[1]杜绪伟,陈 东.低比度钢板微小缺陷的图像增强和分割[J].机械与电子,2020,(12):65-69.
　DU Xuwei,CHEN Dong.Image Enhancement and Segmentation of Small Defects in Low Contrast Steel Plate[J].Machinery & Electronics,2020,(12):65-69.
点击复制

低比度钢板微小缺陷的图像增强和分割()
分享到：

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2020年12期
页码:
65-69
栏目:
智能工程
出版日期:
2020-12-18

文章信息/Info

Title:
Image Enhancement and Segmentation of Small Defects in Low Contrast Steel Plate
文章编号:
1001-2257（2020）12-0065-05
作者:
杜绪伟; 陈 东
青岛科技大学机电工程学院,山东 青岛 266061
Author(s):
DU Xuwei;  CHEN Dong
College of Electromechanical Engineering, Qingdao University of Science and Technology, Qingdao 266061, China
关键词:
低对比度; 微小缺陷; 小波变换; 图像增强; 粒子群优化算法; 最大类间方差法
Keywords:
low contrast;  micro-defects;  wavelet transform;  image enhancement;  particle swarm optimization algorithm;  Otsu method
分类号:
TP391.41
文献标志码:
A
摘要:
针对低对比度、微小的钢板表面缺陷，提出了基于图像增强的图像分割算法来有效分割和识别缺陷目标。采用小波变换与同态滤波结合算法对图像进行增强处理，不仅消除照度不均的影响，还突出了缺陷细节的信息，达到图像增强的效果。最后，利用粒子群算法优化最大类间方差法参数（PSO-Otsu）确定增强后图像的最佳阈值，并结合Canny算子进行缺陷检测。对比其他算法，该算法在检测低对比度的微小缺陷上取得了良好的效果。
Abstract:
An image segmentation algorithm based on image enhancement was proposed to effectively segment and recognize the defects of steel plate with low contrast and small surface defects. Wavelet transform and homomorphic filtering algorithm are used to enhance the image, which not only eliminates the influence of uneven illumination but also highlights the defect details to achieve the effect of image enhancement. Finally, The best threshold of enhanced image was determined by the maximum inter class variance which is optimized by particle swarm optimization (PSO-Otsu).Canny operator uses the best threshold obtained by the improved algorithm for defect detection. Compared with other algorithms, this algorithm has achieved good results in detecting small defects with low contrast.

参考文献/References:

[1]高雪梅.基于机器视觉的带钢表面缺陷检测系统研究[D].保定：河北大学,2011.
[2]LI D I, LIANG L Q, ZHANG W J.Defect inspection and extraction of the mobile phone cover glass based on the principal components analysis[J].International journal of advanced manufacturing technolo,2014,73 (9/10/11/12):1605-1614.
[3]唐庆菊,刘俊岩,王扬,.基于模糊C均值聚类和Canny算子的红外图像边缘识别与缺陷定量检测 [J].红外与激光工程,2016,45(9):274-278.
[4]XIAO L M,LI C,WU Z Z,et al.An enhancement method for X-ray image via fuzzy noise removal and homomorphic filtering[J].Neurocomputing,2016,195:56-64.
[5]SANTHI K,WAHIDA BANU R S D.Contrast enhancement by modified octagon histogram equalization[J].Signal, image and video processing 2015,9(1):73-87.
[6]李昌顺,杨浩,裴蕾.基于高密度离散小波变换的改进图像降噪方法[J].计算机工程,2012,38(1):211-214.
[7]QU Y D,CUI C S,CHEN S B,et al.A fast subpixel edge detection method using Sobel-Zernike moments algorithm[J]．Image and vision computing,2005,23 (1):11-17．
[8].激光光斑边缘检测算子的研究进展[J].量子光学学报,2019,25(1):109-116.
[9].高效Prewitt边缘检测算法的NEON实现[J].小型微型计算机系统,2018,39(11):2514-2517.
[10].基于Kirsch算子图像分割的FPGA设计与实现[J].影像科学与光化学,2019,37(4):332-335.
[11]CANNY J.A computational approach to edge detection[J].IEEE Transactions on pattern analysis and machine intelligence1986,8(6):678-698.
[12]郝欢欢,王丙龙,聂森,.基于傅里叶变换和小波分析的拖拉机振动研究[J].农机化研究,2016,38(8):232-236.
[13][14]宋森森,贾振红,杨杰,等.结合Ostu阈值法的最小生成树图像分割算法[J].计算机工程与应用,2019,55(09):178-183.
[15]KENNEDY J,EBERHART R. Particle swarm optimization[C]//Proceedings of IEEE International Conference on Neural Networks.Perth:IEEE,1995:1942-1948.
[16]OTSU N.A threshold selection method from gray-level histograms[J].IEEE transactions on systems,man and cybernetics,1979,9(1):62-66.
[17]段红燕,邵豪,张淑珍,等.一种基于Canny算子的图像边缘检测改进算法[J].上海交通大学学报,2016,50(12):1861-1865.
[18]刘克平,李西卫,隋吉雷,等.基于改进Canny算法的工件边缘检测方法[J].广西大学学报(自然科学版),2017,42(6):2022-2029.

备注/Memo

备注/Memo:
收稿日期：2020-09-10
作者简介: 杜绪伟(1993－)，男，山东聊城人，硕士,研究方向为机器人技术;陈 东(1973－)，男，山东青岛人，博士，讲师，研究方向为机电一体化及运动控制技术
更新日期/Last Update: 2020-12-18