首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于图像分析的显微视觉自动调焦方法研究
引用本文:陈国良,黄心汉,王敏,刘明尧.基于图像分析的显微视觉自动调焦方法研究[J].华中科技大学学报(自然科学版),2007,35(5):1-4.
作者姓名:陈国良  黄心汉  王敏  刘明尧
作者单位:1. 武汉理工大学,机电工程学院,湖北,武汉,430070
2. 华中科技大学,控制科学与工程系,湖北,武汉,430074
基金项目:国家高技术研究发展计划(863计划) , 湖北省自然科学基金
摘    要:定义了一种基于边缘灰度的显微图像清晰度评价函数,该函数采用改进的线性微分拉普拉斯算子和阈值滤波的方法以减少图像聚焦的误差.将该函数用于显微镜的自动调焦中,具体方法包括:对显微图像的噪声进行中值和同态滤波以提高显微图像的质量;通过带门限的帧差技术以区分背景与前景,同时,为减少噪声和图像前景变化的影响,在评价函数中引入了阈值参数.实验结果表明,该方法准确、稳定和可靠,精度较高.

关 键 词:图像分析  显微镜  自动调焦  评价函数  图像分析  显微视觉  自动  调焦  方法  研究  image  analysis  focus  精度  稳定  结果  实验  阈值参数  影响  变化  减少噪声  前景  背景  帧差  门限
文章编号:1671-4512(2007)05-0001-04
修稿时间:04 21 2006 12:00AM

Micro-vision auto focus by image analysis
Chen Guoliang,Huang Xinhan,Wang Min,Liu Mingyao.Micro-vision auto focus by image analysis[J].JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE,2007,35(5):1-4.
Authors:Chen Guoliang  Huang Xinhan  Wang Min  Liu Mingyao
Institution:1 School of Mechatronic, Wuhan University Technology, Wuhan 430070, China; 2 Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
Abstract:Edge gray-based evaluation function was defined,and an improved differential Laplacian and threshold value-based filter were used to reduce the errors of image focusing and a threshold value as a parameter was introduced.Microscopes were focused automatically by the evaluation function and some measures were adopted in the process.Medium and homomorphic filtering were employed to filter the noises from microscopic images to improve the quality of microscopic images. A method was designed to evaluate the clarity of the images.A frame difference technique with a limit was implemented to distinguish the foreground from the background of the microscopic images and reduced the noise effects and the foreground changes.Results show that the method with a high precision is stable and reliable.
Keywords:Image analysis  microscope  auto-focus  evaluation function
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号