摘要
图像分割是图像处理中最常见但也是最重要的组成部分,目标的状态、背景复杂程度、光照强度以及不同分割方法等因素都会对目标分割的效果产生影响。通过迭代法、直方图选择法、最大类间方差法三种经典的图像分割方法,对不同时间、不同状态下的大理大学标志物进行分割,并对不同分割方法的分割结果进行比较,仿真结果显示不同分割方法分割出的大理大学标志物在细节上存在着差异,同时得出分割结果受光照因素影响。
Image segmentation is the most common but also the most important part of image processing. The state of the target, the complexity of the background, the intensity of illumination and different segmentation methods will all affect the effect of target segmentation. Through the three classical image segmentation methods of iteration method, histogram selection method and maximum inter class variance method, the Dali University landmarks at different times and in different states are segmented, and the segmentation results of different segmentation methods are compared. The simulation results show that the Dali University landmarks segmented by different segmentation methods are different in detail, and it is concluded that the segmentation results are affected by lighting factors.
作者
刘光宇
王帅
曹禹
赵恩铭
张璐
苏蕾
邢传玺
Liu Guangyu;Wang Shuai;Cao Yu;Zhao Enming;Zhang Lu;Su Lei;Xing Chuanxi(Dali University,Dali 671003 Yunan;Yunnan University of Nationalities,Kunming 650504 Yunan)
出处
《黄冈职业技术学院学报》
2022年第4期99-103,共5页
Journal of Huanggang Polytechnic
基金
国家自然科学基金项目“基于无线传感器网络的云南高原湖泊声层析监测关键技术研究”(62065001)
国家自然科学基金项目“基于谱聚类的水下目标探测关键技术研究”(61761048)
云南省地方本科高校基础研究联合专项资金项目“基于自旋交换泵浦技术的高透过率、超窄带原子滤光器的研究”[2019FH001(-066)]。
关键词
阈值分割
迭代法
直方图选择法
最大类间方差法
Threshold segmentation
Iterative method
Histogram selection method
Maximum inter class variance method
