网站首页期刊简介编委会过刊目录投稿指南广告合作征订与发行联系我们English
基于改进MRF的冲压件轮廓缺陷图像分割算法
英文标题:Image segmentation algorithm on contour defects for stamping part based on improved MRF
作者:吕宁1 2 肖剑2 高健2 欧阳雪峰2 罗忠洁2 
单位:1. 扬州职业大学 2. 哈尔滨理工大学 
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 
分类号:TP391.41;TG84
出版年,卷(期):页码:2022,47(4):101-109
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. 

基金项目:
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)
作者简介:
作者简介:吕宁(1970-),男,工学博士,教授,研究生导师 E-mail:ning_lv@163.com 通信作者:肖剑(1996-),男,硕士研究生 E-mail:moqizixi@163.com
参考文献:

 [1]陈广锋, 管观洋, 魏鑫. 基于机器视觉的冲压件表面缺陷在线检测研究[J]. 激光与光电子学进展, 2018, 55(1): 341-347.


Chen G F, Guan G Y, Wei X. Online stamping parts surface defects detection based on machine vision[J]. Laser & Optoelectronics Progress, 2018, 55(1):341-347.

[2]李丽娟, 徐尚龙, 秦杰. 基于图像处理技术的五金件表面缺陷检测研究[J]. 工程设计学报, 2011, 18(2): 134-138. 

Li L J, Xu S L, Qin J. Research on hardware surface defects detection based on image processing techniques[J]. Chinese Journal of Engineering Design. 2011, 18(2):134-138.

[3]Borji A, Cheng M M, Hou Q, et al. Salient object detection: A survey[J]. Computational Visual Media, 2019, 5(2):117-150.

[4]黄鹏, 郑淇, 梁超. 图像分割方法综述[J]. 武汉大学学报:理学版, 2020, 66(6):519-531.

Huang P, Zheng Q, Liang C. Overview of image segmentation methods[J]. Journal of Wuhan University:Natural Science Edition, 2020, 66(6):519-531.

[5]Tao X, Zhang D P, Ma W Z, et al. Automatic metallic surface defect detection and recognition with convolutional neural networks[J]. Applied Sciences, 2018, 8(9):1575.

[6]Domen Tabernik, Samo ela, Jure Skvarcˇ, et al. Segmentation-based deep-learning approach for surface-defect detection[J]. Journal of Intelligent Manufacturing, 2020, 31(3): 759-776.

[7]田洪志, 王东兴, 林建钢, 等. 基于双阈值图像区域生长法的冲压件划痕检测[J].锻压技术, 2020, 45(6):175-181.

Tian H Z, Wang D X, Lin J G. Scratch detection on stamping part based on double threshold image region growth method[J]. Forging & Stamping Technology, 2020, 45(6):175-181.

[8]林俊义, 吴雷, 杨梅英, 等. 大型自由曲面零件的机器人视觉快速定位方法[J/OL]. http://kns.cnki.net/kcms/detail/11.5946.TP.20210105.1328.017.html.

Lin J Y, Wu L, Yang M Y, et al. Rapid robot vision positioning method for large free-form surface parts[J/OL].http://kns.cnki.net/kcms/detail/11.5946.TP.20210105.1328.017.html.

[9]陈德潮. 易拉罐冲压视觉检测方法设计[J]. 中山大学研究生学刊:自然科学·医学版, 2013, 34(2):87-99.

Chen D C. Design of visual inspection method of cans-stampings[J]. Journal of the Graduates Sun Yat-Sen University:Natural Sciences·Medicine, 2013, 34(2): 87-99.

[10]Zhou J, Bao X, Li D, et al. Traffic video image segmentation model based on bayesian and spatio-temporal markov random field[J]. Journal of Physics Conference Series, 2017, 910:012041.

[11]Wu S, Weng X. Image labeling with Markov random fields and conditional random fields[J/OL]. https://www.researchgate. net/publication/329266098,2018.

[12]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, (5):789-798.

Li X C, Zhu S A. A survey of the markov random field method for image segmentation[J]. Journal of Image and Graphics, 2007, (5):789-798.

[13]Hammersley J M, Clifford P. Markov fields on finite graphs and lattices [R]. Oxford: Oxford University, 1971.

[14]Chauhan A S, Silakari S, Dixit M. Image segmentation methods: A survey approach[A]. Fourth International Conference on Communication Systems & Network Technologies[C]. IEEE, 2014.

[15]Chen X, Zheng C, Yao H, et al. Image segmentation using a unified markov random field model[J]. Iet Image Processing, 2017, 11(10):860-869.

[16]夏平, 任强, 吴涛, 等. 融合多尺度统计信息模糊C均值聚类与Markov随机场的小波域声纳图像分割[J]. 兵工学报, 2017, 38(5):940-948.

Xia P, Ren Q, Wu T, et al. Sonar image segmentation fusion of multi-scale statistical information FCM clustering and MRF model in wavelet domain[J]. Acta Armamentarii, 2017, 38(5):940-948.

[17]徐胜军, 韩九强, 刘光辉. 基于马尔可夫随机场的图像分割方法综述[J]. 计算机应用研究, 2013, 30(9): 2576-2582.

Xu S J, Han J Q, Liu G H. Survey of image seg-mentation methods based on markov random fields[J]. Application Research of Computers, 2013, 30(9): 2576-2582.

[18]Wong A, Scharcanski J, Fieguth P. Automatic skin lesion segmentation via iterative stochastic region merging[J]. IEEE Transactions on Information Technology in Biomedicine A Publication of the IEEE Engineering in Medicine & Biology Society, 2011, 15(6):929-36.

[19]Nock R, Nielsen F. Statistical region merging[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2004, 26(11):1452.

[20]Marr D. Vision: A Computational Investigation Into the Human Representation and Processing of Visual Information[M]. Cambridge: MIT Press, 2010.

[21]Canny J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6):679-698.

[22]康牧, 许庆功, 王宝树. 一种Roberts自适应边缘检测方法[J]. 西安交通大学学报, 2008, (10):1240-1244.

Kang M, Xu Q G, Wang B S. A Roberts′ adaptive edge detection method[J]. Journal of Xi'an Jiaotong University, 2008, (10):1240-1244.

[23]张光年, 葛庆平. 基于Marr-Hildreth算子多尺度图像边缘检测[J]. 首都师范大学学报:自然科学版, 2005, (3):17-21.

Zhang G N, Ge Q P. Multi-scale image edge detection based on Marr-Hildreth operator algorithm[J]. Journal of Capital Normal University:Natural Science Edition, 2005, (3):17-21.

[24]Salih O, Viriri S. Skin lesion segmentation using enhanced unified Markov random field[A]. International Conference on Mining Intelligence and Knowledge [C]. Springer, 2018.

[25]Grana C, Borghesani D, Cucchiara R. Connected co-mponent labeling techniques on modern architectures[A]. International Conference on Image Analysis and Processing[C]. Berlin, Heidelberg,2009.

[26]Haralick R M, Shapiro L G. Computer and robot vision[J]. Addison-Wesley, 1992, 1: 28-48.
服务与反馈:
本网站尚未开通全文下载服务】【加入收藏
《锻压技术》编辑部版权所有

中国机械工业联合会主管 北京机电研究所有限公司 中国机械工程学会塑性工程分会主办
联系地址:北京市海淀区学清路18号 邮编:100083
电话:+86-010-82415085 传真:+86-010-62920652
E-mail: fst@263.net(稿件) dyjsjournal@163.com(广告)
京ICP备07007000号-9