基于动态分组和权重学习教与学算法的Otsu图像阈值分割  

OTSU IMAGE THRESHOLD SEGMENTATION BASED ON DYNAMIC GROUPING AND WEIGHT LEARNING TEACHING AND LEARNING ALGORITHM

作　　者：姚金宝 张义民[1] 张凯 Yao Jinbao;Zhang Yimin;Zhang Kai(Institute of Equipment Reliability,Shenyang University of Chemical Technology,Shenyang 110142,Liaoning,China)

机构地区：[1]沈阳化工大学装备可靠性研究所,辽宁沈阳110142

出　　处：《计算机应用与软件》2022年第10期191-197,237,共8页Computer Applications and Software

基　　金：NSFC-辽宁联合基金项目(U1708254);国家重点研发计划的重点专项(2019YFB2004400)。

摘　　要：在实际应用中最大类间方差法(Otsu)的计算量大,算法运行所需时间长。对此在动态分组教与学算法(DGSTLBO)的基础上加入权重学习和极差比较,提出基于动态分组和权重学习的教与学算法(GDSWLTLBO),将DGSWLTLBO与Otsu算法结合提高了图像分割的质量。实验结果表明,该算法有效地降低了运行时间,避免在教学过程陷入局部最优,提高了探索能力与寻优能力,保证了算法的全局收敛性。算法在图像分割的结果优于动态分组的教与学算法、教与学算法、粒子群算法、灰狼算法,在相同误差条件下,时间平均缩短了70%。In practical application,Otsu has a large amount of calculation and takes a long time to run.Based on dynamic grouping teaching and learning algorithm(DGSTLBO),adding weighted learning and range comparison,this paper proposes a teaching and learning algorithm based on dynamic grouping and weight learning(GDSWLTLBO).The combination of GDSWLTLBO and Otsu improved the quality of image segmentation.The experimental results show that the algorithm effectively reduces the running time and avoids falling into local optimum in the teaching process,improves the exploration ability and optimization ability,and ensures the global convergence of the algorithm.This algorithm is better than the dynamic grouping teaching and learning algorithm,teaching and learning algorithm,particle swarm optimization and gray wolf algorithm.Under the same error condition,the time is shortened by 70%on average.

关 键 词：动态分组的教与学算法 权重学习 最大类间方差法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]