摘要
针对刑侦图像分割问题,提出一种基于粒子群优化(particle swarm optimization,PSO)直觉模糊集相似度的阈值算法。采用双边滤波对图像去噪,结合"投票模型"构造图像的直觉模糊集模型,以直觉模糊集上含权重参数的相似度为目标函数优化阈值,利用粒子群优化的方法自适应选取相似度中的权重。仿真结果表明,该算法能获得较好的分割效果,能够推广于自然图像的处理。
For the criminal investigation image segmentation,a threshold algorithm based on the similarity measure between intuitionistic fuzzy sets with particle swarm optimization was presented.The bilateral filter was used to de-noise an image.Combining the vote model with intuitionistic fuzzy sets,a model for an image was constructed.The similarity measure including weight parameters between intuitionistic fuzzy sets was used as the objective function to optimize the threshold.By using the particle swarm optimization algorithm,the weight parameters in the similarity measure were selected adaptively.Simulation results show that the proposed algorithm can obtain better segmentation effects and it can be generalized to the processing of natural images.
作者
兰蓉
程阳子
LAN Rong;CHENG Yang-zi(School of Communication and Information Engineering,Xi’an University of Posts and Telecommunications,Xi’an 710121,China;Key Laboratory of Electronic Information Application Technology for Scene Investigation of Ministry of Public Security,Xi’an University of Posts and Telecommunications,Xi’an 710121,China;Shaanxi International Joint Research Center for Wireless Communication and Information Processing,Xi’an University of Posts and Telecommunications,Xi’an 710121,China)
出处
《计算机工程与设计》
北大核心
2019年第10期2949-2954,3001,共7页
Computer Engineering and Design
基金
国家自然科学基金项目(61571361、61671377)
陕西省教育厅科学研究计划基金项目(16JK1709)
西安邮电大学西邮新星团队基金项目(xyt2016-01)
关键词
刑侦图像
阈值分割
双边滤波
直觉模糊集
相似度
粒子群优化
criminal investigation image
threshold segmentation
bilateral filter
intuitionistic fuzzy set
similarity measure
particle swarm optimization
