A deep learning approach to the classification of 3D CAD models

Fei-wei QIN; Lu-ye LI; Shu-ming GAO; Xiao-ling YANG; Xiang CHEN

doi:10.1631/jzus.C1300185

Your Location：

Home >

Browse articles >

A deep learning approach to the classification of 3D CAD models

Computer & Automation | Updated：2022-05-19

- A deep learning approach to the classification of 3D CAD models
- 用于三维CAD模型分类的深度学习方法
- Frontiers of Information Technology & Electronic Engineering Vol. 15, Issue 2, Pages: 91-106(2014)
- Affiliations：
  
  State Key Lab of CAD & CG, Zhejiang University, Hangzhou 310058, China
- Author bio：
  
  [ "Fei-wei QIN, qinfeiwei@zjucadcg.cn" ]
  [ "Lu-ye LI, liluye@cad.zju.edu.cn" ]
  Shu-ming GAO, smgao@cad.zju.edu.cn
  [ "Xiao-ling YANG, xchen@cad.zju.edu.cn" ]
  [ "Xiang CHEN, sunny_aday@163.com" ]
- Funds：
- DOI：10.1631/jzus.C1300185
  CLC： TP391.72
- Received：09 July 2013，
  
  Revised：2014-1-15，
  
  Accepted：21 November 2013，
  
  Published：2014-02
- Accepted：
Scan QR Code
Fei-wei QIN, Lu-ye LI, Shu-ming GAO, et al. A deep learning approach to the classification of 3D CAD models[J]. Frontiers of Information Technology & Electronic Engineering, 2014, 15(2): 91-106.
DOI：

Fei-wei QIN, Lu-ye LI, Shu-ming GAO, et al. A deep learning approach to the classification of 3D CAD models[J]. Frontiers of Information Technology & Electronic Engineering, 2014, 15(2): 91-106. DOI： 10.1631/jzus.C1300185.

摘要

研究目的

模型分类对于工程领域中三维CAD模型的有效管理和重用非常关键。由于三维CAD模型分类固有的复杂性，难以通过设计一定的规则实现模型自动分类。因此，一些学者采用机器学习技术解决三维CAD模型的自动分类问题。受传统机器学习技术的制约，已有方法效果并不理想，无法应用于实际工业生产。近年来，深度学习取得了突破性进展，在图像分类、自然语言处理、语音识别等领域获得了不错效果。本文探索利用机器学习领域的最新研究成果——深度学习技术，对工程领域中常见的三维CAD模型进行自动分类。

创新要点

利用深度学习技术，模拟工程师人工识别三维零件的三个主要环节，构建了CAD模型的自动分类器；采用多种行之有效的训练策略，得到具有较好泛化性能的分类器。

研究方法

基于深度学习的三维CAD模型分类方法的主要步骤为：从制造企业获取足够的样本数据，构建三维CAD模型数据集；分析CAD领域的特点，选取合适的三维模型描述符进行特征提取，并处理为输入向量；利用深度学习技术模拟工程师人工识别工程零件的过程，设计分类器的拓扑结构并选择相应的组成元素，构建深层神经网络分类器；采用多种实用的训练技巧，使训练得到的分类器的自由参数取值尽可能逼近全局最优解，避免过拟合。

重要结论

实验数据表明，将深度学习技术与CAD领域知识结合，能够取得满意效果。深层神经网络分类器在测试集上的分类误差率低，足以满足工业生产的需求。

Abstract

Model classification is essential to the management and reuse of 3D CAD models. Manual model classification is laborious and error prone. At the same time

the automatic classification methods are scarce due to the intrinsic complexity of 3D CAD models. In this paper

we propose an automatic 3D CAD model classification approach based on deep neural networks. According to prior knowledge of the CAD domain

features are selected and extracted from 3D CAD models first

and then preprocessed as high dimensional input vectors for category recognition. By analogy with the thinking process of engineers

a deep neural network classifier for 3D CAD models is constructed with the aid of deep learning techniques. To obtain an optimal solution

multiple strategies are appropriately chosen and applied in the training phase

which makes our classifier achieve better performance. We demonstrate the efficiency and effectiveness of our approach through experiments on 3D CAD model datasets.

关键词

Keywords

references

J. Bai , , , S. Gao , , , W. Tang , , , 等 . . Design reuse oriented partial retrieval of CAD models . . Comput.-Aided Des. , , 2010 . . 42 ( ( 12 ): ): 1069 - - 1084 . . DOI: 10.1016/j.cad.2010.07.002 http://doi.org/10.1016/j.cad.2010.07.002 . .

Z. Barutcuoglu , , , C. DeCoro . . Hierarchical shape classification using Bayesian aggregation . . IEEE Int. Conf. on Shape Modeling and Applications , , 2006 . . p.44 - - 48 . . DOI: 10.1109/SMI.2006.15 http://doi.org/10.1109/SMI.2006.15 . .

Y. Bengio . . Learning deep architectures for AI . . Found. Trends Mach. Learn. , , 2009 . . 2 ( ( 1 ): ): 1 - - 127 . . DOI: 10.1561/2200000006 http://doi.org/10.1561/2200000006 . .

Y. Bengio , , , A. Courville , , , P. Vincent . . Representation learning: a review and new perspectives . . IEEE Trans. Pattern Anal. Mach. Intell. , , 2013 . . 35 ( ( 8 ): ): 1798 - - 1828 . . DOI: 10.1109/TPAMI.2013.50 http://doi.org/10.1109/TPAMI.2013.50 . .

J. Bergstra , , , O. Breuleux , , , F. Bastien , , , 等 . . Theano: a CPU and GPU math compiler in Python . . Proc. 9th Python in Science Conf. , , 2010 . . p.1 - - 7 . . . .

A.D. Bimbo , , , P. Pala . . Content-based retrieval of 3D models . . ACM Trans. Multim. Comput. Commun. Appl. , , 2006 . . 2 ( ( 1 ): ): 20 - - 43 . . DOI: 10.1145/1126004.1126006 http://doi.org/10.1145/1126004.1126006 . .

C.M. Bishop . . Neural Networks for Pattern Recognition , , : : Oxford Oxford University Press , , 1995 . . .

A. Bordes , , , X. Glorot , , , J. Weston , , , 等 . . A semantic matching energy function for learning with multi-relational data . . Mach. Learn. , , 2014 . . 94 ( ( 2 ): ): 233 - - 259 . . DOI: 10.1007/s10994-013-5363-6 http://doi.org/10.1007/s10994-013-5363-6 . .

D. Chen . . Three-Dimensional Model Shape Description and Retrieval Based on Light Field Descriptors . . PhD Thesis, National Taiwan University, Taiwan , , 2003 . . .

D. Chen , , , X. Tian , , , Y. Shen , , , 等 . . On visual similarity based 3D model retrieval . . Comput. Graph. Forum , , 2003 . . 22 ( ( 3 ): ): 223 - - 232 . . DOI: 10.1111/1467-8659.00669 http://doi.org/10.1111/1467-8659.00669 . .

S. Dreiseitl , , , L. Ohno-Machado . . Logistic regression and artificial neural network classification models: a methodology review . . J. Biomed. Inform. , , 2002 . . 35 ( ( 5 ): ): 352 - - 359 . . DOI: 10.1016/S1532-0464(03)00034-0 http://doi.org/10.1016/S1532-0464(03)00034-0 . .

R.O. Duda , , , P.E. Hart , , , D.G. Stork . . Pattern Classification (2nd Ed.) . . John Wiley & Sons, New York , , 2001 . . .

X. Fang , , , H. Luo , , , J. Tang . . Structural damage detection using neural network with learning rate improvement . . Comput. & Struct. , , 2005 . . 83 ( ( 25-26 ): ): 2150 - - 2161 . . DOI: 10.1016/j.compstruc.2005.02.029 http://doi.org/10.1016/j.compstruc.2005.02.029 . .

X. Glorot , , , Y. Bengio . . Understanding the difficulty of training deep feedforward neural networks . . Proc. Int. Conf. on Artificial Intelligence and Statistics , , 2010 . . p.249 - - 256 . . . .

T.G. Gunn . . The mechanization of design and manufacturing . . Sci. Am. , , 1982 . . 247 114 - - 130 . . DOI: 10.1038/scientificamerican0982-114 http://doi.org/10.1038/scientificamerican0982-114 . .

S. Haykin . . Neural Networks and Learning Machines (3rd Ed.) . . Prentice Hall, New York , , 2008 . . .

G.E. Hinton , , , R.R. Salakhutdinov . . Reducing the dimensionality of data with neural networks . . Science , , 2006 . . 313 ( ( 5786 ): ): 504 - - 507 . . DOI: 10.1126/science.1127647 http://doi.org/10.1126/science.1127647 . .

S. Hou , , , K. Lou , , , K. Ramani . . SVM-based semantic clustering and retrieval of a 3D model database . . Comput. Aided Des. Appl. , , 2005 . . 2 ( ( 1-4 ): ): 155 - - 164 . . . .

F.J. Huang , , , Y. LeCun . . Large-scale learning with SVM and convolutional nets for generic object categorization . . IEEE Computer Society Conf. on Computer Vision and Pattern Recognition , , 2006 . . p.284 - - 291 . . DOI: 10.1109/CVPR.2006.164 http://doi.org/10.1109/CVPR.2006.164 . .

C.Y. Ip , , , W.C. Regli . . Content-based classification of CAD models with supervised learning . . Comput. Aided Des. Appl. , , 2005a . . 2 ( ( 5 ): ): 609 - - 617 . . . .

C.Y. Ip , , , W.C. Regli . . Manufacturing classification of CAD models using curvature and SVMs . . Int. Conf. on Shape Modeling and Applications , , 2005b . . p.361 - - 365 . . DOI: 10.1109/SMI.2005.27 http://doi.org/10.1109/SMI.2005.27 . .

C.Y. Ip , , , W.C. Regli , , , L. Sieger , , , 等 . . Automated learning of model classifications . . Proc. 8th ACM Symp. on Solid Modeling and Applications , , 2003 . . p.322 - - 327 . . DOI: 10.1145/781606.781659 http://doi.org/10.1145/781606.781659 . .

N. Iyer , , , S. Jayanti , , , K. Lou , , , 等 . . Three-dimensional shape searching: state-of-the-art review and future trends . . Comput.-Aided Des. , , 2005 . . 37 ( ( 5 ): ): 509 - - 530 . . DOI: 10.1016/j.cad.2004.07.002 http://doi.org/10.1016/j.cad.2004.07.002 . .

K. Kavukcuoglu , , , P. Sermanet , , , Y. Boureau , , , 等 . . Learning convolutional feature hierarchies for visual recognition . . Proc. 24th Annual Conf. on Neural Information Processing Systems , , 2010 . . p.1090 - - 1098 . . . .

A. Krizhevsky , , , I. Sutskever , , , G.E. Hinton . . ImageNet classification with deep convolutional neural networks . . Proc. 26th Annual Conf. on Neural Information Processing Systems , , 2012 . . p.1106 - - 1114 . . . .

H. Larochelle , , , Y. Bengio , , , J. Louradour , , , 等 . . Exploring strategies for training deep neural networks . . J. Mach. Learn. Res. , , 2009 . . 10 ( ( 1 ): ): 1 - - 40 . . . .

J. Ngiam , , , Z. Chen , , , P.W. Koh , , , 等 . . Learning deep energy models . . Proc. 28th Int. Conf. on Machine Learning , , 2011 . . p.1105 - - 1112 . . . .

L. Prechelt . . Automatic early stopping using cross validation: quantifying the criteria . . Neur. Networks , , 1998 . . 11 ( ( 4 ): ): 761 - - 767 . . DOI: 10.1016/S0893-6080(98)00010-0 http://doi.org/10.1016/S0893-6080(98)00010-0 . .

M.A. Ranzato , , , V. Mnih , , , G.E. Hinton . . Generating more realistic images using gated MRF's . . Proc. 24th Annual Conference on Neural Information Processing Systems , , 2010 . . p.2002 - - 2010 . . . .

R. Reed . . Pruning algorithms—a survey . . IEEE Trans. Neur. Networks , , 1993 . . 4 ( ( 5 ): ): 740 - - 747 . . DOI: 10.1109/72.248452 http://doi.org/10.1109/72.248452 . .

P. Shilane , , , P. Min , , , M. Kazhdan , , , 等 . . The Princeton Shape Benchmark . . Proc. Conf. on Shape Modeling Applications , , 2004 . . p.167 - - 178 . . DOI: 10.1109/SMI.2004.1314504 http://doi.org/10.1109/SMI.2004.1314504 . .

W. Wang , , , X. Liu , , , L. Liu . . Shape matching and retrieval based on multiple feature descriptors . . Comput. Aided Draft. Des. Manuf. , , 2013 . . 23 ( ( 1 ): ): 60 - - 67 . . . .

W. Wei , , , Y. Yang , , , J. Lin , , , 等 . . Color-based 3D model classification using Hopfield neural network . . Proc. Int. Conf. on Computer Science and Software Engineering , , 2008 . . p.883 - - 886 . . DOI: 10.1109/CSSE.2008.1177 http://doi.org/10.1109/CSSE.2008.1177 . .

M.C. Wu , , , S.R. Jen . . A neural network approach to the classification of 3D prismatic parts . . Int. J. Adv. Manuf. Technol. , , 1996 . . 11 ( ( 5 ): ): 325 - - 335 . . DOI: 10.1007/BF01845691 http://doi.org/10.1007/BF01845691 . .

Y. Yao , , , L. Rosasco , , , A. Caponnetto . . On early stopping in gradient descent learning . . Constr. Approx. , , 2007 . . 26 ( ( 2 ): ): 289 - - 315 . . DOI: 10.1007/s00365-006-0663-2 http://doi.org/10.1007/s00365-006-0663-2 . .

D. Zhang , , , G. Lu . . An integrated approach to shape based image retrieval . . Proc. 5th Asian Conf. on Computer Vision , , 2002 . . p.652 - - 657 . . . .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Neural mesh refinement

Domain adaptation in reinforcement learning: a comprehensive and systematic study

Accurate estimation of 6-DoF tooth pose in 3D intraoral scans for dental applications using deep learning

Towards sustainable adversarial training with successive perturbation generation

Advances and challenges in artificial intelligence text generation

Related Author

Zhiwei ZHU

Xiang GAO

Lu YU

Yiyi LIAO

Amirfarhad FARHADI

Mitra MIRZAREZAEE

Arash SHARIFI

Mohammad TESHNEHLAB

Related Institution

Zhejiang Provincial Key Laboratory of Information Processing, Communication and Networking (IPCAN)

College of Information Science and Electronic Engineering, Zhejiang University

Department of Control Engineering, K.N. Toosi University of Technology

Department of Computer Engineering, Science and Research Branch, Islamic Azad University

Hangzhou Dental Hospital

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰