基于梯度场和局部偏差的复杂工件X射线图像增强  

X-ray image enhancement for complex workpieces based on gradient field and local deviation

作　　者：韩美蓉 陈平[2] 潘晋孝[1,2] HAN Meirong;CHEN Ping;PAN Jinxiao(School of Mathematics,North University of China,Taiyuan Shanxi 030051,China;Shanxi Key Laboratory of Signal Capturing&Processing(North University of China),Taiyuan Shanxi 030051,China)

机构地区：[1]中北大学数学学院,太原030051 [2]信息探测与处理山西省重点实验室(中北大学),太原030051

出　　处：《计算机应用》2023年第S02期182-185,共4页journal of Computer Applications

基　　金：国家自然科学基金资助项目(62122070,61971381);山西省自然科学基金资助项目(20210302124190,20210302124191)。

摘　　要：复杂异形工件的X射线图像由于自身结构复杂性出现对比度低或特征信息不明确的问题,基于局部方差和偏微分方程的方法虽然可以增加图像对比度,但不能有效地抑制噪声。针对该问题,提出基于梯度场和局部偏差(LD)的图像增强算法,提高视觉质量。首先,由于梯度信息对射线图像中工件的轮廓和边缘处比较敏感,因此基于梯度场构建对比度自适应增强模型,以提高射线图像的对比度;然后,引入LD量化图像局部信息的平坦度,并将LD与梯度场结合构建增益函数,从而增强图像的对比度场,特别地,用最小二乘法拟合一个完全平坦的参考平面,再通过计算实际平面与参考平面之间的LD值将更多像素点纳入考虑范围,从而降低噪声的影响;最后,建立能量泛函并用变分法求解以获得更清晰的图像。对两个工件的射线图像进行图像增强和缺陷检测实验,实验结果表明所提算法能够有效地提升X射线图像的质量和对比度,从而提高无损检测的准确性和可靠性。X-ray images of complex workpieces often incline to low contrast and unclear feature information by high dynamic X-ray imaging system.Methods based on local variance and partial differential equations have been proposed to enhance image contrast,but they fail to effectively suppress noise.To solve this problem,an image enhancement algorithm based on gradient field and Local Deviation(LD)was proposed to improve visual quality.Since gradient information was sensitive to the outlines and edges of an object in an image,a model of adaptive contrast enhancement model based on the gradient field was built to improve the contrast of X-ray images.Then,LD was introduced to quantify the flatness of the local information of an image,and the gain function was constructed by combining the LD with the gradient field to enhance the contrast field.Specially,a completely flat reference plane was fitted by the least squares method,and by calculating the LD value between the actual plane and the reference plane,more pixels were taken into account to reduce the effect of noise.Finally,an energy functional was established and solved by variational method to obtain sharper images.Image enhancement and defect detection experiments on X-ray images of two workpieces were launched,and the experimental results show that the proposed algorithm effectively improves the visual quality and contrast of X-ray images,thereby improving the accuracy and reliability of non-destructive detection.

关 键 词：X射线成像 图像增强 梯度场 局部偏差 变分法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]