[1]李敏,罗洪艳,郑小林,等.一种改进的最大类间方差图像分割法[J].南京理工大学学报(自然科学版),2012,36(02):332-337.
 LI Min,LUO Hong-yan,ZHENG Xiao-lin,et al.Image Segmentation Based on Improved Otsu Algorithm[J].Journal of Nanjing University of Science and Technology,2012,36(02):332-337.
点击复制

一种改进的最大类间方差图像分割法
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
36卷
期数:
2012年02期
页码:
332-337
栏目:
出版日期:
2012-04-30

文章信息/Info

Title:
Image Segmentation Based on Improved Otsu Algorithm
作者:
李敏; 罗洪艳; 郑小林; 谭立文; 朱文武;
重庆大学生物工程学院; 第三军医大学基础部;
Author(s):
LI Min1LUO Hong-yan1ZHENG Xiao-lin1TAN Li-wen2ZHU Wen-wu1
1.Bioengineering College,Chongqing University,Chongqing 400030,China; 2.Department of Anatomy,Third Military Medical University,Chongqing 400038,China
关键词:
最大类间方差(大津法) 图像分割 阈值 白质 开运算
Keywords:
maximum between-duster variance(Otsu) image segmentation threshhold white matters open operation
分类号:
TP391.41
摘要:
该文根据脑部切片图像中白质的特点,将均方差因素引入传统分割方法,提出了一种改进的最大类间方差图像分割方法。采用连通域标记进行图像预分割,借助形态学的开运算进行滤波处理,根据改进的最大类间方差分割原理进行白质提取。将该方法与传统最大类间方差法对序列脑切片的白质分割结果进行定性比较,并借助漏检率和误检率指标进行定量评估,发现两种方法的平均漏检率均约为0.03,平均误检率分别为0.251和0.026,表明该方法能够综合利用图像的区域特性和边缘特性,分割更加准确有效。
Abstract:
According to the features of white matter in the human brain slice images,an improved maximum between-cluster variance(Otsu)algorithm for the image segmentation is proposed by introducing the average variance into the conventional Otsu method.The images are pre-segmented by the connected component labeling method and then filtered by means of the open operation of morphology.Finally,the improved Otsu theory is applied to extract the white matter from the slice images.The proposed algorithm is compared with the conventional Otsu algorithm in terms of their performances on the segmentation of white matter in sequential slice images qualitatively,and evaluated quantitatively by using the missed detection rate and the false detection rate.The average missed detection rates of the two methods are all 0.03 around,and the average false declection are 0.026 and 0.251 respectively.The results indicate that the improved Otsu method characterized by the combination of the region information and edge information can lead to more accurate and effective segmentation.

参考文献/References:

[1] Li Qiyu,Zhang Shaoxiang,Heng Phengann,et al. Segmentation and three-dimension reconstruction of Chinese digitized human cerebrum[J]. Computerized Medical Imaging and Graphics, 2006, 30: 89-94.
[2] 陈允杰,张建伟,王利,等. 基于改进的Mean Shift 算法虚拟人脑图像分割[J]. 计算机辅助设计与图形学学报, 2008, 20( 1) : 55-60.
[3] 郑小林,李敏,罗洪艳,等. 基于数学形态学的新方法在脑组织分割中的应用[J]. 仪器仪表学报, 2010, 31( 2) : 464-469.
[4] 石澄贤,王平安,夏德深. Snakes 外力场的改进及其左心室MRI 的精确分割[J]. 南京理工大学学报, 2006, 30( 1) : 76-81.
[5] Huang Dengyuan,Wang Chiahung. Optimal multi-level thresholding using a two-stage otsu optimization approach[J]. Pattern Recognition Letters,2009,30: 275-284.
[6] Otsu N. A threshold selection method from gray-level histogram[J]. IEEE Trans Systems Man Cybern, 1979,9 ( 1) , 62-66.
[7] 朱煜,江林佳,肖玉玲. 材料图像目标粘连点定位与分割方法研究[J]. 南京理工大学学报, 2008, 32( 1) : 110-114.
[8] 李惠光,姚磊,石磊. 改进的Otsu 理论在图像阈值选取中的应用[J]. 计算机仿真, 2007, 24( 4) : 216-222.
[9] 胡斌,宫宁生. 一种改进的Otsu 阈值分割算法[J].微电子学与计算机, 2009, 26( 12) : 153-156.
[10] 徐建东,蒋野,孙迎春,等. 基于改进的形态学算子的灰度图像边缘检测[J]. 佳木斯大学学报( 自然科学版) , 2009, 27( 6) : 857-860.

相似文献/References:

[1]陆宝春,李建文,王婧,等.基于特征差异性的荧光磁粉探伤图像分割算法[J].南京理工大学学报(自然科学版),2011,(06):797.
 LU Bao-chun,LI Jian-wen,WANG Jing,et al.Feature Difference Based Image Segmentation Algorithm for Fluorescent Magnetic Detection[J].Journal of Nanjing University of Science and Technology,2011,(02):797.
[2]陆宝春,李建文,陈吉朋,等.荧光磁粉探伤自动缺陷识别方法研究[J].南京理工大学学报(自然科学版),2010,(06):803.
 LU Bao-chun,LI Jian-wen,CHEN Ji-peng,et al.Automatic Flaw Recognition Method of Fluorescent Magnetic Detection[J].Journal of Nanjing University of Science and Technology,2010,(02):803.
[3]李 峰*,徐 诚,任国全,等.基于数学形态学的铁谱磨粒图像分割研究[J].南京理工大学学报(自然科学版),2005,(01):70.
 LI Feng,XU Cheng,REN Guo-quan,et al.Image Segmentation of Ferrography Wear Particles Based On Mathematical Morphology[J].Journal of Nanjing University of Science and Technology,2005,(02):70.
[4]娄震,胡钟山,杨静宇.支票自动处理系统中的图像处理及识别[J].南京理工大学学报(自然科学版),1999,(03):85.
 LouZhen HuZhongshan YangJingyu.Applications of Image Processing and Recognition Technology in an Automatic Bankcheck Processing System[J].Journal of Nanjing University of Science and Technology,1999,(02):85.
[5]石澄贤,等.Snakes外力场的改进及其左心室MRI的精确分割[J].南京理工大学学报(自然科学版),2006,(01):76.
 SHI Cheng-xian,WANG Ping- an,et al.Improved External Force Field for Snakes and Accurate Segmentation of Left Ventricle MRI[J].Journal of Nanjing University of Science and Technology,2006,(02):76.
[6]陈沅涛,徐蔚鸿,吴佳英,等.基于增量学习向量SVM方法的图像分割应用[J].南京理工大学学报(自然科学版),2014,38(01):6.
 Chen Yuantao,Xu Weihong,Wu Jiaying,et al.Image segmentation application based on incremental learning vector SVM algorithm[J].Journal of Nanjing University of Science and Technology,2014,38(02):6.
[7]廖传柱,张 旦,江铭炎.基于ABC-PCNN模型的图像分割[J].南京理工大学学报(自然科学版),2014,38(04):558.
 Liao Chuanzhu,Zhang Dan,Jiang Mingyan.Image segmentation based on ABC-PCNN model[J].Journal of Nanjing University of Science and Technology,2014,38(02):558.
[8]郭东岩,赵春霞,李军侠,等.结合图像显著与灰度不一致性的目标自动提取[J].南京理工大学学报(自然科学版),2014,38(05):701.
 Guo Dongyan,Zhao Chunxia,Li Junxia,et al.Image saliency and intensity inhomogeneity based automatic object extraction[J].Journal of Nanjing University of Science and Technology,2014,38(02):701.
[9]王 鑫,胡洋洋,杨慧中.基于迭代腐蚀的粘连细胞图像分割研究[J].南京理工大学学报(自然科学版),2016,40(03):285.[doi:10.14177/j.cnki.32-1397n.2016.40.03.006]
 Wang Xin,Hu Yangyang,Yang Huizhong.Segmentation of adherent cell image based on iterative erosion[J].Journal of Nanjing University of Science and Technology,2016,40(02):285.[doi:10.14177/j.cnki.32-1397n.2016.40.03.006]
[10]许 芹,唐敦兵,蔡祺祥.改进的快速模糊C均值聚类图像分割算法[J].南京理工大学学报(自然科学版),2016,40(03):309.[doi:10.14177/j.cnki.32-1397n.2016.40.03.010]
 Xu Qin,Tang Dunbing,Cai Qixiang.Improved fast fuzzy C-means clustering algorithm for image segmentation[J].Journal of Nanjing University of Science and Technology,2016,40(02):309.[doi:10.14177/j.cnki.32-1397n.2016.40.03.010]

备注/Memo

备注/Memo:
国家自然科学基金(60771025;30900323);中央高校基本科研业务费资助项目(CDJXS10231122)
更新日期/Last Update: 2012-10-12