基于云计算的激光医学图像伪影去除系统
|
摘要
针对传统图像伪影去除系统存在稳定性差、伪影去除后图像清晰度较低等问题,设计了基于云计算的激光医学图像伪影去除系统。系统在partan-3FPGA平台基础上,将系统划分为多个不同的模块,通过硬件语言编写了边缘检测电路,该电路具有实时数据处理能力,结合相关的总线以及缓存电路,构建基于云计算的激光医学图像伪影去除硬件系统,并详细介绍了每个模块的不同功能。引入线性插值方法,获取经过初步校正后的医学图像,并根据该图像建立先验图像,通过估计原始先验图中的伪影区域信息,将图像再次进行重构,实现激光医学图像伪影去除。经过实验证明可知,本文系统具有很好的伪影去除效果,有效保持了图像的细节部分以及清晰度。
Aiming at the problems of poor stability and low definition of image in the traditional image artifact removal system,a laser medical image artifact removal system based on cloud computing is designed. On the basis of partan-3FPGA platform,the system is divided into several different modules,and the edge detection circuit is written by hardware language. The circuit has real-time data processing ability. Combined with related bus and buffer circuit,the hardware system of laser medical image artifact removal based on cloud computing is constructed,and the different functions of each module are introduced in details. The linear interpolation method is introduced to obtain the medical image and then establish the priori image accordingly. The image is reconstructed again by estimating the information of the artifact region in the original priori image and the artifacts of the laser medical image are removed. The experimental results show that the designed system has a good effect of removing artifacts and effectively keeps the details and sharpness of the image.
Aiming at the problems of poor stability and low definition of image in the traditional image artifact removal system,a laser medical image artifact removal system based on cloud computing is designed. On the basis of partan-3FPGA platform,the system is divided into several different modules,and the edge detection circuit is written by hardware language. The circuit has real-time data processing ability. Combined with related bus and buffer circuit,the hardware system of laser medical image artifact removal based on cloud computing is constructed,and the different functions of each module are introduced in details. The linear interpolation method is introduced to obtain the medical image and then establish the priori image accordingly. The image is reconstructed again by estimating the information of the artifact region in the original priori image and the artifacts of the laser medical image are removed. The experimental results show that the designed system has a good effect of removing artifacts and effectively keeps the details and sharpness of the image.
引文
[1]徐苗,孙柯,王卓,等.激光散射图像检测桃果实货架期的食用价值[J].食品科学,2016,37(18):244-249.
[2]马增强,王永胜,宋子彬.基于激光源的机车轮轨相对横移图像检测[J].图学学报,2017,38(4):623-628.
[3]韩朵朵,孙正,苑园.血管内光声图像的时间反演重建方法[J].中国图象图形学报,2016,21(4):442-450.
[4]朱浩然,刘云清.基于对比度增强与多尺度边缘保持分解的红外与可见光图像融合[J].电子与信息学报,2018,40(6):1294-1300.
[5]乔闹生.印制电路板缺陷图像边缘检测[J].光子学报,2016,45(4):117-123.
[6]强钲捷,张合新,孟飞,等.激光主动成像图像边缘检测算法[J].激光与红外,2016,46(6):1192-1196.
[7]蔡健荣,刘梦雷,孙力,等.基于改进惯性矩算法的冷鲜猪肉新鲜度激光散斑图像检测[J].农业工程学报,2017,33(7):268-274.
[8]袁翠云,齐宏亮,陈梓嘉,等.基于投影域校正的CT图像环形伪影去除方法[J].计算机工程与设计,2017,38(3):735-738.
[9]李磊,王林元,席晓琦,等.基于加权TV正则化的X射线CT系统能谱估计方法[J].光谱学与光谱分析,2017,37(7):2230-2236.
[10]卜丽静,郑新杰,张正鹏,等.运动分割和光流估计的卫星视频超分辨率重建[J].测绘科学,2016,41(12):233-237.
[11]温海滨,毕笃彦,马时平,等.消除光晕和细节增强的多尺度Retinex红外图像增强[J].红外技术,2016,38(2):149-156.
[12]夏元,薛春燕,吴艳,等.常见致病真菌所致角膜炎的激光扫描共焦显微镜图像特点分析[J].中华实验眼科杂志,2016,34(2):155-159.
[13]唐庆菊,刘俊岩,王扬,等.基于模糊C均值聚类和Canny算子的红外图像边缘识别与缺陷定量检测[J].红外与激光工程,2016,001(9):274-278.
[14]刘子腾,白瑞林,王秀平.基于激光视觉的角焊缝图像特征点提取[J].焊接学报,2016,37(2):89-93.
[15]王宇.激光制导武器目标光斑检测系统设计与实现[J].电子器件,2017,40(4):978-982.
[16]马增强,宋子彬,王永胜.基于激光线的轮轨冲角检测新方法[J].光电工程,2017,44(8):818-825.
[17]王华,娄小平,李伟仙,等.基于FPGA工具的关节臂激光扫描测头CMOS图像采集系统[J].工具技术,2017,51(6):112-116.
[2]马增强,王永胜,宋子彬.基于激光源的机车轮轨相对横移图像检测[J].图学学报,2017,38(4):623-628.
[3]韩朵朵,孙正,苑园.血管内光声图像的时间反演重建方法[J].中国图象图形学报,2016,21(4):442-450.
[4]朱浩然,刘云清.基于对比度增强与多尺度边缘保持分解的红外与可见光图像融合[J].电子与信息学报,2018,40(6):1294-1300.
[5]乔闹生.印制电路板缺陷图像边缘检测[J].光子学报,2016,45(4):117-123.
[6]强钲捷,张合新,孟飞,等.激光主动成像图像边缘检测算法[J].激光与红外,2016,46(6):1192-1196.
[7]蔡健荣,刘梦雷,孙力,等.基于改进惯性矩算法的冷鲜猪肉新鲜度激光散斑图像检测[J].农业工程学报,2017,33(7):268-274.
[8]袁翠云,齐宏亮,陈梓嘉,等.基于投影域校正的CT图像环形伪影去除方法[J].计算机工程与设计,2017,38(3):735-738.
[9]李磊,王林元,席晓琦,等.基于加权TV正则化的X射线CT系统能谱估计方法[J].光谱学与光谱分析,2017,37(7):2230-2236.
[10]卜丽静,郑新杰,张正鹏,等.运动分割和光流估计的卫星视频超分辨率重建[J].测绘科学,2016,41(12):233-237.
[11]温海滨,毕笃彦,马时平,等.消除光晕和细节增强的多尺度Retinex红外图像增强[J].红外技术,2016,38(2):149-156.
[12]夏元,薛春燕,吴艳,等.常见致病真菌所致角膜炎的激光扫描共焦显微镜图像特点分析[J].中华实验眼科杂志,2016,34(2):155-159.
[13]唐庆菊,刘俊岩,王扬,等.基于模糊C均值聚类和Canny算子的红外图像边缘识别与缺陷定量检测[J].红外与激光工程,2016,001(9):274-278.
[14]刘子腾,白瑞林,王秀平.基于激光视觉的角焊缝图像特征点提取[J].焊接学报,2016,37(2):89-93.
[15]王宇.激光制导武器目标光斑检测系统设计与实现[J].电子器件,2017,40(4):978-982.
[16]马增强,宋子彬,王永胜.基于激光线的轮轨冲角检测新方法[J].光电工程,2017,44(8):818-825.
[17]王华,娄小平,李伟仙,等.基于FPGA工具的关节臂激光扫描测头CMOS图像采集系统[J].工具技术,2017,51(6):112-116.