采样优化支持的指纹图像二值化算法研究  

Research on Fingerprint Image Binarization Algorithm Based on Sampling Optimization Support

作　　者：霍延军[1] Huo Yanjun(Yan̓an Vocational and Technical College,Yan̓an 716000,China)

机构地区：[1]延安职业技术学院,延安716000

出　　处：《单片机与嵌入式系统应用》2020年第9期43-46,共4页Microcontrollers & Embedded Systems

摘　　要：针对传统动态阈值算法在指纹图像采集过程中噪声大、分辨率低、效果失真的问题,提出一种动态阈值加填补的二值算法来改善变形指纹图像的细节处理能力,并设计一种邻域均值模板对图像边缘细节处理进行优化。通过对指纹图像进行串口分割,引入惩罚相作为分割窗口灰色度阈值,提升算法的有效性和鲁棒性;通过对4个特征方向的像素点进行均值处理,有效区分边缘像素和中间像素点的重要度,提升图像边缘点分类精确度。实验结果表明:本文改进的算法在处理复杂指纹图像时,能够很好地保留指纹图像细节部分,且图像占比更小;同时,算法对边缘细节部分的优化更显著,且具有很高的计算速度。Aiming at the problem that the traditional dynamic threshold algorithm has high noise,low resolution and distortion in the process of fingerprint image acquisition,a binary algorithm with dynamic threshold plus filling is proposed to improve the detail processing ability of the deformed fingerprint image,and a neighborhood mean template is designed to optimize the image edge detail processing.Through the serial port segmentation of fingerprint image,the penalty phase is introduced as the gray degree threshold of segmentation window,the effectiveness and robustness of the algorithm are improved,and the importance degree of edge pixel and middle pixel point are effectively distinguished by the pixel points and the mean value processing characteristic directions,and the classification accuracy of edge point of image is improved.The experiment results show that the improved algorithm can keep the detail part of the fingerprint image while processing the complex fingerprint image.

关 键 词：指纹图像 二值化计算 动态阈值法 邻域均值 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]