Image. Journal of Image and Graphics, 2004, 9(5): 557564 (in Chinese) (王芙蓉,程 鹏,邹 璇.直接提取指纹特征算法的优化研究.中国图象图形学报, 2004, 9(5): 557564) [8] Kégl B, Krzyzak A, Linder T, et al. A Polygonal Line Algorithm for Constructing Principal Curves // Proc of the Conference on Neural Information Processing Systems. Denver, USA, 1999: 501507 [9] Kégl B, Krzyzak A. Piecewise Linear Skeletonization Using Principal Curves. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(1): 5974 [10] Suzuki S, Abe K. Sequential Thinning of Binary Pictures Using Distance Transformation // Proc of the 8th International Conference on Pattern Recognition. Paris, France, 1986: 289292 [11] Yu S S, Tsai W H. A New Thinning Algorithm for GrayScale Images by the Relaxation Technique. Pattern Recognition, 1990, 23(10): 10671076 [12] Lin Hong, Jain A K, Pankanti S, et al. Fingerprint Enhancement // Proc of the 3rd IEEE Workshop on Applications of Computer Vision. Sarasota, USA, 1996: 202207 [13] Lin Hong, Wan Yifei, Anil J. Fingerprint Image Enhancement: Algorithm and Performance Evaluation. IEEE Trans on Pattern Analysis and Machine Intelligence, 1998, 20(8): 777789
2007, Vol. 20 
