3D objects reconstruction from single 2D graph based on neural networks - 文章详情页

作者：

收录：

EI Scopus PKU CSCD

摘要：

A　system　scheme　was　presented　in　this　paper,　which　could　be　used　in　3D　objects　reconstruction　from　single　2D　sketch.　Corner　points　and　several　other　structural　features　were　adopted　in　this　system.　BP　neural　network　was　also　applied　due　to　its　non-linear　mapping　and　feature　extracting　ability.　In　order　to　obtain　the　corner　points　more　effectively,　an　adaptive　corner　detection　algorithm　was　proposed　based　on　curvature　and　slide　windows.　Experimental　results　show　that　the　selected　features　and　the　algorithm　have　superiority　in　3D　objects　reconstruction.

关键词：

Backpropagation Edge detection Feature extraction Graphic methods Image reconstruction Neural networks

作者机构：

[ 1 ] [Sun, Guang-Min]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China
[ 2 ] [Xu, Lei]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China
[ 3 ] [Chen, De-Ming]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China
[ 4 ] [Wang, Chun]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China
[ 5 ] [Li, Gang]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China
[ 6 ] [Wang, Jing]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China

通讯作者信息：

电子邮件地址：

查看成果更多字段

成果类型
所属机构

所有年份指定年份从至