本文已被：浏览 2328次 下载 5483次
Received:October 30, 2009 Revised:January 25, 2010
Received:October 30, 2009 Revised:January 25, 2010
中文摘要: 指纹图像的二值化处理是指纹图像预处理中的关键步骤，直接影响到指纹图像细化的质量和细节特征提取的准确性。在深入分析指纹图像信息熵的基础上，将信息熵引入到指纹图像二值化算法中，通过求取对应指纹图像区域的最大信息熵估计二值化阈值，并依据此阈值实现对指纹图像的二值化处理。实验结果表明，文中算法对噪声具有鲁棒性，能够有效实现对指纹图像的二值化，提高了细节特征提取结果的准确率。
Abstract:In fingerprint image pre-processing，fingerprint image binarization processing is a key step in a direct impact on the quality of fingerprint image thinning and accuracy of the extraction of the minutiaes. After an in-depth analysis of information entropy of fingerprint images, information entropy is introduced to the fingerprint image binarization algorithm. Through calculating a maximum entropy of the corresponding the region in fingerprint image, binarization threshold is estimated, and based on the achievement of this threshold fingerprint image binarization processing is done. The experimental results show that the algorithm is robust to noise and able to effectively realize the fingerprint image binarization.
文章编号： 中图分类号： 文献标志码：
基金项目:安徽省自然科学基金(090412072);山东省博士后基金(200602014)
引用文本：
张理想,詹小四,张修如.基于信息熵的指纹图像二值化算法①.计算机系统应用,2010,19(6):148-152
ZHANG Li-Xiang,ZHAN Xiao-Si,ZHANG Xiu-Ru.Fingerprint Image Binarization Algorithm Based on Information Entropy.COMPUTER SYSTEMS APPLICATIONS,2010,19(6):148-152
张理想,詹小四,张修如.基于信息熵的指纹图像二值化算法①.计算机系统应用,2010,19(6):148-152
ZHANG Li-Xiang,ZHAN Xiao-Si,ZHANG Xiu-Ru.Fingerprint Image Binarization Algorithm Based on Information Entropy.COMPUTER SYSTEMS APPLICATIONS,2010,19(6):148-152
