基于参数化变形模板的圆形引脚元件视觉定位  

Visual positioning for round pin chips based on parametric deformable template

作　　者：王祖进[1] 黄筱调[1] 顾萍萍 

机构地区：[1]南京工业大学机械与动力工程学院,江苏南京210009 [2]南京康尼机电股份有限公司,江苏南京210038

出　　处：《中南大学学报（自然科学版）》2015年第9期3274-3278,共5页Journal of Central South University:Science and Technology

基　　金：国家自然科学基金资助项目(51175242);江苏省科技成果转化专项基金资金项目(BA2012031);江苏省普通高校研究生科研创新计划项目(CXZZ13_0436)~~

摘　　要：通过分析圆形引脚元件的图像特征,提出一种基于参数化变形模板的贴片元件偏转角度与偏移量检测方法。根据元件引脚的排列形式构建变形模板,采用5个参数表征变形模板的平移、偏转和缩放。结合图像的梯度、灰度以及几何特征定义变形模板的能量函数,采用遗传算法对能量函数进行优化搜索,找到变形模板和目标图像的最佳匹配位置。研究结果表明:该方法具有很好的准确性和稳定性,对偏移量的检测误差小于0.25个像素,对偏转角度的检测误差小于0.07°,满足贴片机对视觉系统定位算法的精度要求。A detection method of the deflection angle and the offset using the parametric deformable template was proposed based on the analysis of the image features of round pin chips. A deformable template was constructed according to the arrangement of pins. The offset, deflection and zoom of the deformable template were denoted with 5 parameters. Image gradient, gray and geometry features were combined to define an energy function, and genetic algorithm was used to optimize the energy function to find the best matching position between the deformable template and a target image. The results show that this method has good accuracy and stability, the detection errors of the offset are less than 0.25 pixels, and the detection errors of the deflection are less than 0.07°, which can meet the positioning accuracy of placement machine vision system.

关 键 词：视觉定位 变形模板 贴片机 亚像素 遗传算法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]