期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

结肠镜图像自动分割技术研究 被引量：1

Study of automatic segmentation technique for colonoscopic images
下载PDF
导出
摘要 提出了一种融合颜色、亮度、空间距离和纹理等特征的彩色结肠镜图像分割新算法.纹理特征采用一组Gabor滤波器对原始图像滤波后计算得到的分形维特征.利用基于元素间相似性的随机聚类方法对特征空间进行聚类.通过对图中的切割进行采样,自动获得最佳的类别数目,算法复杂度较低,其随机特性使得它具有抗噪声的鲁棒性.对多幅结肠镜图像进行分割实验,结果证实了该算法的有效性. An Algorithm for segmenting color colonoscopic images by fusing color, brightness, spatial distance and texture information was presented. The fractal dimensions, which served as the measurement for the texture features, were obtained from the filtered images of original images by a set of Gabor filters. A stochastic clustering method based on pairwise similarity of elements was utilized to cluster feature space. Based on the sampling of cuts in graphs, the optimal number of clusters was obtained automatically and with low complexity. Furthermore, the method's stochastic nature makes it robust against noise. The segmentation of several colonoscopic images proves the effectiveness of the algorithm.
作者 朱丹琦 夏顺仁 楼晓敏 周乐平 张国雄
机构地区 浙江大学生物医学工程教育部重点实验室 杭州市中医院
出处 《浙江大学学报（工学版）》 EI CAS CSCD 北大核心 2004年第7期821-825,共5页 Journal of Zhejiang University：Engineering Science
基金 国家自然科学基金资助项目(60272029) 浙江省自然科学基金资助项目(M603227).
关键词 图像分割 特征融合 分形维 元素间相似性 随机聚类 Algorithms Color image processing Textures Variational techniques
分类号 TN911.73 [电子电信—通信与信息系统] TP317.4 [自动化与计算机技术—计算机软件与理论]
  • 相关文献

参考文献10

  • 1KRISHNAN S M, GOH P M Y. Quantitative parameterization of colonoscopic images by applying fuzzy technique [A]. Proceeding of the 19th International Conference of the IEEE Engineering in Medicine and Biology Society [C]. Los Alamitos: IEEE, 1997: 1121-1123.
  • 2SHUNREN X,KRISHNAN S M,TJOA M P,et al. A novel approach for extracting colon's lumen from colonoscopic images [A]. Proceeding of the 6th World Multiconference on Systemics, Cybernetics and Informatics; Proceeding-Image, Acoustic, Speech and Signal Processing I [C]. Florida: Informatics ＆ Systemics,2002: 205-210.
  • 3PANJWANI D K, HEALEY G. Markov random field models for unsupervised segmentation of texture colour images [J]. IEEE Trans Pattern Analysis and Machine Intelligence, 1995, 17(10): 939-954.
  • 4KRISHNANMOORTHI R, BHATTACHARYYA P.On unsupervised segmentation of colour texture images [A]. Proceeding of the Fourth International Conference on High-Performance Computing [C]. Los Alamitos: IEEE, 1997: 500-504.
  • 5OJALA T, PIETIKAINEN M. Unsupervised texture segmentation using feature distribution [J]. Pattern Recognition, 1999, 32(3): 477-486.
  • 6CELENK M. Hierarchical colour clustering for segmentation of textured images [A]. Proceedings of the Twenty-Ninth Southeastern Symposium on System Theory [C]. Los Alamitos: IEEE, 1997: 483-487.
  • 7PENG W, KRISHNAN S M, KUGEAN C, et al. Classification of endoscopic images based on texture and neural network [A]. Proceeding of the 23rd International Conference of the IEEE Engineering in Medicine and Biology Society [C]. Los Alamitos: IEEE, 2001.
  • 8CHAUNDHURI B B, SARKER N. Texture segmentation using fractal dimension [J]. IEEE Trans Pattern Analysis and Machine Intelligence, 1995, 17(1): 72-77.
  • 9KASPARIS T, CHARALAMPIDIS D, GEORGIOPOULOS M, et al. Segmentation of textured images based on fractals and image filtering [J]. Pattern Recognition, 2001, 34(10): 1963-1973.
  • 10GDALYAHU Y, WEINSHALL D, WERMAN M.Stochastic image segmentation by typical cuts [A].Proceedings of IEEE Conference on Computer Vision & Pattern Recognition [C]. Los Alamitos: IEEE,1999: 588-601.

同被引文献26

  • 1Dietterich TG.Machine learning for sequential data:A review[J].Lecture Notes in Comput Sci,2002,2396:15-30.
  • 2Breiman L.Bagging predictors[J].Machine learning,1996,24(2):123-140.
  • 3Kodogiannis VS,Chowdrey HS.Multi network classification scheme for computer-aided diagnosis in clinical endoscopy[A].In:Proc Int Conf Adv Med Sign Inform Proc[C].Malta,2004.262-267.
  • 4Melville P.Creating diverse ensemble classifier[D].PhD Proposal of University of Texas at Austin,2003.
  • 5Wei L,Yang Y,Nishikawa RM,et al.A study on several machinelearning methods for classification of malignant and benign clustered microcalcifications[J].Med Imag,2005,24(3):371-380.
  • 6Madabhushi A,Feldman M.Optimal feature combination for automated segmentation of prostatic adenocarcinoma from high resolution MRI[A].In:Proc 25th Ann Int Conf IEEE EMBS[C].Mexico:Cancun,2003.614-617.
  • 7Roli F,Giacinto G,Vernazza G.Methods for designing multiple classifier systems[A].In:Proc Second Int Workshop Multiple Classifier Syst[C].London,2001.78-87.
  • 8Kuncheva LI,Whitaker CJ,Shipp CA.Limits on the majority vote accuracy in classifier fusion[J].Pattern Analy Appl,2003,6:22-31.
  • 9Kitterler J,Hatef M,Duin RPW,et al.On combining classifiers[J].Pattern Analy and Machine Intelligence,1998,20(3):226-238.
  • 10Giacinto G,Roli F.An approach to the automatic design of multiple classifier systems[J].Pattern Recogn Lett,2001,22:25-33.

引证文献1

二级引证文献10

浙江大学学报（工学版）
2004年 第7期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部