CAD models clustering with machine learning
Similarity assessment between 3D models is an important problem in many fields including medicine, biology and industry. As there is no direct method to compare 3D geometries, different model representations (shape signatures) are developed to enable shape description, indexing and clustering. Even...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Polish Academy of Sciences
2019-04-01
|
| Series: | Archive of Mechanical Engineering |
| Subjects: | |
| Online Access: | https://journals.pan.pl/Content/112046/PDF/AME_2019_128441.pdf |
| _version_ | 1811314913358905344 |
|---|---|
| author | Dawid Machalica Marek Matyjewski |
| author_facet | Dawid Machalica Marek Matyjewski |
| author_sort | Dawid Machalica |
| collection | DOAJ |
| description | Similarity assessment between 3D models is an important problem in many fields including medicine, biology and industry. As there is no direct method to compare 3D geometries, different model representations (shape signatures) are developed to enable shape description, indexing and clustering. Even though some of those descriptors proved to achieve high classification precision, their application is often limited. In this work, a different approach to similarity assessment of 3D CAD models was presented. Instead of focusing on one specific shape signature, 45 easy-to-extract shape signatures were considered simultaneously. The vector of those features constituted an input for 3 machine learning algorithms: the random forest classifier, the support vector classifier and the fully connected neural network. The usefulness of the proposed approach was evaluated with a dataset consisting of over 1600 CAD models belonging to 9 separate classes. Different values of hyperparameters, as well as neural network configurations, were considered. Retrieval accuracy exceeding 99% was achieved on the test dataset. |
| first_indexed | 2024-04-13T11:20:54Z |
| format | Article |
| id | doaj.art-4c35bf21e52f4d9a9a0a60974c18c349 |
| institution | Directory Open Access Journal |
| issn | 2300-1895 |
| language | English |
| last_indexed | 2024-04-13T11:20:54Z |
| publishDate | 2019-04-01 |
| publisher | Polish Academy of Sciences |
| record_format | Article |
| series | Archive of Mechanical Engineering |
| spelling | doaj.art-4c35bf21e52f4d9a9a0a60974c18c3492022-12-22T02:48:49ZengPolish Academy of SciencesArchive of Mechanical Engineering2300-18952019-04-01vol. 66No 2133152https://doi.org/10.24425/ame.2019.128441CAD models clustering with machine learningDawid Machalica0Marek Matyjewski1Warsaw Institute of Aviation, Warsaw, Poland.Warsaw University of Technology, Institute of Aeronautics and Applied Mechanics, Warsaw, Poland.Similarity assessment between 3D models is an important problem in many fields including medicine, biology and industry. As there is no direct method to compare 3D geometries, different model representations (shape signatures) are developed to enable shape description, indexing and clustering. Even though some of those descriptors proved to achieve high classification precision, their application is often limited. In this work, a different approach to similarity assessment of 3D CAD models was presented. Instead of focusing on one specific shape signature, 45 easy-to-extract shape signatures were considered simultaneously. The vector of those features constituted an input for 3 machine learning algorithms: the random forest classifier, the support vector classifier and the fully connected neural network. The usefulness of the proposed approach was evaluated with a dataset consisting of over 1600 CAD models belonging to 9 separate classes. Different values of hyperparameters, as well as neural network configurations, were considered. Retrieval accuracy exceeding 99% was achieved on the test dataset.https://journals.pan.pl/Content/112046/PDF/AME_2019_128441.pdf3d shape matching3d shape retrieval3d model recognition3d shapecontent-based retrievalmachine learning |
| spellingShingle | Dawid Machalica Marek Matyjewski CAD models clustering with machine learning Archive of Mechanical Engineering 3d shape matching 3d shape retrieval 3d model recognition 3d shape content-based retrieval machine learning |
| title | CAD models clustering with machine learning |
| title_full | CAD models clustering with machine learning |
| title_fullStr | CAD models clustering with machine learning |
| title_full_unstemmed | CAD models clustering with machine learning |
| title_short | CAD models clustering with machine learning |
| title_sort | cad models clustering with machine learning |
| topic | 3d shape matching 3d shape retrieval 3d model recognition 3d shape content-based retrieval machine learning |
| url | https://journals.pan.pl/Content/112046/PDF/AME_2019_128441.pdf |
| work_keys_str_mv | AT dawidmachalica cadmodelsclusteringwithmachinelearning AT marekmatyjewski cadmodelsclusteringwithmachinelearning |