An Algorithm for Fingerprint Image Segmentation with Smooth Contour
An important step in automatic fingerprint recognition system is the segmentation of fingerprint images. The task of a fingerprint segmentation algorithm is to decide which part of the image belongs to the foreground and which part to the background. Different methods have been proposed for fingerprint segmentation. Some of the traditional methods are introduced and implemented in this paper and a pixel base fingerprint segmentation algorithm is proposed. The method used two pixel features,being the coherence and the variance. Morphology is applied as post- processing to obtain a smooth contour line. The experiment result demonstrate the effectiveness of the proposed method,especially in low quality images,in terms of including less background and excluding less foreground. In addition,this robust segmentation algorithm is capable of filtering efficiently spurious boundary.
Futgerprint Segmentation Variance Coherence Contour
Hua Quanping Xiang Ming
Information Engineering Insititue,Zhejiang Textile & Fashion Vocational and Technical College,Ningbo Mathematics and Information College of Zhejiang Ocean University,Zhoushan 316000,China
国际会议
南宁
英文
97-100
2010-12-10（万方平台首次上网日期，不代表论文的发表时间）