基于Markov随机场模型的数字X光图像自适应增强算法  

Adaptive Enhancement Algorithm of Digital X-Ray Image Based on Markov Random Field Model

作　　者：袁义 李国祥[2] 王继军[2,3] YUAN Yi;LI Guoxiang;WANG Jijun(College of Computer Science,Hunan University of Technology,Zhuzhou 412007,Hunan Province,China;School of Big Data and Artificial Intelligence,Guangxi University of Finance and Economics,Nanning 530003,China;Guangxi Key Laboratory of Big Data in Finance and Economics,Nanning 530003,China)

机构地区：[1]湖南工业大学计算机学院,湖南株洲412007 [2]广西财经学院大数据与人工智能学院,南宁530003 [3]广西财经大数据重点实验室,南宁530003

出　　处：《吉林大学学报（理学版）》2023年第2期377-383,共7页Journal of Jilin University:Science Edition

基　　金：国家自然科学基金(批准号:62162006,71862003);广西高校中青年教师基础能力提升项目(批准号:2020KY16021,2021KY0650);广西多源信息挖掘与安全重点实验室开放基金(批准号:MIMS18-05,MIMS17-02).

摘　　要：为明确X光图像纹理粗细和组织分布状况,强化呈现身体结构信息,降低模糊图像对医生诊断病情结果的错误判断,提出一种基于Markov随机场模型的数字X光图像自适应增强算法.该算法首先统计X光图像全部范围内相同亮度像素,利用直方图均衡化法将原始图像变换成灰度级分布影像,消除光线干扰;然后分析组织属性,通过灰度共生矩阵提取X光图像的纹理特征,获取图像纹理粗细和布局结构的灰度信息;最后通过映射函数和对数函数计算平均亮度,用Markov随机场模型调整图像明暗度,补充纹理细小部位亮度,再用随机场函数划分光滑图像,采取二次重构,以保证图像锐化增强效果平衡.仿真实验结果表明,该算法能提升图像的内部信息清晰度.In order to clarify the texture thickness and tissue distribution of the X-ray image,enhance the presentation of body structure information,and reduce the wrong judgment of fuzzy image on doctors’diagnosis results,we proposed an adaptive enhancement algorithm of digital X-ray image based on Markov random field model.Firstly,the algorithm counted the pixels with the same brightness in the whole range of X-ray image,and the histogram equalization method was used to transform the original image into gray level distribution image to eliminate light interference.Secondly,we analyzed the organization attributes,extracted the texture features of X-ray image through gray level co-occurrence matrix,and obtained the gray level information of image texture thickness and layout structure.Finally,the average brightness was calculated by the mapping function and logarithmic function,the Markov random field model was used to adjust the brightness of the image,supplement the brightness of small parts of the texture,then the smooth image was divided by the random field function,and the secondary reconstruction was adopted to ensure the balance of image sharpening and enhancement effect.The simulation results show that the proposed algorithm can improve the internal information clarity of the image.

关 键 词：MARKOV随机场模型 数字X光图像 图像自适应增强 图像特征提取 图像预处理 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]