长沙理工大学学报（自然科学版）2016，Vol.13Issue(1)：75-80,6.
改进灰度共生矩阵的指纹图像分割算法
An improved gray level co-occurrence fingerprint image segmentation algorithm
摘要
Abstract
In the process of fingerprint image segmentation,matrix artificial selection of the threshold is not accurate,tedious.A fingerprint image segmentation algorithm is proposed by improved gray level co-occurrence matrix.Firstly,Mv is the mean value of the contrast variance for fingerprint images,Pv is the mean value of the contrast variance between the fingerprint region.Mv is adopted as the image segmentation threshold.Then,Mv is adj usted continuously,when the Pv/Mv is between 1.5 and 2 the best segmentation results is ob-tained through experiment.The adaptive segmentation threshold of gray level co-occurrence matrix is obtained.Experimental results show that this algorithm is superior to the segmen-tation error rate,time consuming and more accurate compared with the existing segmenta-tion algorithm.关键词
指纹图像/分割/灰度共生矩阵/自适应阈值Key words
fingerprint image/segmentation/gray level co-occurrence/adaptive threshold分类
信息技术与安全科学引用本文复制引用
黄敏,刘云坚..改进灰度共生矩阵的指纹图像分割算法[J].长沙理工大学学报（自然科学版）,2016,13(1):75-80,6.基金项目
国家自然科学基金资助项目(61402053) （61402053）
