首页 > 论文 > 光子学报 > 48卷 > 7期(pp:710001--1)

基于邻域向量主成分分析图像增强的弱小损伤目标检测方法

A Method for Detecting Small and Weak Defect Targets Based on Neighborhood Vector PCA Image Enhancement

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

提出了基于邻域向量主成分分析(NVPCA)图像增强的弱小损伤目标检测方法.该方法将损伤图像中的每个像素和它的8邻域像素看作一个列向量参加运算, 由每个像素生成的所有列向量构建一个9维的数据立方体, 通过PCA变换后中间像素和邻域像素之间不相关, 消除小目标和邻域像素之间的相关性, 这样9维数据立方体的主要信息将集中在第一维, 则变换后的第一维数据为NVPCA图像.另外, 使用局域对比度法对NVPCA图像再一次进行处理后, 获得了较好的图像增强效果.最后, 使用区域增长法将损伤目标从背景中分离出来.实验结果表明, 该方法能够检测损伤大小为1个像素和处于局部亮区的损伤目标, 满足了在线光学元件损伤检测光学系统对于损伤目标精度的要求.

Abstract

A method for detecting small and weak damaged targets based on Neighborhood Vector PCA (NVPCA) image enhancement was proposed. The main idea is that each pixel and its 8 neighborhood pixels in the damaged image are treated as a column vector to participate in the operation. All column vectors generated by each pixel will construct a 9-dimensional data cube. After PCA transformation, the correlation between the middle and neighborhood pixels is eliminated, so that the main information of the 9-dimensional data cube will be set in the first dimension, and the transformed first dimension data is NVPCA image. When the NVPCA image is processed again by LCM method, a better image enhancement effect is obtained. In addition, the region growth method is used to separate the damage target from background. The experimental results show that the method can detect the damage target with the size of 1 pixel and located in local bright area, and meet the requirement of on-line optical damage detection system for the accuracy of the damage target.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/gzxb20194807.0710001

基金项目:国家自然科学基金(Nos. 11327303, 61405244), 国家高技术研究与发展计划(No. 051Z331BOA)

收稿日期:2018-12-29

修改稿日期:2019-05-20

网络出版日期:--

作者单位    点击查看

王拯洲:中国科学院西安光学精密机械研究所, 西安 710119
李刚:中国科学院西安光学精密机械研究所, 西安 710119
王伟:中国科学院西安光学精密机械研究所, 西安 710119
夏彦文:中国工程物理研究院 激光聚变研究中心, 四川 绵阳 621900
王力:中国科学院西安光学精密机械研究所, 西安 710119
谭萌:中国科学院西安光学精密机械研究所, 西安 710119

联系人作者:王拯洲(azhou_china@126.com)

备注:王拯洲(1976-), 男, 副研究员, 博士, 主要研究方向为信号与信息处理.

【1】PENG Zhi-tao, WEI Xiao-feng, YUAN Hao-yu, et al. Signalnoise ratio of total internal reflection edge illumination for optics damage inspection[J]. Infrared and laser Engineering, 2011, 40(6): 1111-1114.
彭志涛, 魏晓峰, 元浩宇, 等.全内反射照明光学元件损伤检测信噪比分析[J]. 红外与激光工程,2011, 40(6): 1111-1114.

【2】FENG Bo, LIU Bing-guo, CHEN Feng-dong, et al. Final optics damage online inspection system for ICF[J]. Infrared and Laser Engineering, 2013, 42(9): 2519-2524.
冯博, 刘炳国, 陈凤东, 等.ICF终端光学元件损伤在线检测装置的研究[J] . 红外与激光工程, 2013, 42(9):2519-2524.

【3】MALLAT K, TRILLO C. Background elimination and interferometric capability in optical coherence tomography by a nonlinear optical gating based on type-II second-harmonic generation[J]. Applied Optics, 2015, 54(1): 650-656.

【4】BLISSE, SALMON T, DAVIS D, et al. Laser control systems[R]. UCRL-LR-105821-97-3, University of California, Lawrence Livermore National Laboratory, USA, March 1997.

【5】ZHANG Ji, LI Da-hai. Algorithm of optics damage inspection from its dark-field image[J]. Chinese Journal of Lasers, 2006, 33(8): 1109-1112.
张际, 李大海. 光学元件损伤暗场成像检测的算法[J]. 中国激光,2006,33(8): 1109-1112.

【6】LI Fu-ming, LI Da-hai, PENG Zhi-tao, et al. A study on target extraction automatically from the dark-field image of optics damage[J]. Laser Journal, 2008, 29(2): 25-27.
李付明, 李大海, 彭志涛, 等. 光学元件损伤暗场图像中的目标自动提取研究[J] . 激光杂志, 2008, 29(2):25-27.

【7】XIE Ya-ping, SUN Zhi-hong, CHENG Ze, et al. Image processing in online inspection of damage in optics[J]. High Power Laser and Particle Beams, 2006, 18(7): 1085-1089.
谢亚平, 孙志红,成泽, 等. 光学元件损伤的在线检测中的图像处理[J]. 强激光与粒子束, 2006, 18(7): 1085-1089.

【8】KEGELMEYER L M, FONG P W, GLENN S M, et al. Local Area Signal-to-Noise Ratio (LASNR) algorithm for image segmentation[C]. Optics and Photonics for Information Processing, San Diego, CA, United states, 2007.

【9】FENG Bo, CHEN Feng-dong, LIU Bing-guo, et al. Segmentation of small defects in final optics damage online inspection images[C]. IEEE International Conference on Image Analysis and Signal Processing, 2012, 11: 110-113.

【10】CHEN C L P, LI H, WEI Y T, et al. A local contrast method for small infrared target detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(1): 574-581.

【11】WANG Gang, CHEN Yong-guang, YANG Suo-chang, et al. Detection of infrared dim small target based on image patch contrast[J]. Optics and Precision Engineering, 2015, 23(5): 1424-1432
王刚, 陈永光, 杨锁昌,等. 采用图像块对比特性的红外弱小目标检测[J]. 光学精密工程, 2015, 23(5): 1424-1432.

【12】ZHANG Bo, NI Kai-zao, WANG Lin-jun, et al. New algorithm of detecting optical surface imperfection based on background correction and image segmentation[J]. Acta Optica Sinica, 2016, 36(9): 09911004
张博, 倪开灶, 王林军,等. 基于背景校正和图像分割定量分析光学元件表面疵病的新算法[J]. 光学学报, 2016, 36(9): 09911004.

【13】TIAN Yu-ting, WU Rong, YANG Ye. Optical damage inspection based on local signal enhancement[J]. Chinese Journal of Lasers, 2018, 45(11): 1104001.
田玉婷, 邬融, 杨野. 基于局域邻域增强的光学元件损伤检测[J]. 中国激光, 2018, 45(11): 1104001.

【14】AGARWAL A, ISSAC A,DUTTA M K. A region growing based imaging method for lesion segmentation from dermoscopic images[C]. IEEE Uttar Pradesh Section International Conference on Electrical. Computer and Electronics(UPCON), 2017: 632-637.

【15】GUO Hai-tao,TIAN Tan, WANG Lian-yu. Image segmentation using the maxiumu entropy of the two dimensional boound histogram[J]. Acta Optica Sinica, 2006, 27(4): 506-509.
郭海涛, 田坦, 王连玉. 利用二维属性直方图的最大熵的图像分割方法[J] . 光学学报, 2006, 27(4): 506-509.

【16】AI Jia-qiu, QI Xiang-yang, LIU Fan, et al. Application of EMD-based speckle reduction and tophat transform in preprocessing of ship detection[J]. Journal of the Graduate School of the Chinese Academy of Sciences, 2010, 27(4): 517-822.
艾加秋, 齐向阳, 刘凡, 等. 经验模式分解去斑和顶帽变换在舰船检测预处理中的应用[J] .中国科学院研究生院学报, 2010, 27(4): 517-822.

引用该论文

WANG Zheng-zhou,LI Gang,WANG Wei,XIA Yan-wen,WANG Li,TAN Meng. A Method for Detecting Small and Weak Defect Targets Based on Neighborhood Vector PCA Image Enhancement[J]. ACTA PHOTONICA SINICA, 2019, 48(7): 0710001

王拯洲,李刚,王伟,夏彦文,王力,谭萌. 基于邻域向量主成分分析图像增强的弱小损伤目标检测方法[J]. 光子学报, 2019, 48(7): 0710001

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF