[1]刘孝星,郑力新,周凯汀,等.采用图像处理的胶囊尺寸缺陷检测方法[J].华侨大学学报(自然科学版),2017,38(5):716-720.[doi:10.11830/ISSN.1000-5013.201505045]
　LIU Xiaoxing,ZHENG Lixin,ZHOU Kaiting,et al.Detection Method of Capsule Size Defect Using Image Processing[J].Journal of Huaqiao University(Natural Science),2017,38(5):716-720.[doi:10.11830/ISSN.1000-5013.201505045]
点击复制

采用图像处理的胶囊尺寸缺陷检测方法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第38卷
期数:
2017年第5期
页码:
716-720
栏目:
出版日期:
2017-09-20

文章信息/Info

Title:
Detection Method of Capsule Size Defect Using Image Processing
文章编号:
1000-5013(2017)05-0716-05
作者:
刘孝星1;  郑力新2;  周凯汀1;  吴哲2;  林立峰1
1. 华侨大学 信息科学与工程学院, 福建 厦门 361021; 2. 华侨大学 工学院, 福建 泉州 362021
Author(s):
LIU Xiaoxing1;  ZHENG Lixin2;  ZHOU Kaiting1;  WU Zhe2;  LIN Lifeng1
1. College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China; 2. College of Engineering, Huaqiao University, Quanzhou 362021, China
关键词:
尺寸缺陷;  胶囊;  图像处理;  区域分割
Keywords:
size defect;  capsule;  image processing;  region segmentation
分类号:
TP391
DOI:
10.11830/ISSN.1000-5013.201505045
文献标志码:
A
摘要:
针对透明胶囊的成像特点,提出一种实时性好、健壮性较强的结合阈值分割、腐蚀、轮廓提取及区域填充的图像提取算法.利用旋转和一阶差分分割胶囊本体,通过最小包围矩形测量胶囊的尺寸,并与公认标准进行对比,从而判别胶囊是否存在尺寸缺陷.实验结果表明:胶囊图像提取和尺寸缺陷识别算法的平均漏检率为6.38%,平均误检率为4.13%.
Abstract:
In view of the characteristics of transparent capsule image, this paper proposed the image extraction algorithm combining with threshold segmentation, corrosion, contour extraction and region filling with good real-time and strong robustness. Then by using rotating and first-order difference divided capsule ontology, through the minimum bounding rectangle measured the size of capsule, compared with generally accepted standards we can distinguish whether capsule exists size defect. The experimental results show that: the average missing rate of capsule image extraction and the size defect recognition algorithm was 6.38%, the average error rate was 4.13%.

参考文献/References:

[1] ISLAM M J,AHMADI M,SID-AHMED M A.Image processing techniques for quality inspection of gelatin capsules in pharmaceutical applications[C]//International Conference on Control, Automation, Robotics and Vision.Washington D C:IEEE Press,2008:862-867.
[2] MURAI T,MORIMOTO M,FUJII K.A visual inspection system for medical capsules[C]//International Conference on Systems, Man, and Cybernetics.Washington D C:IEEE Press,2012:1433-1437.
[3] 王娟,周永霞,徐冰俏.图像处理在胶囊外形缺陷检测中的应用[J].中国计量学院学报,2012,23(3):239-245.
[4] WANG Dejiang,ZHANG Tao.Noise analysis and measurement of time delay and integration charge coupled device[J].Chinese Physics B,2011,20(8):352-357.
[5] 杨文博,马天玮,刘剑.非局部变分修复法去除高密度椒盐噪声[J].中国光学,2013,6(6):876-884.
[6] 李刚,范瑞霞.一种改进的图像中值滤波算法[J].北京理工大学学报(自然科学版),2002,22(3):376-378.
[7] ROSENFELD A,PFALTZ J L.Sequential operations in digital picture processing[J].Journal of the ACM,1966,13(4):471-494.
[8] HARALOCK R M,SHAPIRO L G.Computer and robot vision[M].New Jersey:Prentice Hall,1991:57-64.
[9] IRANI M,ANANDAN P,BERGEN J,et al.Efficient representations of video sequences and their applications[J].Signal Processing: Image Communication,1996,8(4):327-351.
[10] 吴恒山,段雄文,李晨阳.叶结点编码四叉树的邻域寻找算法[J].计算机应用,2005,25(11):2624-2626.
[11] 周秀芝,陈洋,胡文婷.基于交叉点的树遍历二值图像边界跟踪算法[J].计算机应用与软件,2014,31(2):230-232.
[12] 王福生,齐国清.二值图像中目标物体轮廓的边界跟踪算法[J].大连海事大学学报,2006,32(1):62-64.
[13] ZHOU Zhiwei,LI Linlin,TAN C L.Edge based binarization for video text images[C]//International Conference on Pattern Recognition.Washington D C:IEEE Press,2010:133-136.
[14] ADAMS R,BISCHOF L.Seeded region growing[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,16(6):641-647.

备注/Memo

备注/Memo:
收稿日期: 2015-05-25
通信作者: 郑力新(1967-),男,教授,博士,主要从事工业自动化技术的研究.E-mail:1275373176@qq.com.
基金项目: 福建省科技厅资助项目(2013H2002)
更新日期/Last Update: 2017-09-20