工程图纸分割方法研究  

Research on engineering drawing segmentation method

作　　者：于灏[1] 王小刚[1,2] 杨建鸣 YU Hao;WANG Xiaogang;YANG Jianming(School of Mechanical Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,China;Coal Coke Chemical Branch of Baogang united Steel,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]包钢钢联股份煤焦化工分公司,内蒙古包头014010

出　　处：《现代电子技术》2019年第13期69-72,共4页Modern Electronics Technique

基　　金：内蒙古自然科学基金:二维工程图向三维实体的转换研究(2015MS0562)~~

摘　　要：针对工程图纸分割运算时间长、效率低的问题,提出一种基于蝙蝠算法(BA)的最大熵工程图纸分割算法。通过引入二进制编码机制模拟遗传学中基因的编码、翻译与表达,优化BA算法中蝙蝠位置的初始化,使其易于约束位置的初始空间与产生多样性良好的种群。实验结果证明:基于BA算法的分割效果与穷举法相同,优于基于果蝇算法(FOA)的分割方法;运算时间远小于穷举法,约是基于FOA算法的50%;收敛性与鲁棒性明显优于基于FOA的分割算法。A maximum entropy engineering drawing segmentation method based on bat algorithm (BA) is proposed to shorten the computing time and improve the efficiency of engineering drawing segmentation algorithm. By means of introducing the binary encoding mechanism,the encoding,translation and expression of gene in genetics are simulated,the initialization of bat position is optimized in BA algorithm to make it easier to locate in constrain positional initial space and generate the population with better diversification. The experimental results show that the segmentation effect of the method based on BA algorithm is superior to that of the method based on fruit fly optimization algorithm (FOA),and is just the same as that of exhaustion method;but its operation time is only 50% of FOA algorithm,and is much shorter than that of exhaustion method;the convergence and robustness of the proposed method is obviously superior to that of the segmentation method based on FOA.

关 键 词：工程图纸 图像识别 图像分割 阈值法 蝙蝠算法 最大熵 

分 类 号：TN911.73-34[电子电信—通信与信息系统] TP391.4[电子电信—信息与通信工程]