Please wait a minute...
Chin J Eng Design  2023, Vol. 30 Issue (1): 13-19    DOI: 10.3785/j.issn.1006-754X.2023.00.004
Design Theory and Method     
Research on workpiece contour recognition method based on surface evaluation
Sheng-hu PAN(),Lin-cheng XIE,Yun-qiang LIU,Shang-fei XU
School of Mechatronics Engineering, Southwest Petroleum University, Chengdu 610500, China
Download: HTML     PDF(3352KB)
Export: BibTeX | EndNote (RIS)      

Abstract  

The diversity of existing workpiece materials and processing methods makes the surface of the workpiece diverse, which makes it difficult for the vision system to accurately recognize the workpiece contour. Therefore, a contour recognition method suitable for different workpiece surfaces was proposed. The workpiece surface was evaluated and classified according to the ratio of texture area to convex hull area. For the workpiece with good surface quality, the high-pass linear filter was used to filter the image, and the edge of the workpiece image was extracted by the difference between the workpiece surface information and the edge information; for the workpiece with poor surface quality, an adaptive contour extraction method was adopted to recognize the image edge. Experimental results showed that the proposed method could better remove noise interference than the traditional Canny edge detection algorithm, and its contour recognition accuracy was higher. The proposed contour recognition method has good adaptability to different workpiece surfaces and has certain application value.



Key wordsworkpiece contour      surface evaluation      thinning algorithm      edge extraction     
Received: 31 March 2022      Published: 06 March 2023
CLC:  TP 751  
Cite this article:

Sheng-hu PAN,Lin-cheng XIE,Yun-qiang LIU,Shang-fei XU. Research on workpiece contour recognition method based on surface evaluation. Chin J Eng Design, 2023, 30(1): 13-19.

URL:

https://www.zjujournals.com/gcsjxb/10.3785/j.issn.1006-754X.2023.00.004     OR     https://www.zjujournals.com/gcsjxb/Y2023/V30/I1/13


基于表面评估的工件轮廓识别方法研究

现有加工工件材料和加工方式的多样性使得工件的表面情况多样,导致视觉系统难以准确识别工件轮廓,因此提出了一种适用于不同工件表面的轮廓识别方法。根据纹理区域面积与凸包面积的比值对工件表面进行评估和分类。对于表面质量较好的工件,采用高通线性滤波器对图像进行滤波处理,通过工件表面信息与边缘信息的差异实现工件图像边缘提取;对于表面质量较差的工件,采用一种自适应轮廓提取方法来识别图像边缘。实验表明,与传统的Canny边缘检测算法相比,所提出的方法能够更好地去除噪声干扰,其识别轮廓的精度更高。所提出的轮廓识别方法对不同工件表面有较好的适应性,具有一定的应用价值。


关键词: 工件轮廓,  表面评估,  细化算法,  边缘提取 
Fig.1 Standard deviation image of gray value
Fig.2 Image after threshold segmentation
Fig.3 Process of accurately extracting image edge
Fig.4 Schematic of 3×3 window template
Fig.5 Pixel node types
Fig.6 Image after removing three pixel nodes
Fig.7 Schematic diagram of edge pruning
Fig.8 Workpiece image and its processing process
Fig.9 Contour recognition result of workpiece with good surface quality
Fig.10 Image segmented by hysteresis boundary threshold
Fig.11 Image after connected domain filtering
Fig.12 Image after thinning operation
Fig.13 Contour recognition result of workpiece with poor surface quality
Fig.14 Comparison of workpiece contour accuracy recognized by different algorithms
[1]   唐路路,张启灿,胡松.一种自适应阈值的Canny边缘检测算法[J].光电工程,2011,38(5):127-132.
TANG Lu-lu, ZHANG Qi-can, HU Song. An improved algorithm for Canny edge detection with adaptive threshold[J]. Opto-Electronic Engineering, 2011, 38(5): 127-132.
[2]   倪元敏,巫茜.基于模糊形态学的图像边缘轮廓提取改进分割算法[J].西南师范大学学报(自然科学版),2013,38(12):95-100.
NI Yuan-min, WU Qian. On improvement segmentation algorithm of image edge contour extraction based on fuzzy morphology[J]. Journal of Southwest China Normal University (Natural Science Edition), 2013, 38(12): 95-100.
[3]   权威,黄华.多特征方向偏好轮廓提取算法[J].计算机辅助设计与图形学学报,2018,30(1):100-106. doi:10.3724/sp.j.1089.2018.16227
QUAN Wei, HUANG Hua. Contour extraction of multi-feature orientation preference[J]. Journal of Computer-Aided Design & Computer Graphics, 2018, 30(1): 100-106.
doi: 10.3724/sp.j.1089.2018.16227
[4]   胡敏,李梅,汪荣贵.改进的Otsu算法在图像分割中的应用[J].电子测量与仪器学报,2010,24(5):443-449. doi:10.3724/sp.j.1187.2010.00443
HU Min, LI Mei, WANG Rong-gui. Application of an improved Otsu algorithm in image segmentation[J]. Journal of Electronic Measurement and Instrumentation, 2010, 24(5): 443-449.
doi: 10.3724/sp.j.1187.2010.00443
[5]   李强,徐凯源,刘昂,等.一种连续相位板焦斑边缘轮廓的提取方法[J].强激光与粒子束,2013,25(12):3205-3209. doi:10.3788/hplpb20132512.3205
LI Qiang, XU Kai-yuan, LIU Ang, et al. A method for abstracting edge profile of continuous phase plate focus spot[J]. High Power Laser and Particle Beams, 2013, 25(12): 3205-3209.
doi: 10.3788/hplpb20132512.3205
[6]   陈芳,姚建刚,杨迎建,等.灰度拉伸及边缘扫描在红外图像分割中的应用[J].计算机工程与应用,2009,45(14):167-169.
CHEN Fang, YAO Jian-gang, YANG Ying-jian, et al. Segmentation algorithm of infrared image based on gray stretching and edge scanning[J]. Computer Engineering and Applications, 2009, 45(14): 167-169.
[7]   崔刚刚,徐安恬,周小丽.模拟雾环境下目标图像清晰度研究[J].照明工程学报,2020,31(3):31-37. doi:10.3969/j.issn.1004-440X.2020.03.006
CUI Gang-gang, XU An-tian, ZHOU Xiao-li. Research on target image sharpness in simulated fog environment[J]. China Illuminating Engineering Journal, 2020, 31(3): 31-37.
doi: 10.3969/j.issn.1004-440X.2020.03.006
[8]   田杰,徐忠民.基于ROI提取和改进SURF算法的图像匹配方法研究[J].新型工业化,2021,11(8):3-5,42.
TIAN Jie, XU Zhong-min. Research on image matching method based on ROI extraction and improved SURF algorithm[J]. The Journal of New Industrialization, 2021, 11(8): 3-5, 42.
[9]   王艺璇.机器视觉测量中的工件外轮廓提取方法[D]. 武汉:华中科技大学,2019:37-39. doi:10.30919/esmm5f615
WANG Yi-xuan. Extraction method of workpiece contour in machine vision measurement[D]. Wuhan: Huazhong University of Science and Technology, 2019: 37-39.
doi: 10.30919/esmm5f615
[10]   韦皞,张光锋,娄国伟.基于分水岭和形态学的图像特征提取方法[J].探测与控制学报,2014,36(1):63-66,70.
WEI Hao, ZHANG Guang-feng, LOU Guo-wei. Image feature extraction based on watershed algorithm and morphology[J]. Journal of Detection & Control, 2014, 36(1): 63-66, 70.
[11]   赵子润,高保禄,郭云云,等.基于改进Canny算法的噪声图像边缘检测[J].计算机测量与控制,2020,28(12):202-206,212.
ZHAO Zi-run, GAO Bao-lu, GUO Yun-yun, et al. Edge detection of noise image based on improved Canny algorithm[J]. Computer Measurement & Control, 2020, 28(12): 202-206, 212.
[12]   李柏岑.融合纹理特征的SLICT超像素算法研究[D].天津:河北工业大学,2019:16-19.
LI Bo-cen. Research on SLICT superpixel algorithm for texture feature fusion [D]. Tianjin: Hebei University of Technology,2019: 16-19.
[13]   王凯,黄山,赵瑜,等.面向图像目标提取的改进连通域标记算法[J].计算机工程与设计,2014,35(7):2438-2441,2498. doi:10.3969/j.issn.1000-7024.2014.07.035
WANG Kai, HUANG Shan, ZHAO Yu, et al. Improved algorithm of connected component labeling for image targets extraction[J]. Computer Engineering and Design, 2014, 35(7): 2438-2441, 2498.
doi: 10.3969/j.issn.1000-7024.2014.07.035
[14]   DONG Jian-wei, CHEN Yan-mei, YANG Zhi-jing, et al. A parallel thinning algorithm based on stroke continuity detection[J]. Signal, Image and Video Processing, 2017, 11(5): 873-879.
[15]   武书彦,邹建华,吴青娥,等.基于图像的目标特征提取算法[J].广西大学学报(自然科学版),2019,44(6):1658-1666.
WU Shu-yan, ZOU Jian-hua, WU Qing-e, et al. A feature extraction algorithm for target based on image[J]. Journal of Guangxi University (Natural Science Edition), 2019, 44(6): 1658-1666.
No related articles found!