摘要
为更好地分割出水面漂浮物区域,利用水面图像背景比较均匀的特点,在一维Otsu法的基础上结合均匀性测度函数实现自适应阈值的选择,提出基于均匀性测度函数的阈值分割法,采用基于GT图像的分割算法性能评价方法进行分割结果对比。实验结果表明,在背景相对均匀的水面图像中,该方法比传统的一维Otsu法具有更好的分割效果。
To segment the area of flotsam on the water,using the characteristic that the surface image background is more uniform,on the basis of the one-dimensional Otsu method,uniformity measurement function was combined to realize the adaptive threshold selection,and the threshold segmentation method based on homogeneity measurement was proposed. The performance evaluation method of segmentation algorithm based on GT image was used to compare the segmentation results. Experimental results show that the proposed method has better segmentation effects than the traditional one-dimensional Otsu.
作者
徐守坤
王雨萱
李宁
石林
XU Shou-kun;WANG Yu-xuan;LI Ning;SHI Lin(School of Information Scienceand Engineering,School of Mathematics and Physics,Changzhou University,Changzhou 213164,China;Fujian Provincial Key Laboratory of Information Processing and Intelligent Control,Minjiang University,Fuzhou 350108,China)
出处
《计算机工程与设计》
北大核心
2019年第7期1996-2001,共6页
Computer Engineering and Design
基金
福建省信息处理与智能控制重点实验室开放课题基金项目(MJUKF201740)
关键词
水面图像
一维Otsu法
均匀性测度
阈值分割
自适应
water image
one-dimensional Otsu
uniformity measure
threshold segmentation
self-adaption