显微视觉自动聚焦及控制策略

周丽平; 孙志峻; 张泉

doi:10.3788/OPE.20132103.0807

您当前的位置：

首页 >

文章列表页 >

显微视觉自动聚焦及控制策略

信息科学 | 更新时间：2020-08-12

- 显微视觉自动聚焦及控制策略
- Auto-focusing and control of micro-vision system
- 光学精密工程 2013年21卷第3期页码：807-812
- 作者机构：
  
  南京航空航天大学机械结构力学及控制国家重点实验室
- 作者简介：
- 基金信息：
  
  教育部新世纪优秀人才支持计划();国家重点基础研究发展计划项目();广东联合基金重点项目()
- DOI：10.3788/OPE.20132103.0807
  中图分类号： TP391;TH742.9
- 收稿日期：2012-08-24，
  
  修回日期：2012-10-18，
  
  网络出版日期：2013-03-20，
  
  纸质出版日期：2013-03-15
- 稿件说明：
移动端阅览
周丽平孙志峻张泉. 显微视觉自动聚焦及控制策略[J]. 光学精密工程, 2013,21(3): 807-812

ZHOU Li-ping SUN Zhi-jun ZHANG Quan. Auto-focusing and control of micro-vision system[J]. Editorial Office of Optics and Precision Engineering, 2013,21(3): 807-812
周丽平孙志峻张泉. 显微视觉自动聚焦及控制策略[J]. 光学精密工程, 2013,21(3): 807-812 DOI： 10.3788/OPE.20132103.0807.

ZHOU Li-ping SUN Zhi-jun ZHANG Quan. Auto-focusing and control of micro-vision system[J]. Editorial Office of Optics and Precision Engineering, 2013,21(3): 807-812 DOI： 10.3788/OPE.20132103.0807.

摘要

对自动显微镜的自动聚焦评价函数及聚焦控制策略进行了研究。首先，介绍了频域聚焦函数提升小波变换及时域聚焦函数Sobel-Tenengrad算子，通过将提升小波变换和Sobel-Tenengrad算子有机组合提出了一种新型聚焦评价函数。然后，利用离焦、正焦样本图像对自组织算法进行无监督训练，使用粒子群优化算法加速训练过程，并以经过学习的自组织映射算法作为聚焦控制器。最后，进行了显微视觉自动聚焦实验。实验结果表明：新型组合算子具有单峰性，峰值处变化陡峭，对不同样本、不同倍数物镜均可在正焦位置达到最大值，鲁棒性强；经过学习控制器后平均仅用7.6步即可完成自动聚焦，与爬山法相比，该聚焦算法不仅大大提高了聚焦速度且性能稳定，对每幅输入图像处理、识别时间约为120 ms；满足了显微视觉自动聚焦要求，获得了良好聚焦效果。

Abstract

The auto-focusing evaluation function and a controller were researched based on an automated microscopy. At first

the Discrete Wavelet Transform (DWT) and Sobel-Tenengrad function were introduced

and a new auto-focusing evaluation function was proposed by combining the DWT with the Sobel-Tenengrad operator. Then

the defocused and focused sample pictures were used to train the Self-organizing Map (SOM) algorithm in a unsupervised method

and the Particle Swarm Optimization (PSO) was used to accelerate the training process. Finally

an auto-focusing experiment was carried out by using the trained SOM controller. The experimental results show that the new auto-focusing function has the characters of single steep peak and strong robustness to different samples and objective lenses. The results also indicate that the SOM based the controller only take 7.6 steps for auto-focusing process on average

and the focusing speed and stability has been greatly improved compared with that using the mountain climbing method. Moreover

it processes or recognizes the input image only for about 120 ms. The proposed method has met the requirements of auto-focusing of micro-vision system

and obtained good results.

关键词

Keywords

references

LEE J Y, WANG Y H, LAI L J, et al.. Development of an auto-focus system based on the moir method [J]. Measurement, 2011,44(10): 1793-1800.[2]段瑞玲, 段惠波,李庆祥, 等. 基于图像处理的微装配自动调焦系统[J]. 光学精密工程, 2006,14(3): 468-472. DUAN R L, DUAN H B, LI Q X, et al.. Micro-assembly auto-focusing system based on image processing [J]. Opt. Precision Eng., 2006,14(3): 468-472. (in Chinese)[3]孙明磊,宗光华,毕树生. 基于照度优化的自动聚焦技术[J]. 光学精密工程, 2008,16(8): 1508-1514. SUN M L, ZONG G H, BI SH SH. Automatic focusing technique based on illumination optimum [J]. Opt. Precision Eng., 2008,16(8): 1508-1514. (in Chinese) [4]CHEN H C, SHIH T M, CHEN N Z, et al.. A microscope system based on bevel-axial method auto-focus [J]. Optics and Lasers in Engineering, 2008,47(5): 47-51.[5]赵辉, 鲍歌堂,陶卫. 图像测量中自动调焦函数的实验研究与分析[J]. 光学精密工程, 2004,12(5): 531-536. ZHAO H , BAO G T, TAO W. Experimental research and analysis of automatic focusing function for imaging measurement [J]. Opt. Precision Eng., 2004,12(5): 531-536. (in Chinese)[6]WEE CH Y, PARAMESRAN R. Measure of image sharpness using eigenvalues [J]. Information Sciences, 2007,177(12): 2533-2552.[7]CHEN CH Y, HWANG R CH, CHEN Y J. A passive auto-focus camera control system [J]. Applied Soft Computing, 2010,10(1): 296-303. [8]KAUTSKY J, FLUSSER J, ZITOVA B, et al.. A new wavelet-based measure of image focus [J]. Pattern Recognition Letters, 2002,23(14): 1785-1794.[9]LIAO H, MANDAL M K, COCKBURN B F. Efficient architectures for 1-D and 2-D lifting-based wavelet transforms [J]. IEEE Trans. Signal Process., 2004,52(5): 1315-1362.[10]王义文, 刘献礼,谢晖. 基于小波变换的显微图像清晰度评价函数及 3-D 自动调焦技术[J]. 光学精密工程, 2006,14(6) : 1063-1069.WANG Y W, LIU X L, XIE H. A wavelet-based focus measure and 3-D auto focusing for microscope images [J]. Opt. Precision Eng., 2006,14(6): 1063-1069. (in Chinese)[11]HUANG J T, SHEN C H, PHOONG S M, et al.. Robust measure of image focus in the wavelet domain [J]. Pattern Recognition Letters, 2002,23(14): 1785-1794.[12]LEE S Y, KUMAR Y,CHO J M, et al.. Enhanced autofocus algorithm using robust focus measure and fuzzy reasoning [J]. IEEE Trans. Circuits Syst. Video Technnol., 2008,18(9): 1237-1246.[13]HASAN SH, SHAMSUDDIN M S, YUSOB B B. Enhanced self organizing map(SOM) and particle swarm optimization(PSO) for classification [J]. Juanal Generic, 2010,5(2): 7-11.[14]CHEN CH, HAN W, FANG K L. A hybridized clustering approach using particle swarm optimization for image segmentation \[C\]. Audio, Language and Image Processing, 2008. Shanghai, P.R. China: ICALIP, 2008：1365-1368.[15]CHEN J H, YANG L R, SU M CH. Comparison of SOM-based optimization and particle swarm optimization for minimizing the construction time of a secant pile wall [J]. Automation in Construction , 2009,18(6): 844-848.

浏览量

193

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

微颗粒的三维空间跨尺度装配方法

微装配正交精确对准系统的设计

基于柔性解耦梁和显微视觉的精密同轴定位系统

面向IC封装的显微视觉定位系统

微操作机器人显微视觉系统若干问题