《计算机应用研究》|Application Research of Computers

彩色图像分割的FCM初始化方法

Initialization approach for fuzzy C-means algorithm for color image segmentation

免费全文下载 (已被下载 次)  
获取PDF全文
作者 朱征宇,王丽敏
机构 1.重庆大学 计算机学院,重庆 400030;2.软件理论与技术重庆市重点实验室,重庆 400030
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2015)04-1257-04
DOI 10.3969/j.issn.1001-3695.2015.04.071
摘要 针对传统模糊C-均值聚类方法所存在的过度依赖初始聚类中心、计算复杂度高等问题,提出一种新的FCM初始化方法。首先,使用维纳滤波分别对图像的R、G、B分量进行预处理,待转换为LAB色彩空间后,通过二次分水岭方法获取图像的封闭区域,并计算各区域的质心;其次,利用自适应无监督的方法对质心进行筛选和合并,将合并结果作为FCM的初始聚类中心;最后,使用FCM方法进行分割。实验结果表明,该方法不仅能够获得较准确的聚类中心,减少了迭代次数和运算时间,而且能够更好地实现图像的准确分割。
关键词 图像分割;模糊C-均值聚类;初始化;维纳滤波;二次分水岭;质心筛选与合并
基金项目 国家科技支撑计划重点项目(2011BAH25B041)
本文URL http://www.arocmag.com/article/01-2015-04-071.html
英文标题 Initialization approach for fuzzy C-means algorithm for color image segmentation
作者英文名 ZHU Zheng-yu, WANG Li-min
机构英文名 1. College of Computer, Chongqing University, Chongqing 400030, China; 2. Chongqing Key Laboratory of Software Theory & Technology, Chongqing 400030, China
英文摘要 Aiming at the problems of traditional fuzzy C-means algorithm, which was excessively dependent on the initial cluster centers and that had high computation, this paper proposed a novel FCM initialization approach. Firstly, it respectively preprocessed the R, G and B components of the image by Wiener filter.After transformed the image into LAB color space, it extracted the closed areas of the image by secondary watershed, and then computed the centroid of the areas.After that, it used the self-adaptive unsupervised screen method to merge centroid, and set the final centroid as the initial cluster centers.Finally, it applied FCM algorithm to image segmentation. The experimental results show that the proposed method can not only obtain more accuracy cluster centers, which decreases the iteration times and the computation time, but also make the color image segmentation more accuracy.
英文关键词 image segmentation; fuzzy C-means cluster; initialization; Wiener filtering; secondary watershed; centroid screening and merging
参考文献 查看稿件参考文献
  [1] 周东国, 高潮, 郭永彩. 自适应分层阈值的简化PCNN红外人体图像分割[J] . 计算机辅助设计与图形学学报, 2013, 25(2):208-214.
[2] LAN Jin-hui, ZENG Yi-liang. Multi-threshold image segmentation using maximum fuzzy entropy based on a new 2D histogram[J] . Optik:International Journal for Light and Electron Optics, 2013, 124(2013):3756-3760.
[3] OSUMA-ENCISO V, CUEVAS E, SOSSA H. A comparison of nature inspired algorithms for multi-threshold image segmentation[J] . Expert Systems with Applications, 2013, 40(4):1213-1219.
[4] WANG Ling-feng, WU Huai-gu, PAN Chun-hong. Region-based image segmentation with local signed difference energy[J] . Pattern Recognition Letters, 2013, 34(6):637-645.
[5] SINGH J, SINGH P P. Automatic seed placement in region growing image segmentation[J] . Journal of Engineering Computers & Applied Sciences, 2013, 2(7):55-58.
[6] YU Zhi-ding, AU O C, ZOU Ruo-bing, et al. An adaptive unsupervised approach toward pixel clustering and color image segmentation[J] . Pattern Recognition, 2010, 43(5):1889-1906.
[7] 尹芳, 陈德运, 吴锐. 改进的谱聚类图像分割方法[J] . 计算机工程与应用, 2011, 47(21):185-187.
[8] 贺强, 晏立. 基于LOG和Canny算子的边缘检测算法[J] . 计算机工程, 2011, 37(3):210-212.
[9] CHAUDHARY A, GULATI T. Segmenting digital images using edge detection[J] . Methods, 2013, 2(5):319-323.
[10] 徐丽燕, 张洁玉, 孙权森, 等. 结合EFD与NCut的彩色图像分割方法[J] . 模式识别与人工智能, 2010, 23(5):671-677.
[11] 陈沅涛, 徐蔚鸿, 吴佳英. 基于水平集的新型彩色图像分割算法[J] . 计算机应用, 2012, 32(3):749-751.
[12] 张艳, 宦飞. 一种应用遗传算法的彩色图像分割方法[J] . 计算机应用与软件, 2011, 28(3):237-239.
[13] 陈骥思, 余艳梅, 殷宇, 等. 自适应快速FCM彩色图像分割研究[J] . 计算机工程与应用, 2010, 46(7):178-180.
[14] 杨计龙, 王清心, 胡逢法. 一种基于分水岭变换和模糊C-均值聚类的彩色图像分割算法[J] . 科学技术与工程, 2011, 11(18):4237-4239.
[15] TAN K S, MAT ISA N A, LIM W H. Color image segmentation using adaptive unsupervised clustering approach[J] . Applied Soft Computing, 2013, 13(4):2017-2036.
[16] ZADEH L A. Fuzzy sets[J] . Information and Control, 1965, 8(3):338-353.
[17] BEZDEK J C. Cluster validity with fuzzy sets[J] . Journal of Cybernetics, 1973, 3(3):58-73.
[18] 卢志茂, 许晓丽, 范冬梅. 二次分水岭和Ncut相结合的彩色图像分割方法[J] . 华中科技大学学报:自然科学版, 2011, 39(z2):95-98.
收稿日期 2014/3/4
修回日期 2014/4/10
页码 1257-1260
中图分类号 TP391.41
文献标志码 A