3D Model Retrieval Based on Vector Quantisation Index Histograms

摘要：

This paper proposes a novel technique to retrieval 3D mesh models using vector quantisation index histograms. Firstly, points are sampled uniformly on mesh surface.Secondly, to a point five features representing global and local properties are extracted. Thus feature vectors of points are obtained. Third, we select several models from each class, and employ their feature vectors as a training set. After training using LBG algorithm, a public codebook is constructed. Next, codeword index histograms of the query model and those in database are computed. The last step is to compute the distance between histograms of the query and those of the models in database. Experimental results show the effectiveness of our method.

作者: Z M Lu H Luo J S Pan

作者单位: Harbin Institute of Technology Shenzhen Graduate School, Shenzhen 518055, China Harbin Institute of Technology Shenzhen Graduate School, Shenzhen 518055, China;Kaohsiung University Kaohsiung University of Applied Sciences, Kaohsiung 807, Taiwan, China

会议类型: 国际会议

会议名称: 第四届仪器科学与技术国际会议( 4th International Symposium on Instrumentation and Science and Tcchnology)

会议地点: 哈尔滨

会议语种:英文

页码: 437-441

在线出版日期: 2006-08-08（万方平台首次上网日期，不代表论文的发表时间）