计算机科学 ›› 2014, Vol. 41 ›› Issue (7): 322-325.doi: 10.11896/j.issn.1002-137X.2014.07.067

• 图形图像与模式识别 • 上一篇    

结合随机游走与FCM的脑图像分割方法

郭鹏飞,刘万军,林琳,赵永刚,闵亮   

  1. 辽宁工程技术大学软件学院 葫芦岛125105;辽宁工程技术大学软件学院 葫芦岛125105;辽宁工程技术大学软件学院 葫芦岛125105;辽宁工程技术大学软件学院 葫芦岛125105;辽宁工程技术大学软件学院 葫芦岛125105
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金项目(61172144)资助

Brain Image Segmentation Method Based on FCM and Random Walk

GUO Peng-fei,LIU Wan-jun,LIN Lin,ZHAO Yong-gang and MIN Liang   

  • Online:2018-11-14 Published:2018-11-14

摘要: 随机游走算法只考虑相邻像素灰度相似性,忽略了邻域像素梯度信息,抑制了random walker沿着某些与种子点灰度相近的边向种子点前进,从而导致错分与漏分。提出一种脑图像分割方法,先对原图进行小波变换,提取图像梯度信息,将梯度信息融入边的权重。最后使用改进的FCM算法,结合像素邻域信息,进行最终脑图像分割。实验表明,本方法分割的脑组织图像正确率高,图像空洞与斑点明显减少,图像边缘更加平整。

关键词: 随机游走,模糊C均值,图像分割,梯度信息 中图法分类号TP391文献标识码A

Abstract: Random walk algorithm only considers the gray similarity of adjacent pixels,ignores neighboring pixels gra-dient information.This suppresses random walker walking to the seed point along some edges of similar gray to seed point,resulting in misclassification and missing points.This paper presented a segmentation method of brain image.It extracts image gradient information by using wavelet transform,and puts the gradient information into the edge weight.Finally using improved FCM algorithm,combining with the pixel neighborhood information,we obtained a final split brain image.Experimental results show that this method improves segmentation correct rate and the edge of the segmented image is smoother.

Key words: Random walk,Fuzzy C means,Image segmentation,Gradient information

[1] 沙秀艳,王贞俭.基于快速二维熵的加权模糊C均值聚类图像分割[J].计算机工程与应用,2012,48(10):183-186
[2] 葛琦,韦志辉,张建伟,等.结合改进FCM算法的多相位CV模型[J].中国图象图形学报,2011,16(4):548-553
[3] 罗诗途,张玘,罗飞路,等.基于粗糙集理论的图像分割智能决策方法[J].中国图象图形学报,2006,11(1):66-72
[4] 祭黎煌,钟华,张石.结合马尔可夫随机场与模糊C均值聚类的脑MRI图像分割[J].中国图象图形学报,2012,17(12):1554-1560
[5] 许存禄,高佳,武国德.Chan-Vese模型下的脑肿瘤图像分割方法[J].计算机工程与应用,2010,46(9):155-158
[6] 许兴明,赵海峰,罗斌.基于t-混合模型的脑MR 图像白质分割[J].计算机工程与应用,2010,46(17):190-193
[7] 车娜,车翔玖,高占恒,等.基于局部熵最小化的核磁共振脑图像二次分割算法[J].计算机研究与发展,2010,47(7):1294-1303
[8] 于佳丽,郭敏.基于随机游走的医学超声图像分割[J].计算机工程与应用,2010,46(23):241-244
[9] 陈圣国,孙正兴,周杰.基于FCM和随机游走的地层图像分割方法[J].电子学报,2013,41(3):526-532
[10] Grady L.Random walks for image segmentation[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2006,28(11):1768-1783
[11] Grady L,Funka-lea G.Multi-label image segmentation for medical applications based on graph-theoretic electrical potentials [C]∥Lecture Notes in Computer Science,Computer Vision and Mathematical Methods in Medical and Biomedical Image Analysis.Berlin:Springer Berlin/Heidelberg,2004:230-245
[12] Grady L,Schiwietz T,et al.Random walks for interactive organsegmentation in two and three dimensions:Implementation and validation [C]∥Proceedings of the Medical Image Computing and Computer-Assisted Intervention.Berlin:Springer Berlin / Heidelberg,2005:773-780
[13] Doyle P,Snell J.Random Walks and Electric Networks [M].Ann Arbor:The Mathematical Association of America,1984
[14] Mallat S G.A theory for multi-resolution signal decomposition:The wavelet representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7):674-693
[15] Liu Juan,Moulin P.Information-theoretic analysis of inter-scale and intra-scale dependencies between image wavelet coefficients [J].Transactions on Image Processing,2001,10(11):1647-1658

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!