|本期目录/Table of Contents|

[1]李浩然,陆金桂.基于分块阈值LBP算法的光学薄膜表面缺陷分割[J].南京工业大学学报(自然科学版),2020,42(05):594-599.[doi:10.3969/j.issn.1671-7627.2020.05.007]
 LI Haoran,LU Jingui.Segmentation of optical thin film surface defects based on LBP algorithm with block threshold values[J].Journal of NANJING TECH UNIVERSITY(NATURAL SCIENCE EDITION),2020,42(05):594-599.[doi:10.3969/j.issn.1671-7627.2020.05.007]
点击复制

基于分块阈值LBP算法的光学薄膜表面缺陷分割()
分享到:

《南京工业大学学报(自然科学版)》[ISSN:1671-7627/CN:32-1670/N]

卷:
42
期数:
2020年05期
页码:
594-599
栏目:
出版日期:
2020-09-20

文章信息/Info

Title:
Segmentation of optical thin film surface defects based on LBP algorithm with block threshold values
文章编号:
1671-7627(2020)05-0594-06
作者:
李浩然陆金桂
南京工业大学 机械与动力工程学院,江苏 南京 211800
Author(s):
LI Haoran LU Jingui
School of Mechanical and Power Engineering, Nanjing Tech University, Nanjing 211800, China
关键词:
光学薄膜 缺陷检测 局部二值模式(LBP) 分块离散度 全图离散度 LBP阈值
Keywords:
optical thin films defect detection local binary patterns(LBP) block dispersion global dispersion LBP threshold values
分类号:
TP242;TH744
DOI:
10.3969/j.issn.1671-7627.2020.05.007
文献标志码:
A
摘要:
为提高光学薄膜缺陷检测的能力和精度,提出一种基于局部二值模式(LBP)的改进算法。通过对采集到的图像进行分块分析,计算全图和各小块离散度,并进行对比。将分块离散度>全图离散度的视为缺陷与背景共存的模块,以该模块中间像素灰度均值作为LBP阈值进行图像处理; 分块离散度≤全图离散度的视为平稳模块,将全图灰度均值作为LBP阈值进行图像处理。实验结果表明:该算法能有效地检测出光学薄膜的缺陷,同时也避免了噪声的干扰,证明该算法用于检测光学薄膜缺陷的可行性。
Abstract:
To improve the ability and accuracy of defect detection of optical thin films, an improved algorithm based on local binary patterns(LBP)was proposed. The image was divided into blocks and computed the dispersion of each small block and the whole image for comparison. The module with block dispersion higher than global dispersion was regarded as the module with defect and background coexistence, using the average gray value of the middle pixel as the threshold value for LBP processing. The module with block dispersion lower than and equal to global dispersion was regarded as the stable module, using the average gray value of the whole image to process these module. The experimental results showed that this algorithm could effectively detect the defects of optical thin films and avoid noise interference at the same time, and the algorithm was feasible for optical thin film defect detection.

参考文献/References:

[1] TANG B,KONG J Y.WU S Q.Review of surface defect detection based on machine vision[J].Journal of Image and Graphics,2017,22(12):1640.
[2] 钟球盛,李静蓉,胡广华.用于光学薄膜缺陷检测的快速图像分割算法[J].机电工程,2011,28(10):1170.
[3] OJALA T,PIETIKAINEN M,HARWOOD D.A comparative study of texture measures with classification based on featured distributions[J].Pattern Recognition,1996,29(1):51.
[4] PIETIKÄINEN M,OJALA T,XU Z.Rotation-invariant texture classification using feature distributions[J].Pattern Recognition,2000,33(1):43.
[5] OJALA T,VALKEALAHTI K,OJA E,et al.Texture discrimination with multidimensional distributions of signed gray-level differences[J].Pattern Recognition,2001,34(3):727.
[6] 宋丁东.基于LBP的子弹表面缺陷光电检测算法研究[D].成都:电子科技大学,2015.
[7] 李云,张尤赛.基于最优Gabor滤波与局部二值模式的物体表面缺陷检测[J].现代电子技术,2015,38(9):100.
[8] TAN X Y,TRIGGS B.Enhanced local texture feature sets for face recognition under difficult lighting conditions[J].IEEE Transactions on Image Processing,2010,19(6):1635.
[9] HAFIANE A,SEETHARAMAN G,ZAVIDOVIQUE B.Median binary pattern for textures classification[C]//Proceedings of the 2007 International Conference on Image Analysis and Recognition.Montreal:Springer,2007,387.
[10] GUO Z,ZHANG L,ZHANG D,et al.Rotation invariant texture classification using adaptive LBP with directional statistical features[C]//Proceeding of the 17th IEEE International Conference on Image Processing.Hong Kong:IEEE,2010,285.
[11] GUO Z H,ZHANG L,ZHANG D.A completed modeling of local binary pattern operator for texture classification[J].IEEE Transactions on Image Processing,2010,19(6):1657.
[12] 周凯,杨路明,宋虹,等.基于多阈值局部二值模式的人脸识别方法[J].计算机工程,2009,35(17):167.
[13] 钟球盛.基于多目机器视觉的光学薄膜表面缺陷在线检测技术研究[D].广州:华南理工大学,2011.
[14] OJALA T,PIETIKAINEN M,MAENPAA T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971.
[15] 宋克臣,颜云辉,陈文辉,等.局部二值模式方法研究与展望[J].自动化学报,2013,39(6):730.
[16] GUO Z H,ZHANG L,ZHANG D.Rotation invariant texture classification using LBP variance(LBPV)with global matching[J].Pattern Recognition,2010,43(3):706.
[17] VAN DIJK A M,MARTENS J B.Subjective quality assessment of compressed images[J].Signal Processing,1997,58(3):235.

备注/Memo

备注/Memo:
收稿日期:2018-12-20
作者简介:李浩然(1993—),男,E-mail:461110412@qq.com; 陆金桂(联系人),教授,E-mail:lujg@njtech.edu.cn.
引用格式:李浩然,陆金桂.基于分块阈值LBP算法的光学薄膜表面缺陷分割[J].南京工业大学学报(自然科学版),2020,42(5):594-599.
LI Haoran, LU Jingui. Segmentation of optical thin film surface defects based on LBP algorithm with block threshold values[J].Journal of Nanjing Tech University(Natural Science Edition),2020,42(5):594-599..
更新日期/Last Update: 2020-09-24