基于改进果蝇算法的工程图纸分割方法研究  

Research on Engineering Drawing Segmentation Method Based on Improved Fruit Fly Optimization Algorithm

作　　者：于灏[1] 杨建鸣[1] 王小刚[1,2] YU Hao;YANG Jian-ming;WANG Xiao-gang(School of Mechanical Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,China;Coking Plant of Steel Union Corp of Baotou Steel in Inner Mongolia,Baotou 014010,China)

机构地区：[1]内蒙古科技大学机械工程学院,内蒙古包头014010 [2]包头钢铁钢联股份有限公司焦化厂,内蒙古包头014010

出　　处：《计算机技术与发展》2018年第10期124-128,共5页Computer Technology and Development

基　　金：内蒙古自治区自然科学基金(2015MS0562)

摘　　要：工程图纸是机械行业重要的技术资料,凝结着科研人员大量的智慧与心血,对其进行智能识别与三维重建可以有效发掘与保护其上所载信息。矢量化是工程图纸智能识别与三维重建的基础,针对工程图纸矢量化预处理中的图像分割问题,提出了一种基于改进果蝇优化算法(fruit fly optimization algorithm,FOA)的最大熵工程图纸分割方法。参考遗传算法中基因初始化与翻译、表达的机理对果蝇算法进行改进,引进二进制数随机初始化果蝇种群位置,获得具有较好个体多样性的种群,结合最大熵理论使其适用于图像分割中阈值的优化问题。通过实验证明,基于改进果蝇优化算法的最大熵工程图纸分割算法的准确性较高,其误分率与穷举法相同,低于遗传算法的误分率;运算时间与遗传算法相差不大但明显低于穷举法;在收敛性上优于遗传算法。Engineering drawings are important technical data in the mechanical industry,which condense a lot of wisdom and painstakingefforts of scientific researchers. Intelligent identification and three-dimensional reconstruction of engineering drawings can effectively explore and protect the information contained on them. Vectorization is the foundation of intelligent identification and three-dimensional reconstruction of engineering drawings. Aiming at the image segmentation in vectorization pre-processing of engineering drawings,we propose a type of maximum entropy engineering drawing partition method based on fruit fly optimization algorithm （FOA）. By means ofreferring to the mechanism of gene initialization,translation and expression,fruit fly algorithm is improved. Secondly,binary figure is introduced to randomly initialize the position of fruit fly population and acquire the population with better individual diversity,which,through combining with maximum entropy theory,is made to adapt to threshold value optimization in image segmentation. The experiment shows that the accuracy of the proposed algorithm is higher. Meanwhile,similar to exhaust algorithm,its misclassification rate islower than that of genetic algorithm. Besides,its operation time is not quite different from that of genetic algorithm but is obviously lowerthan that of exhaust algorithm with better astringency than genetic algorithm.

关 键 词：工程图纸 图像分割 矢量化 果蝇算法 最大熵 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]