齿轮视觉检测中的尺度与方向相关性联合降噪

叶树亮; 张玉德; 张炜

doi:10.3788/OPE.20142206.1622

您当前的位置：

首页 >

文章列表页 >

齿轮视觉检测中的尺度与方向相关性联合降噪

信息科学 | 更新时间：2020-08-13

- 齿轮视觉检测中的尺度与方向相关性联合降噪
- Scale and directional correlation combined denoiseing in gear visual inspection
- 光学精密工程 2014年22卷第6期页码：1622-1630
- 作者机构：
  
  中国计量学院计量测试工程学院,浙江杭州,310018
- 作者简介：
- 基金信息：
  
  国家质检公益性行业科研专项资助项目（No.201210001-3）()
- DOI：10.3788/OPE.20142206.1622
  中图分类号： TP242;TP391
- 收稿日期：2013-11-01，
  
  修回日期：2013-12-08，
  
  纸质出版日期：2014-06-25
- 稿件说明：
移动端阅览
叶树亮, 张玉德, 张炜. 齿轮视觉检测中的尺度与方向相关性联合降噪[J]. 光学精密工程, 2014,22(6): 1622-1630

YE Shu-liang, ZHANG Yu-de, ZHANG Wei. Scale and directional correlation combined denoiseing in gear visual inspection[J]. Editorial Office of Optics and Precision Engineering, 2014,22(6): 1622-1630
叶树亮, 张玉德, 张炜. 齿轮视觉检测中的尺度与方向相关性联合降噪[J]. 光学精密工程, 2014,22(6): 1622-1630 DOI： 10.3788/OPE.20142206.1622.

YE Shu-liang, ZHANG Yu-de, ZHANG Wei. Scale and directional correlation combined denoiseing in gear visual inspection[J]. Editorial Office of Optics and Precision Engineering, 2014,22(6): 1622-1630 DOI： 10.3788/OPE.20142206.1622.

摘要

建立了小模数齿轮视觉检测系统用于小模数齿轮的工业测量。针对该系统在标定过程对图像降噪的需求，提出了基于Curvelet变换的域尺度与方向相关性联合降噪算法。首先，介绍了Curvelet变换的原理和过程；根据齿轮自身的对称性特点提出了利用尺度和方向间相关性的联合降噪算法，并计算了对应的参数。然后，比较了不同噪声情况下该算法的处理效果。最后，同3种常见的降噪算法（高斯滤波，小波降噪，普通的Curvelet阈值降噪）进行了比较。结果显示：经相关性联合降噪算法处理后的峰值信噪比（PSNR）优于高斯滤波6 db以上；优于小波变换降噪3 db以上；优于阈值降噪8 db以上。处理结果表明：提出的算法可较好地保持齿轮边缘效果，可满足小模数齿轮视觉检测系统后期摄像机自标定图像质量的需求。

Abstract

A visual inspection system for small modulus gears was established to realize their industry measurement. A de-noise algorithm based on scale-correlation and direction-correlation in Curvelet transform was proposed according to the de-noising demands in system calibration. First

the theory and process of the Curvelet transform were introduced. Then

according to the gear symmetry itself

a new combined algorithm for image de-noising based on Curvelet scale-correlation and direction-correlation was proposed

the corresponding parameters were calculated

and the processing results of the algorithm were compared under different noises. Finally

the algorithm was compared with 3 de-noise methods (Gaussian filter

Wavelet De-noise and Threshold De-noise). Experimental results indicate that the Peak Signal to Noise radio(PSNR) from the combined algorithm proposed is 6 db

3 db and 8 db better than those of Gaussian filter

Wavelet De-noise and Threshold De-noise

respectively. It maintains good image edges and satisfies the image quality requirements of camera self-calibration in visual inspection systems for small modulus gears.

关键词

Keywords

references

石照耀,张万年,曲宏芬. 小模数齿轮单面啮合测量机的研制[J]. 仪器仪表学报,2011,32(4): 913-919. SHI ZH Y,ZHANG W N,QU H F. Development of measuring machine based on single-flank testing for fine-pitch gears [J]. Chinese Journal of Scientific Instrument, 2011, 32(4):913-919. (in Chinese)

王文成. 基于机器视觉的齿轮参数测量系统设计[J]. 机械传动,2011, 35(2):41-43. WANG W CH. Design of measurement system of gear parameter based on machine version [J].Journal of Mechanical Transmission, 2011,35(2):41-43.(in Chinese)

徐俊成,张莉彦,阎华. 基于机器视觉的小模数塑料齿轮的在线检测[J]. 组合机床与自动化加工技术,2011,(3):57-60. XU J CH,ZHANG L Y,YAN H. Small module plastic gear on-line detection based on machine vision [J].Modular Machine Tool & Automatic Manufacturing Technique, 2011,(3):57-60.(in Chinese)

张明照,牟建华,刘扬,等. 应用复Morlet小波变换分析条纹图相位[J]. 光学精密工程, 2012,20(3):643-650. ZHANG M ZH,MOU J H,LIU Y,et al.. Phase extraction for fringe patterns based on complex Morlet wavelet transform[J]. Opt. Precision Eng., 2012,20(3):643-650. (in Chinese)

朱明,孙继刚,梁伟,等. 四元数曲波变换多源多聚焦彩色图像融合[J]. 光学精密工程, 2013,21(10):2671-2678. ZHU M,SUN J G,LIAN W,et al.. Multiple multifocus color imae fusion usin quaternion curvelet transform [J]. Opt. Precision Eng., 2013,21(10):2671-2678. (in Chinese)

武国宁,孙娜,段庆全. 多尺度几何分析及其在去噪中的应用[J]. 计算机应用与软件,2011,28(7):64-68. WU G N, SUN N, DUN Q Q. Multi-scale geometric analysis and its application in denoising[J].Computer Applications and Software,2011,28(7):64-68(in Chinese)

李文博,罗代升. 基于Curvelet和Wavelet结合的SAR图像降噪方法[J]. 四川大学学报:工程科学版,2012,44(S1):145-149. LI W B, LUO D SH. SAR image denoising based on combined Curvelet and Wavelet [J].Journal of Sichuan University:Engineering Science Edition, 2012,44(S1):145-149.(in Chinese)

李财莲. 图像多尺度几何分析及去噪算法研究 [D]. 长沙:国防科学技术大学,2011. LI C L. Research on Image Multiscale Geometric Analysis and its Application for Image Denoising [D]. Changsha:Graduate University of National Defense Technology,2011.(in Chinese)

李文辉.基于多尺度几何分析系数相关性去噪算法研究 [D]. 济南:山东大学,2012. LI W H. Study on MGA-based Image Deniosing Algorithm using Dependence of Coefficients [D].Jinan:Shandong University,2012.(in Chinese)

张文娟,康家银. 基于多尺度分析和数学形态学融合的边缘检测[J]. 计算机应用与软件,2011,28(9):85-88. ZHANG W J, KANG J Y. Edge detection based on fusion of multi-scale analysis and mathematical morphology [J].Computer Applications and Software,2011,28(9):85-88.(in Chinese)

郁梅,易文娟,蒋刚毅. 基于Contourlet变换尺度间相关的图像去噪[J]. 光电工程,2006,33(6):73-77. YU M, YI W J, JIANG G Y. Image denoise based on inter-scale correlations of Contourlet transform[J].Opto-Electronic Engineering, 2006,33(6):73-77.(in Chinese)

朱为,李国辉,涂丹. 一种基于第2代曲波变换的尺度相关图像去噪方法[J]. 中国图象图形学报,2008,13(12):2281-2285. ZHU W, LI G H, TU D. A scale correlation image denoising method based on the second generation Curvelet transform [J].Journal of Image and Graphics, 2008,13(12):2281-2285.(in Chinese)

浏览量

322

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向机翼线缆支架的装配符合性视觉检测

EEMD结合小波阈值的光电容积脉搏波信号降噪方法及实现

EEMD结合小波阈值的光电容积脉搏波信号降噪

基于三波长相移轮廓术的表面测量降噪

瞬态流场定量测量中平面激光诱导荧光图像的降噪