广西师范大学学报（自然科学版） ›› 2016, Vol. 34 ›› Issue (4): 93-100.doi: 10.16088/j.issn.1001-6600.2016.04.014

• 广西高校优秀中青年骨干教师培养工程论坛 • 上一篇    下一篇

基于改进的SLIC区域合并的宫颈细胞图像分割

夏海英1,2,3,金凯跃1,邓帅飞1,李建辉1   

  1. 1.广西师范大学电子工程学院,广西桂林541004;
    2.广西师范大学省部共建药用资源化学与药物分子工程国家重点实验室, 广西桂林541004;
    3.桂林电子科技大学广西自动检测技术与仪器重点实验室,广西桂林541004
  • 收稿日期:2016-04-15 出版日期:2016-07-18 发布日期:2018-07-23
  • 通讯作者: 夏海英(1983—),女,山东聊城人,广西师范大学副教授,博士。E-mail:xhy22@gxnu.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(21327007);广西自然科学基金资助项目(2013GXNSFBA019278)

Cervical Cell Images Segmentation Based on Improved SLIC Region Merging

XIA Haiying1,2,3,JIN Kaiyue1,DENG Shuaifei1,LI Jianhui1   

  1. 1.College of Electronic Engineering Guangxi Normal University, Guilin Guangxi 541004, China;
    2. Key Laboratory for the Chemistry ＆ Molecular Engineering of Medicinal Resources, Guangxi Normal University, Guilin Guangxi 541004, China;
    3. Guangxi Key Laboratory of Automatic Detecting Technology ＆ Instruments, Guilin University of Electronic Technology, Guilin Guangxi 541004,China
  • Received:2016-04-15 Online:2016-07-18 Published:2018-07-23

PDF (PC)

23

摘要： 针对现有细胞图像分割算法对噪声敏感,传统SLIC(simple linear iterative clustering)算法对边界分割不精确的问题,提出一种基于改进的SLIC融合区域合并的方法:首先对宫颈细胞图像进行均值漂移处理,消除细微噪声点;然后进行二维Otsu自适应阈值处理得到初始轮廓,应用SLIC算法得到超像素区域,并融合到原图中完成初始分割;最后,在初始分割图中进行初略标记获得交互信息,利用最大相似准则进行合并,不需要预先设定分割阈值,没有被标记的背景区域将成功合并到标记的背景区域,同时,没有被标记的目标区域会被识别出,有效地阻止与背景区域合并。对宫颈细胞图像进行大量的细胞质分割实验,结果表明本文算法能够在较短时间内准确识别出宫颈细胞的细胞质边缘。

关键词: 超像素, 图像分割, 初始轮廓, 区域合并, 最大相似度

Abstract: As the existing cell images segmentation algorithms are sensitive to noise and traditional SLIC(simple linear iterative clustering) algorithm can not divide boundary precisely, an improved SLIC method based on region merging is proposed to resolve the problems. First, the mean shift treatment is used to eliminate noise on the cervical cell images, then the two-dimensional otsu adaptive threshold processing is conducted to abtain the initial contour, then based on SLIC algorithm the superpixel region is obtained, and the superpixel regions are fused to the original image to complete the initial segmentation. Finally, in the initial segmentation map, the initial mark is used to obtain the mutual information, and the maximum similarity criterion is used to merge. In this way, no present threshold is needned. The non-marker background regions are merged with labeled automatically, while the non-marker object regions are identified and avoided from being merged with background. Several experiments of dividing the cytoplasm are conducted for cervical cells images. The proposed algorithm can extract cytoplasm from a single-cell cervical smear image more accurately in a relatively short time.

Key words: superpixel, image segmentation, initial contour, region merging, maximal similarity

中图分类号: 

  • TP391.4
[1] MOO E K, ABUSARA Z, OSMAN N A A, et al. Dual photon excitation microscopy and image threshold segmentation in live cell imaging during compression testing[J]. Journal of Biomechanics, 2013, 46(12):2024-2031.
[2] XU C Y, PRINCE J L. Snakes, shapes and gradient vector flow[J]. IEEE Trans on Image Pocessing, 1998, 7(3):359-369.
[3] LI K,LU Z,LIU W Y,et al.Cytoplasm and nucleus segmentation in cervical smear images using Radiating GVF Snake[J]. Pattern Recognition, 2012, 45(4):1255-1246.
[4] REN X F,MALIK J.Learning a classification model for segmentation[C]//Proceeding of the 9th IEEE International Conference on Computer Vision. Piscataway NJ:IEEE Press, 2003:10-17.
[5] FELZENSZWALB P F, HUTTENLOCHER D P. Efficient graph-based image segmentation[J]. International Journal of Computer Vision, 2004,59(2):167-181.
[6] 张微,汪西莉.基于超像素的条件随机均图像分类[J].计算机应用,2012, 32(5):1272-1275.
[7] SHI Jianbo, MALIK J. Normalized cuts and image segmentation[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,2000,22(8):888-905.
[8] 谭乐怡, 王守觉. 基于双重超像素集的快速路径相似度图像分割算法[J].自动化学报, 2013, 39(10):1653-1664.
[9] 王春瑶, 陈俊周, 李炜. 超像素分割算法研究综述[J]. 计算机应用研究, 2014,31(1) :6-12.
[10] 饶倩,文红,喻文,等.超像素及其应用综述[J]. 电脑与信息技术,2013,21(5):1-3.
[11] ACHANTA R, SHAJI A, SMITH K, et al. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2012, 34(11):2274-2282.
[12] LUCCHI A, SMITH K, ACHANTA R, et al. A fully automated approach to segmentation of irregularly shaped cellular structures in EM images[C]//Medical Image Computing and Computer-Assisted Intervention. Berlin:Springer-Verlag, 2010:463-471.
[13] COMANICIU D,RAMESH V,MEER P. Kernel-based object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[14] LUCHHI A, SMITH K, ACHANTA R, et al. Supervoxel-based segmentation of mitochondria in EM image stacks with learned shape features[J]. IEEE Trans on Medical Imaging, 2012, 31 (2):474-486.
[15] 张亚亚,刘小伟,刘福太,等.基于改进SLIC方法的彩色图像分割[J].计算机工程,2015,41(4):205-209.
[1] 王勋, 李廷会, 潘骁, 田宇. 基于改进模糊C均值聚类与Otsu的图像分割方法[J]. 广西师范大学学报（自然科学版）, 2019, 37(4): 68-73.
[2] 张新明, 张玉珊, 李振云. 一种改进的矩不变图像分割方法[J]. 广西师范大学学报（自然科学版）, 2011, 29(2): 185-190.
[3] 冯嘉礼, 杨润泽. 属性论方法在图像分割中的应用研究[J]. 广西师范大学学报（自然科学版）, 2011, 29(2): 191-194.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 广西师范大学学报（自然科学版）编辑部
地址：广西桂林市三里店育才路15号　邮编：541004
电话：0773-5857325　E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发