基于信息熵的指纹图像二值化算法  

Fingerprint Image Binarization Algorithm Based on Information Entropy

作　　者：张理想[1,2] 詹小四[3,2] 张修如[1] 

机构地区：[1]中南大学信息科学与工程学院,湖南长沙410075 [2]阜阳师范学院计算机与信息学院,安徽阜阳236032 [3]山东大学计算机科学与技术学院,山东济南250100

出　　处：《计算机系统应用》2010年第6期148-152,共5页Computer Systems & Applications

基　　金：安徽省自然科学基金(090412072);山东省博士后基金(200602014)

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。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.

关 键 词：信息熵 阈值分割 二值化 指纹识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]