应用像素邻接特性分析的激光边缘图像修复

谭建平1; 王宪1

doi:10.3788/OPE.20132110.2728

您当前的位置：

首页 >

文章列表页 >

应用像素邻接特性分析的激光边缘图像修复

信息科学 | 更新时间：2020-08-12

- 应用像素邻接特性分析的激光边缘图像修复
- Laser edge image inpainting based on pixel adjacency analysis
- 光学精密工程 2013年21卷第10期页码：2728-2735
- 作者机构：
  
  1. 中南大学机电工程学院，湖南长沙410083
  2. 中南大学高性能复杂制造国家重点实验室，湖南长沙 410083
- 作者简介：
- 基金信息：
  
  国家科技重大专项(No.2009ZX02205)
- DOI：10.3788/OPE.20132110.2728
  中图分类号： TP391
- 收稿日期：2013-02-27，
  
  修回日期：2013-05-08，
  
  网络出版日期：2012-10-19，
  
  纸质出版日期：2013-10-15
- 稿件说明：
移动端阅览
王宪谭建平. 应用像素邻接特性分析的激光边缘图像修复[J]. 光学精密工程, 2013,21(10): 2728-2735

TAN Jian-ping WANG Xian. Laser edge image inpainting based on pixel adjacency analysis[J]. Editorial Office of Optics and Precision Engineering, 2013,21(10): 2728-2735
王宪谭建平. 应用像素邻接特性分析的激光边缘图像修复[J]. 光学精密工程, 2013,21(10): 2728-2735 DOI： 10.3788/OPE.20132110.2728.

TAN Jian-ping WANG Xian. Laser edge image inpainting based on pixel adjacency analysis[J]. Editorial Office of Optics and Precision Engineering, 2013,21(10): 2728-2735 DOI： 10.3788/OPE.20132110.2728.

摘要

针对现有边界提取方法用于复杂工业环境的不足，提出了一种应用像素邻接特性分析的光斑边缘图像修复方法。首先，通过对边缘图像的距离变换和连通分量标记得到一张标号图像，该图像把与最近边缘距离低于某一数值的背景像素标注为边缘候选点，其他背景像素标注为独立的连通区域。然后，依据真实边缘的邻接特性对候选边缘候选点重标号，实现断裂边缘的连接。最后，从邻接特性的角度对噪声进行分类并去除，从而完成激光边缘图像的修复。实验结果表明：该方法能有效修复8 pixel的边缘缝隙并去除较大的噪声；引入的中心定位均方根（RMS）误差为0.05 pixel ，峰值(PV)误差为0.086 pixel，稳定地保持在较低的水平；单次图像修复耗时小于130 ms

实时性较好；能用于工业在线中心定位检测。

Abstract

As existing edge extracting method has its drawbacks in complex industrial environments

a laser edge image inpainting method based on pixel adjacency analysis is presented. The first step of the method is to obtain a label image by distance conversion and connected component mark for an edge image. In the label image

the background pixels whose minimum edge distances are less than a certain value are marked as edge candidate points while the rest background pixels are marked as independent connected regions. The second step is to re-label the edge candidate points based on the adjacency of real edge to connect the broken edges. And the final step is to categorize the noises as per adjacency and remove them respectively to inpaint the laser edge image. The experimental results indicate that this method can effectively inpaint a 8-pixel edge gap and remove larger noises; the introduced root-mean-square（RMS）error of centering measurement is 0.05 pixel

while the peak value（PV） error is 0.086 pixel

which show a steadily low value. Moreover

it takes less than 130 ms for an image to be inpainted one time in real-time. This method is applicable to industrial online centering measurement.

关键词

Keywords

references

WANG X, TAN J P, QUAN L Y, et al.. Real-time monitoring method for five-degrees-of-freedom of the extruder's moving parts [C].2011 International Conference on Vibration, Structural Engineering and Measurement (ICVSEM), Clausthal- Zellerfeld, 2012: 630-634.[2]肖剡军. 125MN挤压机活动部件中心偏移检测系统软件设计与应用研究[D].长沙: 中南大学机电工程学院, 2009: 8-19.XIAO Y J. System software design and applied research of the center offset measuring system for 125MN extruders moving parts [D]. Changsha: College of mechanical and electrical engineering, Central south university, 2009:8-19. (in Chinese)[3]曹万鹏,车仁生,叶东. 一种照明无关的小波多尺度相乘边缘检测方法[J].光学学报，2007,27(10):1751-1757. CAO W P, CHE R SH, YE D. Illumination-independent wavelet scale multiplication edge detection method [J]. Acta Optica Sinica,2007, 27(10):1751-1757. (in Chinese)[4]CHEN T, WU Q H, RAHMANI-TORKAMAN R. A pseudo top-hat mathematical morphological approach to edge detection in dark regions [J]. Pattern Recognition,2002, 35(1):199-210.[5]ZHAO X L. Edge detection algorithm based on multiscale product with Gaussian function [J]. Procedia Engineering, 2011,15：2650-2654.[6]董吉辉,胡企铨,孙东松. 空间激光成像跟踪系统中的图像噪声抑制技术[J].中国激光,2011,38(1):0109002.DONG J H, HU Q Q, SUN D S. Techniques of depressing image noise in laser imaging tracking system [J]. Chinese Journal of Lasers, 2011,38(1):0109002. (in Chinese)[7]付树军,阮秋琦,穆成坡,等. 基于非线性扩散滤波的边缘检测和图像测量[J].光学精密工程,2007,15(2):289-293.FU SH J, RUAN Q Q, MU CH P, et al.. Edge detection for image measurement based on nonlinear diffusion filtering[J].Opt. Precision Eng., 2007,15(2):289-293. (in Chinese)[8]FRANK Y S，CHENG S X. Adaptive mathematical morphology for edge linking [J].Information Sciences, 2004, 167(1-4):9-21.[9]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(9): 2314- 2323.DENG SH CH, LIU T G, XIAO Z X. Extraction of enclosing image edge for metallographic structure based on Canny and grayscale contour line [J].Opt. Precision Eng., 2010, 18(9): 2314-2323. (in Chinese)[10]王蒙军,阳路,王霞,等. 用简化脉冲耦合神经网络实现交通标志图像的类Euclidean距离变换类内特征提取[J].光学精密工程,2012,20(12):2751-2757.WANG M J, YANG L, WANG X, et al.. Realization of within-class feature extracting based on Euclidean-like distance transform for traffic signs using simplied PCNN [J].Opt. Precision Eng.,2012,20(12):2751-2757. (in Chinese)[11]王平,张力,周长其. 基于种子点的粘连巨噬细胞图像的分割方法[J].液晶与显示,2012,27(6):808-813.WANG P, ZHANG L, ZHOU CH Q. Segmentation method to adhesion macrophage image based on seeding point[J]. Chinese Journal of Liquid Crystals and Displays, 2012, 27(6):808-813. (in Chinese)[12]HE L F, CHAO Y Y, SUZUKI K, et al.. Fast connected-component labeling [J]. Pattern Recognition, 2009, 42(9):1977-1987.[13]吕国亮,赵曙光,赵俊. 基于三帧差分和连通性检验的图像运动目标检测新方法[J].液晶与显示,2007,22(1):87-93.LV G L, ZHAO SH G, ZHAO J. Novel method of moving object detection based on three frame differencing and connectivity checking [J]. Chinese Journal of Liquid Crystals and Displays, 2007 ,22(1):87-93. (in Chinese)[14]李红松,侯朝桢. 基于距离变换和形态学的顶点探测算法[J].电子学报,2004,32(1):38-41.LI H S, HOU CH ZH. Corner detection based on distance transform and morphology[J]. Acta Electronica Sinica, 2004, 32(1):38-41. (in Chinese)[15]王宪,谭建平,全凌云,等. 复杂工业环境下激光束中心快速精确定位方法[J].湖南大学学报：自然科学版,2012,39(12):43-49.WANG X, TAN J P, QUAN L Y, et al.. Fast and precise location method of the laser beam center point in complex industrial environment [J]. Journal of Hunan University: Natural Sciences, 2012, 39(12):43-49. (in Chinese)[16]HOOVER A, JEAN-BAPTISTE G, JIANG X. An experimental comparison of range image segmentation algorithms [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(7):673-689.

浏览量

241

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向小目标测量的通道注意力网络与系统设计

强噪声下自适应Canny算子边缘检测

基于种子点传播的快速立体匹配

自动影像测量系统关键算法

LightDiffu-DCE：基于光照强度扩散的低光照图像增强