您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(工学版)》

山东大学学报(工学版) ›› 2017, Vol. 47 ›› Issue (4): 19-24.doi: 10.6040/j.issn.1672-3961.0.2016.382

• • 上一篇    下一篇

基于流形排序的三维模型检索方法

牟春倩,唐雁*,胡金戈   

  1. 西南大学计算机与信息科学学院, 重庆 400715
  • 收稿日期:2016-10-13 出版日期:2017-08-20 发布日期:2016-10-13
  • 通讯作者: 唐雁(1965— ),女,重庆人,教授,主要研究方向为智能科学.E-mail:ytang@swu.edu.cn E-mail:mcq0207@email.swu.edu.cn
  • 作者简介:牟春倩(1992— ),女,四川成都人,硕士研究生,主要研究方向为三维模型检索.E-mail:mcq0207@email.swu.edu.cn
  • 基金资助:
    中央高校基本科研业务费专项资金资助项目(XDJK2015C110);教育部“春晖计划”资助项目(z2011149)

A new 3D model retrieval method based on manifold ranking

MOU Chunqian, TANG Yan*, HU Jinge   

  1. College of Computer and Information Science, Southwest University, Chongqing 400715, China
  • Received:2016-10-13 Online:2017-08-20 Published:2016-10-13

摘要: 针对现有的基于视图的三维模型检索方法大多将二维投影视图特征直接用于表示三维模型,忽略不同视点下的二维投影视图特征的贡献度的问题,提出一种基于流形排序的三维模型检索方法,关注不同二维投影视图特征的贡献度。通过旋转三维模型获得34张不同视点的二维投影视图,采用基于尺度不变特征变换(scale invariant feature transform, SIFT)特征的词袋模型提取34张二维投影视图的词频向量特征,利用流形排序将同一个三维模型的34个词频向量特征聚合成一个三维模型特征。试验表明,基于流形排序的三维模型检索方法能够有效地提高检索结果的准确率。

关键词: 三维模型检索, 二维投影视图, 流形排序, 词袋模型, SIFT特征

Abstract: Most existing view-based 3D model retrieval methods used features of 2D projection views to represent a 3D model directly, ignored their contributions to a 3D model. Therefore, a new 3D model retrieval method based on manifold ranking was proposed, which focused on the contributions of 2D projected views features. 2D projected views from 34 different viewpoints obtained through rotation, word frequency vector featuresextracted by bag-of-feature based on scaleinvariant feature transform(SIFT)features, then aggregated 34 word frequency vector features of a 3D model into a 3D model feature. The experimental results showed that our method improved the retrieval accuracy well.

Key words: 2D projected view, SIFT feature, 3D model retrieval, manifold ranking, bag-of-feature

中图分类号: 

  • TP319
[1] 张开兴,张树生,刘贤喜. 三维 CAD 模型检索技术研究现状与发展分析[J]. 农业机械学报, 2013, 44(7): 256-263. ZHANG Kaixing, ZHANG Shusheng, LIU Xianxi. Current research and feature development of 3-D CAD model retrieval[J]. Transactions of the Chinese Society for Agricultural Machinery, 2013, 44(7):256-263.
[2] SHIH Jauling, LEE Changhsing, WANG Jiantang. A new 3D model retrieval approach based on the elevation descriptor[J]. Pattern Recognition, 2007, 40(1): 283-295.
[3] CHEN Qiang, YU Yongmei. 3D CAD model retrieval based on feature fusion[J]. Advanced Materials Research, 2013, 765: 316-319.
[4] OSADA Robert, FUNKHOUSER Thomas, CHAZELLE Bernard, et al. Shape distributions[J]. Acm Transactions on Graphics, 2002, 21(4):807-832.
[5] MIRELA Benchen, CRAIG Gotsman. Characterizing shape using conformal factors[C] //Eurographics Workshop on 3D Object Retrieval. Crete, Greece: The Eurographics Association, 2008: 1-8.
[6] CHEN Dingyun, TIAN Xiaopei, SHEN Yute, et al. On visual similarity based 3D model retrieval[J]. Computer Graphics Forum, 2003, 22(3):223-232.
[7] OHBUCHI Ryutarou, OSADA Kunio, FURUYA Takahiko, et al. Salient local visual features for shape-based 3D model retrieval[C] //Shape Modeling and Applications. New York, USA: IEEE, 2008: 93-102.
[8] 郑赢,周明全,耿国华,等. 多特征动态融合的三维模型检索方法[J]. 计算机科学, 2010, 37(7): 260-263. ZHENG Ying, ZHOU Mingquan, GENG Guohua, et al. 3D model retrieval on multi-feature dynamic integration[J]. Computer Science, 2013, 37(7):260-263.
[9] LI Bo, JOHAN Henry. 3D model retrieval using hybrid features and class information[J]. Multimedia Tools and Applications, 2013, 62(3): 821-846.
[10] 徐平安, 唐雁, 牟春倩,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(10):131-137. XU Pingan, TANG Yan, MOU Chunqian, et al. A new 3D model retrieval method combining local and global features[J]. Journal of Southwest University(Natural Science), 2015(10):131-137.
[11] 李朋杰. 面向三维模型检索的特征提取算法研究[D]. 北京:北京邮电大学计算机学院,2013. LI Pengjie. Research on feature extraction algorithms for 3D model retrieval[D]. Beijing: School of Computer Science, Beijing University of Posts and Telecommunications, 2013.
[12] ZHOU Dengyong, WESTON Jason, GRETTON Arthur, et al. Ranking on data manifolds[C] //Annual Conference on Neural Information Processing Systems. Vancouver, Canada: MIT Press, 2003:169-176.
[13] LOWE David G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[14] 杨川. 基于先验融合和流形排序的显著目标检测[D]. 大连:大连理工大学信息与通信工程学院, 2013. YANG Chuan. Salient object detection based on prior integration and manifold ranking[D]. Dalian: School of Information and Communication Engineering, Dalian University of Technology, 2013.
[15] 朱征宇, 汪梅. 基于Manifold Ranking和结合前景背景特征的显著性检测[J]. 计算机应用, 2016, 36(9):2560-2565. ZHU Zhengyu, WANG Mei. Saliency detection combining foreground and background features based on manifold ranking[J]. Journal of Computer Applications, 2016, 36(9):2560-2565.
[16] FURUYA Takahiko, OHBUCHI Ryutarou. Diffusion-on-manifold aggregation of local features for shape-based 3D model retrieval[C] //Proceedings of the 5th ACM on International Conference on Multimedia Retrieval. Shanghai: ACM, 2015: 171-178.
[17] SHILANE Philip, MIN Patrick, KAZHDAN Michael, et al. The princeton shape benchmark(Figure 1 and 2)[J]. Proceedings of Shape Modeling International, 2004(6):167-178.
[18] LI Bo, GODIL Afzal, AONO Masaki, et al. SHREC'12 track: generic 3D shape retrieval[J]. Eurographics Conference on 3D Object Retrieval, 2012(5):119-126.
[19] SAUPE Dietmar, VRANIC Dejan V. 3D model retrieval with spherical harmonics and moments[J]. Lecture Notes in Computer Science, 2001(2191):392-397.
[20] DING Ke, WANG Wei, LIU Yunhui. 3D model retrieval using bag-of-view-words[J]. Multimedia Tools & Applications, 2014, 72(3):2701-2722.
[21] KAZHDAN Michael, FUNKHOUSER Thomas, RUSINKIEWICZ Szymon. Rotation invariant spherical harmonic representation of 3D shapedescriptors[C] //Proceedings of the 2003 Eurographics. Aachen, Germany: ACM, 2003:156-164.
[1] 牟春倩,唐雁. 融合整体和局部信息的三维模型检索方法[J]. 山东大学学报(工学版), 2016, 46(6): 48-53.
[2] 魏巍,张艳宁. 基于半监督隐含狄利克雷分配的人脸姿态判别方法[J]. 山东大学学报(工学版), 2011, 41(3): 17-22.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!