基于多特征融合的三维模型检索
|
摘要
特征的选择、表示和融合是基于多特征三维模型检索技术的关键,现有成果大多没有兼顾模型的整体和局部,且特征表示复杂度高.提出了一种基于多特征融合的三维模型检索方法,提取ORB特征描述模型局部信息,并在提取Canny边缘信息的基础上,进一步提取形状上下文特征描述全局信息,融合ORB特征和形状上下文特征得到一个新的特征表示三维模型,通过计算模型相似度得出最终检索结果.试验结果表明,本方法能有效提高检索性能.
The selection of features,the representation of features,and the mode of fusion were key processes of 3D model retrieval technology.In the paper,a new 3D model retrieval method which was based on multiple feature fusion was proposed.It combined the fast ORB features and the precise shape context features.ORB features described the local information.After extracting the Canny edge information,the shape context features were extracted to describe the global information,then the final similarity was calculated based on shape context features and ORB features.Experimental results demonstrated that our method could effectively improve retrieval performance.
The selection of features,the representation of features,and the mode of fusion were key processes of 3D model retrieval technology.In the paper,a new 3D model retrieval method which was based on multiple feature fusion was proposed.It combined the fast ORB features and the precise shape context features.ORB features described the local information.After extracting the Canny edge information,the shape context features were extracted to describe the global information,then the final similarity was calculated based on shape context features and ORB features.Experimental results demonstrated that our method could effectively improve retrieval performance.
引文
[1]ANKERST M,KASTENMLLER G,KRIEGEL H P,et al.3D shape histograms for similarity search and classification in spatial databases[C]//Advances in Spatial Databases.Berlin Heidelberg:Springer,1999:207-226.
[2]PAQUET E,RIOUX M.A content-based search engine for VRML databases[C]//Proceedings of IEEEComputer Society Conference on Computer Vision and Pattern Recognition.Washington D C:IEEE,1998:541-546.
[3]OSADA R,FUNKHOUSER T,DOBKIN D.Shape distributions[J].ACM transactions on graphics,2002,21(4):807-832.
[4]CHEN D,TIAN X,SHEN Y,et al.On visual similarity based 3D model retrieval[J].Computer graphics forum,2010,22(3):223-232.
[5]VRANIC D V.DESIRE:a composite 3D-shape descriptor[C]//Proceedings of the 2005 IEEE International Conference on Multimedia and Expo.Amsterdam:IEEE,2005:4.
[6]ZOU K S,IP W H,CHEN Z Q,et al.A novel 3Dmodel retrieval approach using combined shape distribution[J].Multimedia tools and application,2014,69(3):799-818.
[7]LI B,JOHAN H.3D model retrieval using hybrid features and class information[J].Multimedia tools and applications,2013,62(3):821-846.
[8]SHILANE P,MIN P,KAZHDAN M,et al.The princeton shape benchmark[C]//Proceedings of Shape Modeling Applications.Genova:IEEE,2004:167-178.
[9]CANNY J.A computational approach to edge detection[J].IEEE transactions on pattern analysis and machine intelligence,1986,8(6):679-698.
[10]BELONGIE S,MALIK J,PUZICHA J.Shape matching and object recognition using shape contexts[J].IEEEtransactions on pattern analysis and machine intelligence,2002,24(4):509-522.
[11]陈实,马天骏,黄万红,等.基于形状上下文描述子的步态识别[J].模式识别与人工智能,2007,20(6):794-799.
[12]KUHN H W.The Hungarian method for the assignment problem[J].Naval research logistics quarterly,1955,2(1):83-97.
[13]LI B,LU Y J,LI C Y,et al.A comparison of 3Dshape retrieval methods based on a large-scale benchmark supporting multi modal queries[J].Computer vision and image understanding,2015,131:1-27.
[14]LI B,GODIL A A,AONO M,et al.SHREC'12 Track:Generic 3D Shape Retrieval[C]//Proceedings of the 5th Eurographics Conference on 3D Object Retrieval.Cagliari:Computing Machinery,2012:119-126.
[15]徐平安,唐雁,陈强,等.融合细节与整体特征的三维模型检索方法[J].西南大学学报(自然科学版),2015,37(10):131-137.
[16]LENG B,DU C,GUO S,et al.A powerful 3D model classification mechanism based on fusing multi-graph[J].Neurocomputing,2015,168:761-769.
[17]OSADA R,FUNKHOUSER T,CHAZELLE B,et al.Matching 3D models with shape distributions[C]//International Conference on Shape Modelling and Applications.Washington D C:IEEE,2008:154-166.
[18]KAZHDAN M,FUNKHOUSER T,RUSINKIEWICZ S.Rotation invariant spherical harmonic representation of3D shap descriptirs[J].Eurographics symposium on geometry processing,2003,43:156-164.
[19]杨文柱,刘晴,王思乐,等.基于深度卷积神经网络的羽绒图像识别[J].郑州大学学报(工学版),2018,39(2):11-17.
[20]WANG F,PENG J,LI Y.Hypergraph based feature fusion for 3-D object retrieval[J].Neurocomputing,2015,151:612-619.
[2]PAQUET E,RIOUX M.A content-based search engine for VRML databases[C]//Proceedings of IEEEComputer Society Conference on Computer Vision and Pattern Recognition.Washington D C:IEEE,1998:541-546.
[3]OSADA R,FUNKHOUSER T,DOBKIN D.Shape distributions[J].ACM transactions on graphics,2002,21(4):807-832.
[4]CHEN D,TIAN X,SHEN Y,et al.On visual similarity based 3D model retrieval[J].Computer graphics forum,2010,22(3):223-232.
[5]VRANIC D V.DESIRE:a composite 3D-shape descriptor[C]//Proceedings of the 2005 IEEE International Conference on Multimedia and Expo.Amsterdam:IEEE,2005:4.
[6]ZOU K S,IP W H,CHEN Z Q,et al.A novel 3Dmodel retrieval approach using combined shape distribution[J].Multimedia tools and application,2014,69(3):799-818.
[7]LI B,JOHAN H.3D model retrieval using hybrid features and class information[J].Multimedia tools and applications,2013,62(3):821-846.
[8]SHILANE P,MIN P,KAZHDAN M,et al.The princeton shape benchmark[C]//Proceedings of Shape Modeling Applications.Genova:IEEE,2004:167-178.
[9]CANNY J.A computational approach to edge detection[J].IEEE transactions on pattern analysis and machine intelligence,1986,8(6):679-698.
[10]BELONGIE S,MALIK J,PUZICHA J.Shape matching and object recognition using shape contexts[J].IEEEtransactions on pattern analysis and machine intelligence,2002,24(4):509-522.
[11]陈实,马天骏,黄万红,等.基于形状上下文描述子的步态识别[J].模式识别与人工智能,2007,20(6):794-799.
[12]KUHN H W.The Hungarian method for the assignment problem[J].Naval research logistics quarterly,1955,2(1):83-97.
[13]LI B,LU Y J,LI C Y,et al.A comparison of 3Dshape retrieval methods based on a large-scale benchmark supporting multi modal queries[J].Computer vision and image understanding,2015,131:1-27.
[14]LI B,GODIL A A,AONO M,et al.SHREC'12 Track:Generic 3D Shape Retrieval[C]//Proceedings of the 5th Eurographics Conference on 3D Object Retrieval.Cagliari:Computing Machinery,2012:119-126.
[15]徐平安,唐雁,陈强,等.融合细节与整体特征的三维模型检索方法[J].西南大学学报(自然科学版),2015,37(10):131-137.
[16]LENG B,DU C,GUO S,et al.A powerful 3D model classification mechanism based on fusing multi-graph[J].Neurocomputing,2015,168:761-769.
[17]OSADA R,FUNKHOUSER T,CHAZELLE B,et al.Matching 3D models with shape distributions[C]//International Conference on Shape Modelling and Applications.Washington D C:IEEE,2008:154-166.
[18]KAZHDAN M,FUNKHOUSER T,RUSINKIEWICZ S.Rotation invariant spherical harmonic representation of3D shap descriptirs[J].Eurographics symposium on geometry processing,2003,43:156-164.
[19]杨文柱,刘晴,王思乐,等.基于深度卷积神经网络的羽绒图像识别[J].郑州大学学报(工学版),2018,39(2):11-17.
[20]WANG F,PENG J,LI Y.Hypergraph based feature fusion for 3-D object retrieval[J].Neurocomputing,2015,151:612-619.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |