基于多尺度自适应的近红外手肘静脉提取算法  

Near-Infrared Elbow Vein Extraction Algorithm Based on Multiscale Adaptive Filter

作　　者：朱翔翔 郭永洪 ZHU Xiangxiang;GUO Yonghong(College of Mechanical and Electrical Engineering,China Jiliang University,Hangzhou 310018,China)

机构地区：[1]中国计量大学机电工程学院,浙江杭州310018

出　　处：《红外技术》2020年第5期494-500,共7页Infrared Technology

基　　金：国家重点研发项目(2018YFF0214700)。

摘　　要：由于成像质量不高,光照强度不均匀,皮下脂肪较厚等因素,近红外手肘静脉图像对比度较低,不易提取到清晰的静脉结构。针对该问题,本文提出了一种基于Hessian算子的多尺度自适应静脉滤波提取方法。该方法通过改进的多尺度自适应滤波器从对比度限制自适应直方图均衡化(Contrast-Limited Adaptive Histogram Equalization,CLAHE)增强后的图像中提取静脉。新的滤波器结构能够根据输入图像自适应地确定滤波器参数,在提取静脉的同时抑制噪声。实验结果表明该方法可以有效地获得清晰完整的静脉结构,具有更强的去噪和增强效果以及更高的准确率。A near-infrared elbow vein image has low contrast because of low image quality,uneven illumination intensity,and thicker subcutaneous fat.Therefore,it is difficult to extract a clear vein structure.To address this problem,a multiscale adaptive vein filtering enhancement method based on the Hessian operator is proposed.The method extracts veins from an image enhanced by contrast-limited adaptive histogram equalization with the use of an improved multiscale adaptive filter.The new filter structure can adaptively determine filter parameters based on the input image and suppress noise while extracting veins.The experimental results show that the method can effectively obtain a clear and complete vein structure,and it has stronger denoising,better enhancement effects,and higher accuracy.

关 键 词：手肘静脉图像 CLAHE HESSIAN矩阵 多尺度自适应滤波 静脉提取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]