{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T05:16:36Z","timestamp":1771046196010,"version":"3.50.1"},"reference-count":39,"publisher":"ASME International","issue":"1","license":[{"start":{"date-parts":[[2020,7,21]],"date-time":"2020-07-21T00:00:00Z","timestamp":1595289600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Deep neural networks (DNNs) have been successful in classification and retrieval tasks of images and text, as well as in the graphics domain. However, these DNNs algorithms do not translate to 3D engineering models used in the product design and manufacturing. This paper studies the use of multi-view convolutional neural network (MVCNN) algorithm enhanced by the addition of engineering metadata, for classification and retrieval of 3D computer-aided design (CAD) models. The proposed algorithm (MVCNN++) builds on the MVCNN algorithm with the addition of part dimension data, improving its efficacy for manufacturing part classification and yielding an improvement in classification accuracy of 5.8% over the original version. Unlike datasets used for 3D shape classification and retrieval in the computer graphics domain, engineering level description of 3D CAD models do not yield themselves to neat, distinct classes. Techniques such as relaxed-classification and prime angled cameras for capturing feature detail were used to address training data capture issues specific to 3D CAD models, along with the use of transfer learning to reduce training time. Our study has shown that DNNs can be used to search and discover relevant 3D engineering models in large public repositories, making 3D models accessible to the community.<\/jats:p>","DOI":"10.1115\/1.4047486","type":"journal-article","created":{"date-parts":[[2020,6,12]],"date-time":"2020-06-12T18:29:13Z","timestamp":1591986553000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":25,"title":["MVCNN++: Computer-Aided Design Model Shape Classification and Retrieval Using Multi-View Convolutional Neural Networks"],"prefix":"10.1115","volume":"21","author":[{"given":"Atin","family":"Angrish","sequence":"first","affiliation":[{"name":"Department of Industrial and Systems Engineering, North Carolina State University, 400 Daniels Hall, 111 Lampe Drive, Raleigh, NC 27695-7906"}]},{"given":"Akshay","family":"Bharadwaj","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, North Carolina State University, 400 Daniels Hall, 111 Lampe Drive, Raleigh, NC 27695-7906"}]},{"given":"Binil","family":"Starly","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, North Carolina State University, 400 Daniels Hall, 111 Lampe Drive, Raleigh, NC 27695-7906"}]}],"member":"33","published-online":{"date-parts":[[2020,7,21]]},"reference":[{"issue":"11","key":"2021011101555452700_CIT0001","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based Learning Applied to Document Recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"2021011101555452700_CIT0002","first-page":"945","article-title":"Multi-view Convolutional Neural Networks for","author":"Su","year":"2015"},{"key":"2021011101555452700_CIT0003","first-page":"248","article-title":"Imagenet: A Large-Scale Hierarchical Image Database","author":"Deng","year":"2009"},{"key":"2021011101555452700_CIT0004","doi-asserted-by":"crossref","DOI":"10.1115\/MSEC2019-2882","article-title":"Development of a Pilot Manufacturing Cyberinfrastructure With an Information Rich Mechanical CAD 3D Model Repository","author":"Bharadwaj","year":"2019"},{"issue":"9","key":"2021011101555452700_CIT0005","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1016\/j.cad.2006.06.007","article-title":"Developing an Engineering Shape Benchmark for CAD Models","volume":"38","author":"Jayanti","year":"2006","journal-title":"Comput.-Aided Des."},{"key":"2021011101555452700_CIT0006","first-page":"9601","article-title":"ABC: A Big CAD Model Dataset For Geometric Deep Learning","author":"Koch","year":"2019"},{"issue":"2","key":"2021011101555452700_CIT0007","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1109\/TPAMI.1980.4766990","article-title":"Three-dimensional Moment Invariants","volume":"2","author":"Sadjadi","year":"1980","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"2021011101555452700_CIT0008","first-page":"1","article-title":"Pattern Recognition of 3D CAD Objects: Towards an Electronic Yellow Pages of Mechanical Parts","volume":"1","author":"Cybenko","year":"1997","journal-title":"Int. J. Smart Eng. Syst. Des."},{"issue":"3","key":"2021011101555452700_CIT0009","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1007\/s11042-007-0181-0","article-title":"A Survey of Content Based 3D Shape Retrieval Methods","volume":"39","author":"Tangelder","year":"2007","journal-title":"Multimed Tools Appl."},{"key":"2021011101555452700_CIT0010","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1007\/3-540-45404-7_52","volume-title":"Joint Pattern Recognition Symposium","author":"Saupe","year":"2001"},{"key":"2021011101555452700_CIT0011","first-page":"156","article-title":"Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors","author":"Kazhdan","year":"2003"},{"issue":"4","key":"2021011101555452700_CIT0012","doi-asserted-by":"crossref","first-page":"041006","DOI":"10.1115\/1.4043211","article-title":"\u201cFabSearch\u201d: A 3D CAD Model-Based Search Engine for Sourcing Manufacturing Services","volume":"19","author":"Angrish","year":"2019","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2021011101555452700_CIT0013","first-page":"176","article-title":"Machining Feature-Based Comparisons of Mechanical Parts","author":"Cicirello","year":"2001"},{"issue":"6","key":"2021011101555452700_CIT0014","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1109\/70.897789","article-title":"Manufacturing Feature Recognition From Solid Models: A Status Report","volume":"16","author":"Han","year":"2000","journal-title":"IEEE Trans. Rob. Autom."},{"issue":"1","key":"2021011101555452700_CIT0015","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/S0010-4485(01)00178-6","article-title":"A Database System of Mechanical Components Based on Geometric and Topological Similarity. Part II: Indexing, Retrieval, Matching, and Similarity Assessment","volume":"35","author":"El-Mehalawi","year":"2003","journal-title":"Comput.-Aided Des."},{"key":"2021011101555452700_CIT0016","first-page":"229","article-title":"Reeb Graph Based Shape Retrieval for CAD","author":"Bespalov","year":"2008"},{"key":"2021011101555452700_CIT0017","first-page":"130","article-title":"Skeleton Based Shape Matching and Retrieval","author":"Sundar","year":"2003"},{"issue":"3","key":"2021011101555452700_CIT0018","first-page":"204","article-title":"Group Technology Classification From Feature-Based Geometric Models","volume":"2","author":"Shah","year":"1989","journal-title":"Manuf. Rev."},{"issue":"4","key":"2021011101555452700_CIT0019","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/0278-6125(94)90034-5","article-title":"Grouping Parts With a Neural Network","volume":"13","author":"Chung","year":"1994","journal-title":"J. Manuf. Syst."},{"issue":"5","key":"2021011101555452700_CIT0020","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1016\/j.cad.2004.07.002","article-title":"Three-dimensional Shape Searching: State-of-the-art Review and Future Trends","volume":"37","author":"Iyer","year":"2005","journal-title":"Comput.-Aided Des."},{"issue":"2","key":"2021011101555452700_CIT0021","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1115\/1.1577356","article-title":"A Survey of Shape Similarity Assessment Algorithms for Product Design and Manufacturing Applications","volume":"3","author":"Cardone","year":"2003","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"7","key":"2021011101555452700_CIT0022","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/0010-4485(92)90064-H","article-title":"Automatic Form-Feature Recognition Using Neural-Network-Based Techniques on Boundary Representations of Solid Models","volume":"24","author":"Prabhakar","year":"1992","journal-title":"Comput.-Aided Des."},{"issue":"9","key":"2021011101555452700_CIT0023","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1080\/00207549108948048","article-title":"A Neural Network System for Shape-Based Classification and Coding of Rotational Parts","volume":"29","author":"Kaparthi","year":"1991","journal-title":"Int. J. Prod. Res."},{"key":"2021011101555452700_CIT0024","first-page":"84","volume-title":"Commun. ACM","author":"Krizhevsky","year":"2017"},{"key":"2021011101555452700_CIT0025","first-page":"770","article-title":"Deep Residual Learning for Image Recognition","author":"He","year":"2016"},{"key":"2021011101555452700_CIT0026","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015"},{"key":"2021011101555452700_CIT0027","first-page":"1912","article-title":"3D Shapenets: A Deep Representation for Volumetric Shapes","author":"Wu","year":"2015"},{"key":"2021011101555452700_CIT0028","first-page":"922","article-title":"Voxnet: A 3D Convolutional Neural Network for Real-Time Object Recognition","author":"Maturana","year":"2015"},{"key":"2021011101555452700_CIT0029","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.cad.2018.03.006","article-title":"FeatureNet: Machining Feature Recognition Based on 3D Convolution Neural Network","volume":"101","author":"Zhang","year":"2018","journal-title":"Comput.-Aided Des."},{"key":"2021011101555452700_CIT0030","article-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","author":"Simonyan","year":"2014"},{"issue":"10","key":"2021011101555452700_CIT0031","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A Survey on Transfer Learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans. Knowl. and Data Eng."},{"issue":"10","key":"2021011101555452700_CIT0032","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A Survey on Transfer Learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"4","key":"2021011101555452700_CIT0033","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1109\/TPAMI.2018.2814042","article-title":"Beyond Sharing Weights for Deep Domain Adaptation","volume":"41","author":"Rozantsev","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2021011101555452700_CIT0034","article-title":"Knowledge Projection for Deep Neural Networks","author":"Zhang","year":"2017"},{"key":"2021011101555452700_CIT0035","first-page":"5010","article-title":"Rotationnet: Joint Object Categorization and Pose Estimation Using Multiviews From Unsupervised Viewpoints","author":"Kanezaki","year":"2018"},{"key":"2021011101555452700_CIT0036","first-page":"264","article-title":"GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition","author":"Feng","year":"2018"},{"key":"2021011101555452700_CIT0037","article-title":"FabWave CAD Repository Categorized Part Classes","author":"Starly"},{"key":"2021011101555452700_CIT0038","unstructured":"Keras\n          , 2020, \u201cKeras: Deep Learning Library for Theano and Tensorflow.\u201d URL: https:\/\/github.com\/keras-team\/keras, no. 8:T1."},{"key":"2021011101555452700_CIT0039","author":"Abadi","year":"2016"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/doi\/10.1115\/1.4047486\/6613606\/jcise_21_1_011001.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/doi\/10.1115\/1.4047486\/6613606\/jcise_21_1_011001.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,14]],"date-time":"2021-01-14T04:15:21Z","timestamp":1610597721000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/doi\/10.1115\/1.4047486\/1084494\/MVCNN-Computer-Aided-Design-Model-Shape"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,21]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,2,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4047486","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,21]]},"article-number":"011001"}}