摘要
阈值分割法在图像分割中是一种最为简单和有效的方法,然而如何选取合适的阈值实现有效分割,目前还没有统一的方法。结合信息论与图像的空间信息,提出一种新的阈值优化算法。首先建立图像的混合高斯分布(GMM),然后利用强度的类不确定性和相似度函数特性定制出目标函数,优化出局部阈值,从而获得高效的分割效果。实验结果表明,与大津法(OSTU)相比,该算法能够成功分割出模糊的边界,并且能够将图像中的各个组织有效的分割出来。
Threshold segmentation method in image segmentation is one of the most simple and effective methods, but how to select appropriate thresh- old to achieve effective segmentation is still not unified method at present. Based on information theory and image space information, a new threshold op- timization algorithm is put forward. Firstly, image mixed Gaussian distribution (GMM) is established, and by using the intensity of the class uncertainty and similarity function characteristic custom out the target function, the local threshold value is optimized, so as to achieve efficient segmentation effect. The experimental results show that compared with the OSTU, the proposed algorithm can successfully segment fuzzy boundary and image of each effective organization segmentation out.
出处
《电视技术》
北大核心
2013年第3期40-43,共4页
Video Engineering
基金
国家自然科学基金项目(61071196)
教育部新世纪优秀人才支持计划项目(NCET-10-0927)
信号与信息处理重庆市市级重点实验室建设项目(CSTC
2009CA2003)
重庆市自然科学基金项目(CSTC
2009BB2287
CSTC
2010BB2398
CSTC
2010BB2411)
作者简介
郭红(1984-),女,硕士生,主研图像处理。