基于双三次插值的Canny-Devernay亚像素图像边缘检测算法*

doi:10.16731/j.cnki.1671-3133.2025.03.013

现代制造工程 ›› 2025, Vol. 534 ›› Issue (3): 107-114.doi: 10.16731/j.cnki.1671-3133.2025.03.013

• 仪器仪表/检测/监控 • 上一篇下一篇

基于双三次插值的Canny-Devernay亚像素图像边缘检测算法^*

张喜民^1,2, 詹海生²

1 陕西国际商贸学院信息工程学院,西安 712046;
2 西安电子科技大学计算机学院,西安 710071

收稿日期:2024-08-08 发布日期:2025-03-28
作者简介:张喜民,博士,教授,主要研究方向为机器视觉、计算机测控技术。詹海生,博士,副教授,主要研究方向为图像处理。E-mail:zczya@suhu.com;zhan_haisheng@vip.163.com
基金资助:
*陕西省自然科学基础研究计划项目(2024JC-YBMS-510);陕西省教育厅一般专项科研计划项目(22JK0274)

Research on Canny-Devernay subpixel image edge detection algorithm based on bicubic interpolation

ZHANG Ximin^1,2, ZHAN Haisheng²

1 School of Information Engineering,Shaanxi Institute of International Trade & Commerce, Xi’an 712046,China;
2 School of Computer Science and Technology,Xidian University,Xi’an 710071,China

Received:2024-08-08 Published:2025-03-28

摘要/Abstract

摘要： 为满足机器视觉精密尺寸测量对图像边缘深亚像素级定位和强抗噪能力的要求,提出了基于双三次插值的Canny-Devernay亚像素图像边缘检测算法。首先,采用中值滤波降低采集图像噪声;其次,通过双三次插值细分图像边缘;然后,运用最大化类间方差(Ostu)算法优化Canny-Devernay算法参数并改进轮廓生成步骤,精确提取亚像素边缘;最后基于高分辨率工业相机和高性能计算机构建实验系统,分别以OpenCV图像、USB接口插件采集图像为对象进行实验。实验结果表明,在相机标定精度为0.009 8毫米/像素的情况下,该算法边缘检测平均误差为0.006 85 mm,小于0.7像素,计算耗时偏差为7.68 ‰,其边缘定位精度、抗噪能力和算法稳定性均优于Canny算法、基于Zernike矩的算法以及Canny-Devernay算法,将用于研制某新型精密机器视觉尺寸测量设备。

关键词: 机器视觉, 边缘检测, 双三次插值, 滞后双阈值二值化, Canny-Devernay算法, 亚像素

Abstract: In order to meet the requirements of deep subpixel localization and strong noise resistance for image edge detection in machine vision precise measurement,a Canny-Devernay subpixel image edge detection algorithm based on bicubic interpolation was proposed. Firstly,the median filtering algorithm was used to reduce the noise in the acquired images. Secondly,the image edges were subdivided through bicubic interpolation. Finally,the contour generation step was optimized and Ostu algorithm was applied to obtain an adaptive threshold,which was passed into Canny-Devernay algorithm to achieve accurately extracting subpixel edges of image. An experimental system was developed by high-resolution industrial camera and high-performance computer,and experiments were carried out on the OpenCV image and the acquired images of USB interface plug-in parts as samples,which was done with camera calibration accuracy of 0.009 8 mm/pixels.The experimental results show that the average edge detection error of the proposed algorithm is 0.006 85 mm,which is less than 0.7 pixels,and the calculation time deviation is 7.68 ‰. The edge positioning accuracy,noise resistance and compute stability of the proposed algorithm were better than the Canny algorithm,the algorithm based on Zernike moments and the Canny-Devernay algorithm. The proposed algorithm can better meet the requirements of the stability,reliability and high-precision image edge detection for machine vision precise measurement,and would be used to develop a new type of machine vision dimensional precise measurement device.

Key words: machine vision, edge detection, bicubic interpolation, binary threshold with hysteresis, Canny-Devernay algorithm, subpixel

中图分类号:

TP394.1

张喜民, 詹海生. 基于双三次插值的Canny-Devernay亚像素图像边缘检测算法^*[J]. 现代制造工程, 2025, 534(3): 107-114.

ZHANG Ximin, ZHAN Haisheng. Research on Canny-Devernay subpixel image edge detection algorithm based on bicubic interpolation[J]. Modern Manufacturing Engineering, 2025, 534(3): 107-114.

参考文献

[1] 宋帅帅,黄锋,江燕斌.基于机器视觉几何量测量技术研究进展分析[J].电子测量技术,2021,44(3):22-26.
[2] 张喜民,余奇颖,张金博,等.基于机器视觉的手机尾插件精密测量方法研究[J].仪器仪表学报,2019,40(10):47-54.
[3] 杜港,佟强,侯凌燕,等.基于Canny-Franklin矩的亚像素边缘检测方法[J].计算机集成制造系统,2023,29(3):1-16.
[4] 刘明佩,朱维斌,叶树亮.基于改进Zernike矩的小模数齿轮亚像素边缘检测[J].仪器仪表学报,2018,39(8):259-267.
[5] 顾良玉,吴继薇.基于机器视觉转子冲片亚像素精度尺寸测量研究[J].计算机测量与控制,2024,32(4):29-36.
[6] 杨斌,汪志锋,徐洁.基于气门油封的亚像素边缘检测[J].计算机系统应用,2023,32(9):183-189.
[7] 吴一全,邹宇,刘忠林.基于Franklin矩的亚像素级图像边缘检测算法[J].仪器仪表学报,2019,29(5):221-229.
[8] 李锦鹏,熊显名,曾启林,等.基于三次B样条小波变换和Franklin矩亚像素级图像边缘检测算法[J].红外技术,2022,44(3):255-261.
[9] YU Y B,TANG H W,FENG X,et al.Design of multilayer cellular neural network based on memristor crossbar and its application to edge detection[J].Journal of Systems Engineering and Electronics,2023,34(3):641-649.
[10] XIE S N,TU Z W.Holistically-Nested Edge Detection[J].International Journal of Computer Vision,2017,125(13):3-18.
[11] LIU Y,CHENG M M,HU X W,et al. Richer Convolutional Features for Edge Detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,41(8):1939-1946.
[12] 李江昀,王宇浩,童朝南.一种Zernike矩的高精度板材尺寸测量方法[J].电子学报,2015,43(7):1432-1436.
[13] XIE X,GE S,XIE M,et al. An improved industrial sub-pixel edge detection algorithm based on coarse and precise location[J].Journal of Ambient Intelligence and Humanized Computing,2020,11(5):2061-2070.
[14] WANG Z C,WANG Z,HUANG N H,et al.An Improved Canny-Zernike Subpixel Detection Algorithm[J].Wireless Communications and Mobile Computing,2022(1):1-7.
[15] HUANG C J,WEI X,QIAN L,et al. Sub-pixel Edge Detection Algorithm Based On Canny-Zernike Moment Method[J].Journal of Circuits Systems and Computers,2020,29(15):205-238.
[16] 林海波.基于机器视觉薄零件高精度测量技术的研究[J].压电与声光,2015,37(2):357-360.
[17] 赵亚康.基于机器视觉的轴承密封圈尺寸测量系统研究及实现[D].南京:东南大学,2021.
[18] 韩婷婷.基于机器视觉的型材端面测量技术研究[D].成都:电子科技大学,2024.
[19] GIOI R G V,RANDALL G. A Sub-Pixel Edge Detector:an Implementation of the Canny/Devernay Algorithm[J].Image Processing On Line,2017(7):347-372.
[20] WANG H,XU X,LIU Y,et al.Real-Time Defect Detection for Metal Components:A Fusion of Enhanced Canny-Devernay and YOLOv6 Algorithms[J].Applied Sciences,2023,13(12):6898-6918.

基于双三次插值的Canny-Devernay亚像素图像边缘检测算法^*

Research on Canny-Devernay subpixel image edge detection algorithm based on bicubic interpolation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	袁奎, 付恒勋, 谌立贵, 秦东, 吴怀超, 王则皓. 轴类工件圆度误差亚像素视觉检测和评定方法研究^*[J]. 现代制造工程, 2025, 533(2): 94-100.
[2]	邓鹏, 唐文涛, 黄开明. 基于级联融合网络的密集型抓取位姿检测^*[J]. 现代制造工程, 2024, 526(7): 126-134.
[3]	姜都, 刘永, 王宸, 李伟杰, 王红霞. 基于视觉原理的链轮尺寸测量方法研究^*[J]. 现代制造工程, 2024, 523(4): 129-134.
[4]	潘俊杰, 夏如艇. 基于机器视觉的E型卡簧尺寸检测方法[J]. 现代制造工程, 2024, 520(1): 95-102.
[5]	杨泽青;张明轩;陈英姝;平恩旭;方勇;吕雅丽;高岩. 基于机器视觉的表面缺陷检测方法研究进展[J]. 现代制造工程, 2023, 511(4): 143-156.
[6]	惠翔禹;金隼;顾同成;何心;李冰;高宇星. 装载机动臂孔组同轴度视觉检测系统设计[J]. 现代制造工程, 2023, 510(3): 112-118.
[7]	钱乐平;邵中魁;沈小丽. 基于3D机器视觉的离心泵叶轮智能无序上料技术应用研究[J]. 现代制造工程, 2023, 509(2): 27-35.
[8]	聂鹏，王家明，李海伟，纪俐. 基于机器视觉的铆接高度差检测方法研究[J]. 现代制造工程, 2022, 504(9): 107-112.
[9]	李慧敏，施怡昕. 永磁电动机自动磁钢装配中的视觉系统设计[J]. 现代制造工程, 2022, 503(8): 87-92.
[10]	刘德志，曾勇，袁雨鑫，卢倩，刘聪. 基于机器视觉的火车轮对轴端标记自动识别算法研究[J]. 现代制造工程, 2022, 502(7): 113-120.
[11]	焦博，刘国宁，赵孟轩，马光岩. 基于机器视觉的亚像素精度法兰盘尺寸测量方法[J]. 现代制造工程, 2022, 502(7): 121-126.
[12]	张朝，徐志鹏，曹松晓，蒋庆，周乔君. 基于工业机器人与机器视觉的多路阀自动装配[J]. 现代制造工程, 2022, 501(6): 122-127.
[13]	程亚彬，张宏伟，王新环，郭子路，. 基于YOLO-V5的矿车桁架铆接孔定位技术研究[J]. 现代制造工程, 2022, 500(5): 115-121.
[14]	林晓平，王冠，陈学灵，刘赞丰，张雅文. 46MnVS5连杆裂解槽在机器视觉的几何尺寸检测研究[J]. 现代制造工程, 2022, 499(4): 119-127.
[15]	于福才，张丹，樊璇，曹雏清，蔡宗琰. 泵体口环装配工艺的机器视觉化研究及应用[J]. 现代制造工程, 2022, 498(3): 133-139.