基于渲染图像角度结构特征的三维模型检索方法

计算机科学 ›› 2018, Vol. 45 ›› Issue (11A): 251-255.

基于渲染图像角度结构特征的三维模型检索方法

刘志, 潘晓彬

浙江工业大学计算机科学与技术学院杭州310023

出版日期:2019-02-26 发布日期:2019-02-26
作者简介:刘志(1969-),女,博士,教授,CCF会员,主要研究方向为三维模型检索、图像处理等,E-mail:lzhi@zjut.edu.cn;潘晓彬(1992-),男,硕士生,主要研究方向为三维模型检索。
基金资助:
本文受浙江省自然科学基金(LY16F020033)资助。

3D Model Retrieval Method Based on Angle Structure Feature of Render Image

LIU Zhi, PAN Xiao-bin

College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China

Online:2019-02-26 Published:2019-02-26

摘要/Abstract

摘要： 为了充分利用三维模型的颜色、形状、纹理等特征,提出以三维模型渲染图像为数据集,利用渲染图像角度结构特征实现三维模型检索。首先,该方法以三维模型渲染图像为测试集,利用已有类别标记的自然图像作为训练集,通过骨架形状上下文特征对渲染图像进行分类,提取角度结构特征,建立特征库;然后,对输入的自然图像提取角度结构特征,与特征库中的角度结构特征进行相似度匹配计算,实现三维模型检索。实验结果表明,充分利用渲染图像的颜色、形状和空间信息是实现三维模型检索的有效方法。

关键词: 骨架形状上下文, 角度结构特征, 三维模型检索, 渲染图像

Abstract: In order to make full use of the color,shape,texture and other features in the 3D model,a 3D model retrieval method was proposed based on angle structure features of render images.Firstly,the 3D model render images are taken as a test dataset and the marked natural images are taken as a training set.The render images are classified based on their skeleton-associated shape context and the angle structure features are extracted to establish the feature library.Then,the angle structure features of the input natural images are extracted.The distance measurement method is used to calculate the similarity between the angle structure feature of input natural image and those features in the feature library.The experimental results show that the full utilization of the color,shape and color space information of the render image is an effective way to achieve 3D model retrieval.

Key words: 3D model retrieval, Angle structure feature, Render image, Skeleton-associated shape context

中图分类号:

TP391

刘志, 潘晓彬. 基于渲染图像角度结构特征的三维模型检索方法[J]. 计算机科学, 2018, 45(11A): 251-255. https://doi.org/

LIU Zhi, PAN Xiao-bin. 3D Model Retrieval Method Based on Angle Structure Feature of Render Image[J]. Computer Science, 2018, 45(11A): 251-255. https://doi.org/

参考文献

[1]YOON S M,SCHERER M,SCHRECK T,et al.Sketch-based 3D model retrieval using diffusion tensor fields of suggestive contours[C]∥Proceedings of the 18th ACM International Conference on Multimedia.ACM,2010:193-200.
[2]LEI H,LI Y,CHEN H,et al.A novel sketch-based 3D model retrieval method by integrating skeleton graph and contour feature[J].Journal of Advanced Mechanical Design,Systems,and Manufacturing,2015,9(4).
[3]ZHANG J,BAI C,NEZAN J F,et al.Joint motion model for local stereo video-matching method[J].Optical Engineering,2015,54(12):123108.
[4]ZHANG J,SHANG J,ZHANG G.Verification for different contrail parameterizations based on integrated satellite observation and ECMWF reanalysis data[J].Advances in Meteorology,2017,2017(1):1-11.
[5]李兰,刘洋.基于内容的小波变换图像检索方法[J].计算机科学,2015,42(2):306-310.
[6]翟奥博,温显斌,张鑫.基于改进双树复小波和灰度-梯度共生矩阵的纹理图像检索算法[J].计算机科学,2017(6):274-277.
[7]PASQUALOTTO G,ZANUTTIGH P,CORTELAZZO G M. Combining color and shape descriptors for 3D model retrieval[J].Signal Processing:Image Communication,2013,28(6):608-623.
[8]BIASOTTI S,CERRI A,AONO M,et al.Retrieval and classification methods for textured 3D models:a comparative study[J].The Visual Computer,2016,32(2):217-241.
[9]LIU G H,LI Z Y,ZHANG L,et al.Image retrieval based on micro-structure descriptor[J].Pattern Recognition,2011,44(9):2123-2133.
[10]LIU G H,YANG J Y,LI Z Y.Content-based image retrieval using computational visual attention model[J].Pattern Recognition,2015,48(8):2554-2566.
[11]ZHAO M,ZHANG H,MENG L.An angle structure descriptor for image retrieval[J].China Communications,2016,13(8):222-230.
[12]SHEN W,JIANG Y,GAO W,et al.Shape recognition by bag of skeleton-associated contour parts[J].Pattern Recognition Letters,2016,83:321-329.
[13]SHEN W,BAI X,YANG X W,et al.Skeleton pruning as trade-off between skeleton simplicity and reconstruction error[J].Science China Information Sciences,2013,56(4):1-14.
[14]CRAMMER K,SINGER Y.On the algorithmic implementation of multiclass kernel-based vector machines[J].Journal of Machine Learning Research,2001,2(12):265-292.
[15]MOORE R,DENERO J.L1 and L2 regularization for multiclass hinge loss models[C]∥MLSLP.2011:1-5.
[16]BAI X,LIU W,TU Z.Integrating contour and skeleton for shape classification[C]∥2009 IEEE 12th International Confe-rence on Computer Vision Workshops (ICCV Workshops).IEEE,2009:360-367.
[17]SHEN W,WANG X,YAO C,et al.Shape recognition by combining contour and skeleton into a mid-level representation[C]∥Chinese Conference on Pattern Recognition.Springer Berlin Heidelberg,2014:391-400.
[18]WANG X,WANG Z.A novel method for image retrieval based on structure elements’ descriptor[J].Journal of Visual Communication and Image Representation,2013,24(1):63-74.
[19]刘志,尹世超,潘翔,等.基于特征线条的三维模型检索方法[J].计算机辅助设计与图形学学报,2016,28(9):1512-1520.
[20]SHILANE P,MIN P,KAZHDAN M,et al.The princeton shape benchmark[C]∥Proceedings of Shape Modeling Applications,2004.IEEE,2004:167-178.

相关文章 8

[1]	刘志, 李江川. 基于深度卷积神经网络的三维模型检索 3D Model Retrieval Based on Deep Convolution Neural Network 计算机科学, 2019, 46(1): 278-284. https://doi.org/10.11896／j.issn.1002-137X.2019.01.043
[2]	周燕,曾凡智,杨跃武. 基于多特征融合的三维模型检索算法 3D Model Retrieval Algorithm Based on Multi Feature Fusion 计算机科学, 2016, 43(7): 303-309. https://doi.org/10.11896/j.issn.1002-137X.2016.07.056
[3]	朱新懿,耿国华. 一种结合局部对称的三维模型对齐方法 3D Model’s Alignment Approach Combining Partial Symmetry 计算机科学, 2015, 42(2): 277-279. https://doi.org/10.11896/j.issn.1002-137X.2015.02.058
[4]	赵元庆,吴华. 多尺度特征和神经网络相融合的手写体数字识别 Handwritten Numeral Recognition Based on Multi-scale Features and Neural Network 计算机科学, 2013, 40(8): 316-318.
[5]	孙晓鹏，纪燕杰，李翠芳，魏小鹏. 三维网格模型增量式聚类检索 3D Mesh Model Retrieval Using Incremental Clustering 计算机科学, 2011, 38(11): 248-251.
[6]	郑赢，周明全，耿国华，高原. 多特征动态融合的三维模型检索方法 3D Model Retrieval on Multi-feature Dynamic Integration 计算机科学, 2010, 37(7): 260-263.
[7]	赵鹏飞,金峰. 基于面积分布的三维模型检索算法 Retrieval of 3D Models Based on Area Shape Distribution 计算机科学, 2009, 36(7): 298-299. https://doi.org/10.11896/j.issn.1002-137X.2009.07.074
[8]	林金杰韦伟杨育彬. 面向内容的三维模型数据库设计及其检索系统的实现计算机科学, 2008, 35(10): 238-242.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed