文章基本信息

标题：An Intensity- Texture Model Based K-Means For Mammogram Segmentation
本地全文：下载
作者：K. Karteeka Pavan ; Ch. Srinivasa Rao
期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2015
卷号：24
期号：3
页码：113-118
DOI：10.14445/22312803/IJCTT-V24P125
出版社：Seventh Sense Research Group
摘要：Image segmentation is an important characteristic in many applications including medical imaging etc. Kmeans is the simple, efficient, clustering technique in medical image segmentation. One of the drawbacks in kmeans algorithm does not use the spatial information of image space in the clustering process. This paper proposes a simple algorithm to combine intensity values and spatial information of image to determine regions of interest in mammograms. The spatial information of the image is incur using textural features by dividing the image into windows. Experimental results conducted on each image of MIAS database and on the mammograms collected from Jahnavi imaging, Guntur, A.P. The results demonstrated the accuracy and efficiency of the algorithm in identifying the masses of mammograms.
关键词：Segmentation; texture; intensity; k-meansMammogram; Region of interest.