浏览全部资源
扫码关注微信
1. 天津大学 精仪学院 光电信息技术科学教育部重点实验室 天津,300072
2. 桂林电子科技大学 机电工程学院,广西 桂林,541004
收稿日期:2010-01-08,
修回日期:2010-04-05,
网络出版日期:2010-10-28,
纸质出版日期:2010-10-20
移动端阅览
邓仕超, 刘铁根, 萧泽新. 应用Canny算法和灰度等高线的金相组织封闭边缘提取[J]. 光学精密工程, 2010,18(10): 2314-2323
Deng Shi-chao, Liu Tie-gen, Xiao Ze-xin. Extraction of enclosing image edge for metallographic structure based on Canny and grayscale contour line[J]. Editorial Office of Optics and Precision Engineering , 2010,18(10): 2314-2323
邓仕超, 刘铁根, 萧泽新. 应用Canny算法和灰度等高线的金相组织封闭边缘提取[J]. 光学精密工程, 2010,18(10): 2314-2323 DOI: 10.3788/OPE.20101810.2314.
Deng Shi-chao, Liu Tie-gen, Xiao Ze-xin. Extraction of enclosing image edge for metallographic structure based on Canny and grayscale contour line[J]. Editorial Office of Optics and Precision Engineering , 2010,18(10): 2314-2323 DOI: 10.3788/OPE.20101810.2314.
为了对金相组织的多项组织含量进行定量分析
提出应用Canny算法和灰度等高线相结合的方法来产生封闭金相组织边缘。首先
采用高斯函数对金相组织的灰度图像进行模糊处理
然后
用Canny算法对模糊后的图像获取具有单边缘效应的原始边缘。通过最大类间方差法对原始边缘进行自动计算
获得抑制虚假边缘的阈值
并通过该阈值获取基础边缘。由于基础边缘具有不连续性
因此需根据基础边缘端点的邻域灰度中值计算所需的灰度等高线
同时根据设定的等高线和基础边缘融合的条件
以基础边缘的端点为起点生成封闭边缘。实验结果表明
该算法可有效地生成符合要求的封闭边缘
采用该算法产生的封闭边缘进行金相组织含量测定可使测量误差降低到1%
可测组织含量范围达到5% ~95%。该算法能满足多项金相组织含量测定的定量分析要求且具有普适性。
In order to quantitatively analyse the polyphase contents of metallographic structures
this paper presented an enclosing image edge extraction algorithm based on the Canny algorithm and a grayscale contour line.Firstly
the grayscale images of metallographic structure were blured with Gaussian blur
and then the initial edges with single edge effect in blured images were acquired using Canny algorithm. The thresholds were automatically calculated by the maximising variance between-class to reduce false edges and to obtain the basic edge for the next steps. According to the grayscale neighborhood of the end points of basic edge
the gray values of grayscale contour line were calculated. On the basis fusion conditions of basic edge and grayscale contour line
the closing edge could be created from the end points of basic edge. Experimental results indicate that this algorithm can generate an enclosing edge efficiently. The error rate of the polyphase contents of metallographic structures has decreased to 1% by using this algorithm. The proportion range of different sections about one metallographic image has increased to 5%-95%. The algorithm can satisfy the demand of quantitative analysis of the polyphase structure contents and is suitable for different shape metallographic structures.
GB/T 13305-2008. 不锈钢中-相面积含量金相测定法[S]. GB/T 13305-2008. Micrographic method for determining area content of the -phases in stainless steels [S]. (in Chinese)[2] 刘持森. 双相不锈钢中相含量的精确测定[J]. 理化检验-物理分册,2003,39(8): 414-416. LIU CH S. Measuring the phase content of dual-phases stainless steel accurately [J]. Physical Testing and Chemical Analysis Part A: Physical Testing, 2003,39(8):416-417. (in Chinese)[3] 燕惠芳.钢铁金相组织自动识别系统关键技术研究 . 南京:南京航空航天大学,2006:40-46. YAN H F. Research on key technologies of automatic identification system of metallography organization . Nanjing: Nanjing University of Aeronautics and Astronautics,2006: 40-46. (in Chinese)[4] 汤力琨.金相组织图像分析中关键算法研究 . 成都:四川大学,2005:18-24. TANG L K. Research of some key algorithms in metallographic image analysis system . Chengdu: Sichuang University,2005:18-2. (in Chinese)[5] 黄丽华. 彩色金相显微图像分析系统的建立与彩色图像分割方法的研究 . 杭州:浙江大学,2004:67-77. HUANG L H. The establish of color metallography computer-aided analysis system & the research on color image segmentation . Hangzhou: Zhejiang University, 2004:67-77. (in Chinese)[6] RAFAEL C G, RICHARD E W, STEVEN L E. Digital Image Using MATLAB [M]. Beijing: Publishing Houses of Electronics Industry, 2006.[7] 张建伟,张启衡. 基于块遍历的直线边缘特征提取[J]. 光学 精密工程,2009,17(3):662-668. ZHANG J W, ZHANG Q H. Line-edge feature extraction based on ergodic block [J]. Opt. Precision Eng., 2009,17(3):662-668. (in Chinese)[8] 陈平,潘晋孝,刘宾. CT图像边缘退化模型的建立及其在图像尺寸测量中的应用[J]. 光学 精密工程,2009,17(9):2269-2275. CHEN P, PAN J X, LIU B. Computed tomography image edge degradation model and its application to image size measurement [J]. Opt. Precision Eng., 2009,17(9):2269-2275. (in Chinese)[9] DENG S C, LIU T G, XIAO Z X,et al.. An automatic detection system for flatness of integrated circuit pins . Proc. SPIE - The International Society for Optical Engineering, 2008 International Conference on Optical Instruments and Technology: Optical Systems and Optoelectronic Instruments,Beijing,2008,7156:715639.[10] CANNY J A. Computational approach to edge detection [J].IEEE Trans.on Pattern Analysis and Machine Intelligence,1986,8(6):679-698.[11] 向静波. 基于Contourlet变换和Canny算子的图像边缘检测方法[J]. 红外技术,2009,31(8):479-482. XIANG J B. Edge detection of image based on canny operator and contourlet transform [J]. Infrared Technology, 2009,31(8):479-482 (in Chinese)[12] 何瑾, 刘铁根, 张昊,等. 应用形态学top-hat变换的支票方形印鉴自适应分割[J]. 光学 精密工程, 2009,17(10):2583-2591. HE J, LIU T G, ZHANG H, et al.. Automatic seal identification using edge difference[J]. Opt. Precision Eng., 2009,17(10):2583-2591. (in Chinese)
0
浏览量
519
下载量
5
CSCD
关联资源
相关文章
相关作者
相关机构