基于分形的改进Otsu红外图像分割算法  

Improved Otsu Segmentation Algorithm for IR Image Based on Fractal Algorithm

作　　者：康怀祺[1] 陈宝国[1] 

机构地区：[1]中国空空导弹研究院,河南洛阳471009

出　　处：《红外技术》2009年第6期359-361,共3页Infrared Technology

摘　　要：提出了一种基于分形的改进Otsu红外图像分割算法。针对Otsu算法在目标的相对面积较小时背景信息容易误分问题,以及递归Otsu算法递归终止条件不易确定问题,将分形算法与Otsu算法结合起来,用于分割红外目标。首先计算红外图像的分形维特征,根据分形维特征去除大部分背景信息,然后在潜在目标区域采用Otsu算法进行分割。仿真结果表明,该算法性能优于Otsu算法及递归Otsu算法。An improved Otsu segmentation algorithm for IR image based on fractal algorithm is proposed. To overcome the problems of Otsu algorithm that background information being erroneously divided when object size is small and recursive Otsu algorithm that recursive termination criteria being difficult determined, combination of fractal algorithm and Otsu algorithm is applied to segmentation of infrared object. Large background information is removed firstly using fractal algorithm, then the object is segmented by Otsu algorithm in the object region. Simulation results show that the performance of this algorithm is better than Otsu algorithm and recursive Otsu algorithm.

关 键 词：分形算法 OTSU算法 递归 分割 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]