期刊文献+

基于改进MRF的冲压件轮廓缺陷图像分割算法 被引量:6

Image segmentation algorithm on contour defects for stamping part based on improved MRF
原文传递
导出
摘要 针对冲压件在生产过程中产生的表面缺陷视觉检测问题,提出一种改进的马尔可夫随机场图像分割算法。首先,应用基于像素的马尔可夫随机场算法,获取像素特征,提取基于像素的似然函数。采用随机区域合并算法获得区域特征,提取基于随机区域合并的似然函数。利用最大梯度算法获得图像的边缘特征,提取基于边缘的似然函数,用以恢复随机区域合并过程中丢失的边缘信息。融合3种似然函数,根据能量最小准则,实现图像分割。通过与传统图像分割方法的对比实验,验证了该算法的有效性。实验结果表明,改进算法可实现冲压件图像的精准分割,应用效果较好。 For the problem of visual inspection for surface defects of stamping part during the production process, an improved Markov Random Field(MRF) image segmentation algorithm was proposed. First, the pixel-based MRF algorithm was applied to obtain the pixel features and extract the pixel-based likelihood function, and the stochastic region merging algorithm was used to obtain regional features, and the likelihood function based on stochastic region merging was extracted. Then, the edge features of the image was obtained by the maximum gradient algorithm, and the edge-based likelihood function was extracted to restore the edge information lost in the stochastic region merging process. Furthermore, three kinds of likelihood functions were fused, and image segmentation was realized by the minimum energy criterion. Finally, the effectiveness of the algorithm was verified by comparative experiments with traditional image segmentation methods. The experimental results show that the improved algorithm can achieve accurate segmentation of stamping part images, and the application effect is better.
作者 吕宁 肖剑 高健 欧阳雪峰 罗忠洁 Lyu Ning;Xiao Jian;Gao Jian;Ouyang Xuefeng;Luo Zhongjie(School of Mechanical Engineering,Yangzhou Polytechnic College,Yangzhou 225009,China;School of Automation,Harbin University of Science and Technology,Harbin 150080,China)
出处 《锻压技术》 CAS CSCD 北大核心 2022年第4期101-109,共9页 Forging & Stamping Technology
基金 扬州市“绿扬金凤计划”高层次创新创业领军人才引进项目(2021CX044)。
关键词 冲压件 视觉检测 马尔可夫随机场 随机区域合并 图像分割 似然函数 stamping part visual inspection Markov Random Field stochastic region merging image segmentation likelihood funditon
  • 相关文献

参考文献12

二级参考文献182

  • 1伍济钢,宾鸿赞.机器视觉的薄片零件尺寸检测系统[J].光学精密工程,2007,15(1):124-130. 被引量:65
  • 2左建中,尹辉,陈贤青.小波变换在螺纹边缘检测中的应用[J].制造业自动化,2007,29(1):33-34. 被引量:7
  • 3李旭超,朱善安.图像分割中的马尔可夫随机场方法综述[J].中国图象图形学报,2007,12(5):789-798. 被引量:64
  • 4章毓晋.图像处理和分析[M].清华大学出版社,1999,3..
  • 5朱志刚 石定机 等.数字图像处理[M].北京:电子工业出版社,1998..
  • 6WANG Xue, TANG Yi-ke, CHENG Ping. Machine-vision detection for rail-steel's surface flaws based on quantum neural network [C]. The 7th World Congress on Intelligent Control and Automation. Chongqing, China, June 25-27, 2008.
  • 7LOPEZ Carlos, GARCIA Daniel F, USAMENTIAGA Ruben,et al. Real-time system for flatness inspection ofsteel strips[J]. Machine Vision Applications in Indus- trial Inspection,2005, 5679(1) :228-238.
  • 8SONKA M,HLAVAC V,BOYLE R.图像处理、分析与机器视觉[M].3版.艾海舟,苏延超,等,译.北京:清华大学出版社,2011.
  • 9Yuille A L, Poggio T. Scaling Theorems for Zero Crossings, IEEE Trans. PAMI, 1996(8) : 15 - 25.
  • 10Babaud J, Witkin A, Duda R. Uniqueness of the Gaussian Kernel for Scaling-Space Filtering, IEEE Trans. PAMI, 1986(8) :26 - 33.

共引文献422

同被引文献81

引证文献6

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部