计算机应用研究2017，Vol.34Issue(5)：1577-1580,1593,5.DOI:10.3969/j.issn.1001-3695.2017.05.067
基于改进Lucas-Kanade的亚像素级零件图像配准
Subpixel object-image registration using improved Lucas-Kanade
摘要
Abstract
Due to the problem of image registration caused by illumination change and lack of texture in industrial applications,this paper proposed the subpixel object-image registration algorithm using improved Lucas-Kanade.Firstly,it used illumination and geometric transformation model to build a nonlinear objective function about the template and image for registration.Secondly,it added weights to the objective function according to the consistency of direction vector of two images as well as edge features in order to reduce the redundant points.Finally,it applied Levenberg-Marquardt algorithm to solve the objective function.Using 500 images to test the proposed algorithm,experimental results indicate that the proposed algorithm is robust to illumination change with high accuracy rate,and has subpixel translation and rotating accuracy.The proposed algorithm can satisfy robustness and subpixel accuracy requirements under the industry conditions.关键词
图像配准/亚像素级/Lucas-Kanade/Levenberg-MarquardtKey words
image registration/subpixel/Lucas-Kanade/Levenberg-Marquardt分类
信息技术与安全科学引用本文复制引用
林桂潮,张青,邹湘军..基于改进Lucas-Kanade的亚像素级零件图像配准[J].计算机应用研究,2017,34(5):1577-1580,1593,5.基金项目
国家自然科学基金资助项目(31571568) （31571568）
安徽省热敏性物料加工工程技术研究中心开放课题基金资助项目(RMZ03) （RMZ03）
广州市科技计划项目(201510010140) （201510010140）
广东省产学研科技资助项目(2014B090904056) （2014B090904056）
