图像分割在医学图像处理中的应用研究  

Research of image segmentation technique applied in medical image processing

作　　者：李靖宇[1] 穆伟斌[1] 金成[1] 耿魁[1] 张岩[2] 

机构地区：[1]齐齐哈尔医学院医学技术学院,黑龙江齐齐哈尔161006 [2]齐齐哈尔医学院附属第一医院,黑龙江齐齐哈尔161042

出　　处：《微型机与应用》2012年第8期29-31,共3页Microcomputer & Its Applications

基　　金：黑龙江省教育厅科学技术研究项目(12511625)

摘　　要：图像分割是图像处理中的重要工作,医学图像的多样性和复杂性使其在图像分割中具有较大的难度。阈值法由于高效、简单而成为图像分割的重要方法,但对于复杂的医学图像,其效果并不很理想。Powell法是最好的直接搜索法,利用改进的Powell法可以更好地搜索目标。为此,提出了一种将Otsu法和Powell法相结合的图像分割方法,仿真实验表明,该方法可以快速有效地分割图像,鲁棒性强。The mage segmentation is an important task in image processing.The image segmentation has great difficulty in the medical images because of the diversity and complexity of medical images.The threshold method becomes an important method of image segmentation as it＇s simple and efficient.But the threshold is not very satisfactory to the complex medical image segmentation.Powell algorithm is the best direct search method and the improved Powell method can do the targeted search better.An image segmentation method is introduced,which combines Otsu algorithm and Powell algorithm.The experiment result shows that the method can segment images fast and efficiently with robust.

关 键 词：医学图像 图像分割 阈值分割 优化算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]