[1]吴文艺,崔长彩,叶瑞芳,等.采用二次灰度直方图的砂轮磨粒图像阈值分割[J].华侨大学学报(自然科学版),2016,37(4):422-426.[doi:10.11830/ISSN.1000-5013.201604006]
 WU Wenyi,CUI Changcai,YE Ruifang,et al.Image Segmentation Method Using Second Time Gray Level Histogram of Connected Component Labeling of Grinding Wheel Abrasives Grains[J].Journal of Huaqiao University(Natural Science),2016,37(4):422-426.[doi:10.11830/ISSN.1000-5013.201604006]
点击复制

采用二次灰度直方图的砂轮磨粒图像阈值分割()
分享到:

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

卷:
第37卷
期数:
2016年第4期
页码:
422-426
栏目:
出版日期:
2016-07-04

文章信息/Info

Title:
Image Segmentation Method Using Second Time Gray Level Histogram of Connected Component Labeling of Grinding Wheel Abrasives Grains
文章编号:
1000-5013(2016)04-0422-05
作者:
吴文艺1 崔长彩1 叶瑞芳2 张勇贞1 余卿2
1. 华侨大学 制造工程研究院, 福建 厦门 361021;2. 华侨大学 机电及自动化学院, 福建 厦门 361021
Author(s):
WU Wenyi1 CUI Changcai1 YE Ruifang2 ZHANG Yongzhen1 YU Qing2
1. Institute of Manufacturing Engineering, Huaqiao University, Xiamen 361021, China; 2. College of Mechanical Engineering and Automaton, Huaqiao University, Xiamen 361021, China
关键词:
金刚石磨粒 区域标记 灰度直方图 阈值分割
Keywords:
diamond grain component labeling gray histogram threshold segmentation
分类号:
TP391.41
DOI:
10.11830/ISSN.1000-5013.201604006
文献标志码:
A
摘要:
为了解决金刚石砂轮表面磨粒灰度直方图阈值分割方法对区域划分存在误分割的缺陷,提出一种基于二次灰度直方图连通区域标记磨粒图像分割方法.首先,将原始金刚石磨粒图像转换为灰度图像,并对其滤波处理消除噪声.其次,设定阈值完成第一次直方图阈值分割,消除较小结构暗细节.然后,标记各个连通区域,填上不同的颜色.最后,设定阈值完成第二次直方图阈值分割,获取感兴趣目标磨粒区域.结果表明:文中方法可将感兴趣目标磨粒与背景分离,得到较好的分割效果和较高的分割效率.
Abstract:
In this work, an approach based on two gray levels histogram connected components labeling was proposed to reduce the undesirable effects of blurred segmentation of abrasive grains on the surface of diamond grinding wheels using traditional gray histogram method. This developed approach includes following steps. Firstly, an original diamond grain image was transformed into gray image and the noise was filtered and removed. Secondly, the obtained grey image was segmented by setting a proper threshold value to eliminate smaller structures. Thirdly, different connected components were labeled with different colors. Finally, another threshold was set to complete the second histogram segmentation and extract the target grain region of interests. A case study indicated that the proposed method can precisely and efficiently segment the target grains from background.

参考文献/References:

[1] 周丽君.基于垂直扫描白光干涉测量法的砂轮磨粒测量及评定[D].厦门:华侨大学,2013:1-16.
[2] KHAN J F,BHUIYAN M A,ADHAMI R R.Image segmentation and shape analysis for road-sign detection[J].IEEE Transactions on Intelligent Transportation Systems,2011,12(1):83-96.
[3] DESHMUKH K S.Color image segmentation: A review[C]//Society of Photo-Optical Instrumentation Engineers Conference Series.Singapore:ISPE,2010:7546(4-6).
[4] 黄长专,王彪,杨忠.图像分割方法研究[J].计算机技术与发展,2009,19(6):76-79.
[5] 李淼,杨恢先,张建波,等.改进二维直方图区域划分的阈值分割方法研究[J].光电子·激光,2013,24(7):1426-1433.
[6] 钱卫星,黄丽亚.二维Otsu自适应阈值快速算法的改进[J].华侨大学学报(自然科学版),2015,36(4):427-431.
[7] AL-KHISHALI M,AL-JUBOORI H.Automatic identification of grains of material samples[C]//International Conference on Information Society.Toronto:IEEE Press,2013:42-47.
[8] 梁华为.直接从双峰直方图确定二值化阈值[J].模式识别与人工智能,2002,15(2):253-256.
[9] 卢建华.基于直方图阈值法的遥感图像分割算法研究[D].福州:福建农林大学,2013:29-31.
[10] 阳树洪.灰度图像阈值分割的自适应和快速算法研究[D].重庆:重庆大学,2014:4-26.
[11] 张立国,杨瑾,李晶,等.基于小波包和数学形态学结合的图像特征提取方法[J].仪器仪表学报,2010,31(10):2285-2290.

相似文献/References:

[1]张桂全.单颗金刚石磨粒切削面积的推导[J].华侨大学学报(自然科学版),2002,23(4):399.[doi:10.3969/j.issn.1000-5013.2002.04.014]

备注/Memo

备注/Memo:
收稿日期: 2015-11-13
通信作者: 崔长彩(1972-),女,教授,博士,主要从事精密测量技术及光学仪器的研究.E-mail:cuichc@hqu.edu.cn.
基金项目: 国家自然科学基金资助项目(51475176, 51505162); 华侨大学研究生科研创新能力培育计划资助项目(1400203055)
更新日期/Last Update: 2016-07-20