RECORD
A learning-based approach to feature recognition of Engineering shapes
Computer Vision and Pattern Recognition · Submitted 15 Dec 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim A comparison has been done with other non-network based machine learning approaches to show that our approach has the highest accuracy.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
In this paper, we propose a machine learning approach to recognise engineering shape features such as holes, slots, etc. in a CAD mesh model. With the advent of digital archiving, newer manufacturing techniques such as 3D printing, scanning of components and reverse engineering, CAD data is proliferated in the form of mesh model representation. As the number of nodes and edges become larger in a mesh model as well as the possibility of presence of noise, direct application of graph-based approaches would not only be expensive but also difficult to be tuned for noisy data. Hence, this calls for newer approaches to be devised for feature recognition for CAD models represented in the form of mesh. Here, we show that a discrete version of Gauss map can be used as a signature for a feature learning. We show that this approach not only requires fewer memory requirements but also the training time is quite less. As no network architecture is involved, the number of hyperparameters are much lesser and can be tuned in a much faster time. The recognition accuracy is also very similar to that of the one obtained using 3D convolutional neural networks (CNN) but in much lesser running time and storage requirements. A comparison has been done with other non-network based machine learning approaches to show that our approach has the highest accuracy. We also show the recognition results for CAD models having multiple features as well as complex/interacting features obtained from public benchmarks. The ability to handle noisy data has also been demonstrated.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | In this paper, we propose a machine learning approach to recognise engineering shape features such as holes, slots, etc. in a CAD mesh model. | contribution 1.00 | 0.80 | 0.18 | asserted 0.93 |
| s1 | With the advent of digital archiving, newer manufacturing techniques such as 3D printing, scanning of components and reverse engineering, CAD data is proliferated in the form of mesh model representation. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s2 | As the number of nodes and edges become larger in a mesh model as well as the possibility of presence of noise, direct application of graph-based approaches would not only be expensive but also difficult to be tuned for noisy data. | background 0.79 | 0.13 | 0.02 | asserted 0.79 |
| s3 | Hence, this calls for newer approaches to be devised for feature recognition for CAD models represented in the form of mesh. | gap 0.74 | 0.07 | 0.04 | asserted 0.84 |
| s4 | Here, we show that a discrete version of Gauss map can be used as a signature for a feature learning. | method 0.82 | 0.86 | 0.15 | asserted 0.99 |
| s5 | We show that this approach not only requires fewer memory requirements but also the training time is quite less. | result 0.96 | 0.93 | 0.14 | asserted 1.00 |
| s6 | As no network architecture is involved, the number of hyperparameters are much lesser and can be tuned in a much faster time. | result 0.67 | 0.73 | 0.06 | asserted 1.00 |
| s7 | The recognition accuracy is also very similar to that of the one obtained using 3D convolutional neural networks (CNN) but in much lesser running time and storage requirements. | result 0.99 | 0.91 | 0.27 | asserted 1.00 |
| s8 | A comparison has been done with other non-network based machine learning approaches to show that our approach has the highest accuracy. | result 0.96 | 0.94 | 0.18 | asserted 1.00 |
| s9 | We also show the recognition results for CAD models having multiple features as well as complex/interacting features obtained from public benchmarks. | result 0.76 | 0.94 | 0.07 | asserted 1.00 |
| s10 | The ability to handle noisy data has also been demonstrated. | result 0.93 | 0.91 | 0.06 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
In this paper, we propose a machine learning approach to recognise engineering shape features such as holes, slots, etc. in a CAD mesh model. With the advent of digital archiving, newer manufacturing techniques such as 3D printing, scanning of components and reverse engineering, CAD data is proliferated in the form of mesh model representation. As the number of nodes and edges become larger in a mesh model as well as the possibility of presence of noise, direct application of graph-based approaches would not only be expensive but also difficult to be tuned for noisy data. Hence, this calls for newer approaches to be devised for feature recognition for CAD models represented in the form of mesh. Here, we show that a discrete version of Gauss map can be used as a signature for a feature learning. We show that this approach not only requires fewer memory requirements but also the training time is quite less. As no network architecture is involved, the number of hyperparameters are much lesser and can be tuned in a much faster time. The recognition accuracy is also very similar to that of the one obtained using 3D convolutional neural networks (CNN) but in much lesser running time and storage requirements. A comparison has been done with other non-network based machine learning approaches to show that our approach has the highest accuracy. We also show the recognition results for CAD models having multiple features as well as complex/interacting features obtained from public benchmarks. The ability to handle noisy data has also been demonstrated.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.