基于粒子群优化的自适应对比度增强算法在中子照相中的应用  

Application of adaptive contrast enhancement algorithm based on particle swarm optimization in neutron radiography

作　　者：曹旭宁 陈思泽[1] 俞杰 张连鑫[1,2] 张早娣 李桃生 CAO Xuning;CHEN Size;YU Jie;ZHANG Lianxin;ZHANG Zaodi;LI Taosheng(Institute of Nuclear Energy Safety Technology,Hefei Institutes of Physical Science,Chinese Academy of Sciences,Hefei 230031,China;University of Science and Technology of China,Hefei 230027,China)

机构地区：[1]中国科学院合肥物质科学研究院核能安全技术研究所,合肥230031 [2]中国科学技术大学,合肥230027

出　　处：《核技术》2021年第7期67-75,共9页Nuclear Techniques

基　　金：国家"十三五"核能开发科研项目(No.[2019]1342)资助。

摘　　要：由于成像机理和中子源的限制,中子照相成像图像易出现对比度不足的缺陷,利用对比度增强算法改善图像质量成为解决问题的常用方法。新提出的自适应对比度增强算法利用粒子群优化算法对中子图像全局像素进行迭代分析,确定自适应处理过程中的关键增益因子系数,可实现图像对比度自动寻优增强。利用该算法对多幅中子图像进行处理并与传统优化算法处理结果进行对比分析。结果显示:新算法对于不同中子照相的图像均具有明显的对比度增强效果,且该算法优化图像的信息熵、灰度平均梯度和对比度等参数相比传统优化算法均有提高,具备推广应用价值。[Background]Due to the imaging mechanism of neutron radiography and the limitation of neutron source,neutron radiography images are prone to lack of contrast,and it is a common method to improve image quality by contrast enhancement algorithm.[Purpose]This study aims to solve the problems related to low contrast and loss of details in neutron imaging.[Methods]An adaptive contrast enhancement(ACE)algorithm based on the particle swarm optimization(PSO)was proposed.First of all,the gain factor coefficient was treated as a particle and initializes a particle swarm.Then,the optimal gain factor coefficient with the PSO algorithm was calculated,and the contrast of the high frequency part of neutron images was improved through implementing this optimal gain factor coefficient in ACE algorithm.Finally,several neutron images were processed by this PSO algorithm and compared with the results of traditional optimization algorithm.[Results]The new algorithm has obvious contrast enhancement effect for different neutron images,and the parameters such as entropy value,gray average gradient value and contrast value of the optimized image are improved compared with the traditional optimization algorithm.[Conclusions]This algorithm can enhance the contrast of image stably,which has practical significance for the wide application of neutron radiography.

关 键 词：中子照相 图像增强算法 自适应对比度增强 粒子群优化算法 

分 类 号：TL99[核科学技术—核技术及应用]