# Sharp Feature Detection as a Useful Tool in Smart Manufacturing

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

#### Prior Work

## 2. Methods and Materials

#### 2.1. Edge Points Detection

#### 2.1.1. PCA—Normal Estimation

- $({\lambda}_{0}\le {\lambda}_{1}\le {\lambda}_{2})\wedge ({\lambda}_{1}\approx {\lambda}_{2})$
- $({\lambda}_{0}\le {\lambda}_{1}\le {\lambda}_{2})\wedge ({\lambda}_{0}\approx {\lambda}_{1})$
- $({\lambda}_{0}\le {\lambda}_{1}\le {\lambda}_{2})\wedge ({\lambda}_{0}\approx {\lambda}_{1}\approx {\lambda}_{2})$.

#### 2.1.2. Region Growing—Initial Normal Threshold Value $th{r}_{{\theta}_{N}}$

#### 2.2. B-Spline Edge Representation

## 3. Results and Discussion

#### 3.1. Estimation of Normal Threshold $th{r}_{{\theta}_{N}}$

#### 3.2. B-Spline Curve Fitting

## 4. Conclusions

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## Abbreviations

RP | Rapid Prototyping |

RE | Reverse Engineering |

CAD | Computer Aided Design |

PCA | Principal Component Analysis |

STL | Standard Tessellation Language |

NURBS | Non-Uniform Rational B-spline |

## Appendix A

${\mathit{thr}}_{{\mathit{\theta}}_{\mathit{N}}}$ | 0.5 | 2 | 4 | 6 | 14 | |
---|---|---|---|---|---|---|

${M}_{1}$ | ||||||

$per{c}_{N}$ | 4.71 | 1.57 | 0.47 | 0.05 | 0.02 | |

${M}_{2}$ | ||||||

$per{c}_{N}$ | 4.34 | 3.36 | 1.71 | 0.85 | 0.85 | |

${M}_{3}$ | ||||||

$per{c}_{N}$ | 26.54 | 16.38 | 3.24 | 0.56 | 0.01 | |

${M}_{4}$ | ||||||

$per{c}_{N}$ | 29.27 | 18.65 | 2.87 | 0.38 | ≈ 0 | |

${M}_{5}$ | ||||||

$per{c}_{N}$ | 10.41 | 6.56 | 4.04 | 2.03 | 0.06 | |

${M}_{6}$ | ||||||

$per{c}_{N}$ | 67.14 | 37.25 | 14.10 | 5.09 | 0.09 |

Model | Chart | Regression |
---|---|---|

${M}_{1}$ | $-2.06\xb7\mathrm{ln}\left(x\right)+4.10$ | |

${M}_{2}$ | $-4.87\xb7\mathrm{ln}\left(x\right)+8.39$ | |

${M}_{3}$ | $-1.50\xb7\mathrm{ln}\left(x\right)+5.57$ | |

${M}_{4}$ | $-1.28\xb7\mathrm{ln}\left(x\right)+5.21$ | |

${M}_{5}$ | $-2.43\xb7\mathrm{ln}\left(x\right)+7.01$ | |

${M}_{6}$ | $-1.92\xb7\mathrm{ln}\left(x\right)+9.07$ |

**Table A3.**Comparison of B-spline curve approximation of testing clouds, CP is number of control points, ${w}_{\phi}$ is average weighted error.

${C}_{1}$ | |||||

CP | 4 | 10 | 20 | ||

${w}_{\phi}$[mm] | 2.35 | 1.15 | 0.83 | ||

${C}_{2}$ | |||||

CP | 4 | 10 | 20 | 40 | 80 |

${w}_{\phi}$[mm] | 14.01 | 5.54 | 2.02 | 1.25 | 0.99 |

${C}_{3}$ | |||||

CP | 20 | 40 | 80 | ||

${w}_{\phi}$[mm] | 3.96 | 0.96 | 0.85 | ||

${C}_{4}$ | |||||

CP | 80 | 100 | 160 | ||

${w}_{\phi}$[mm] | 0.41 | 0.37 | 0.27 | ||

${C}_{5}$ | |||||

CP | 10 | 40 | 80 | ||

${w}_{\phi}$[mm] | 2.19 | 0.67 | 0.33 |

## References

- Davis, J.; Edgar, T.; Porter, J.; Bernaden, J.; Sarli, M. Smart manufacturing, manufacturing intelligence and demand-dynamic performance. Comput. Chem. Eng.
**2012**, 47, 145–156. [Google Scholar] [CrossRef] - Vaidya, S.; Ambad, P.; Bhosle, S. Industry 4.0—A Glimpse. Procedia Manuf.
**2018**, 20, 233–238. [Google Scholar] [CrossRef] - Chua, C.K.; Leong, K.F.; Lim, C.S. Rapid Prototyping: Principles and Applications. In Rapid Prototyping: Principles and Applicationse; World Scientific Publishing: Singapore, 2010. [Google Scholar]
- Qiu, Y.; Zhou, X.; Qian, X. Direct slicing of cloud data with guaranteed topology for rapid prototyping. Int. J. Adv. Manuf. Technol.
**2011**, 53, 255–265. [Google Scholar] [CrossRef] - Livesu, M.; Ellero, S.; Martinez, J.; Lefebvre, S.; Attene, M. From 3D models to 3D prints: An overview of the processing pipeline. Comput. Graph. Forum
**2017**, 36, 1–24. [Google Scholar] [CrossRef] [Green Version] - Choi, S.-H.; Samavedam, S. Modelling and optimisation of rapid prototyping. Comput. Ind.
**2002**, 47, 39–53. [Google Scholar] [CrossRef] - Sen, S.K.; Agarwal, R.P. Golden ratio in science, as random sequence source, its computation and beyond. J. Comput. Math. Appl.
**2008**, 56, 469–498. [Google Scholar] [CrossRef] [Green Version] - Javidrad, R.; Pourmoayed, A.R. Contour curve reconstruction from cloud data for rapid prototyping. Robot. Comput. Integr. Manuf.
**2011**, 27, 397–404. [Google Scholar] [CrossRef] - Grilli, E.; Menna, F.; Remondino, F. A review of point clouds segmentation and classification algorithms. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci.
**2017**, XLII-2/W3, 339–344. [Google Scholar] [CrossRef] [Green Version] - Nguyen, A.; Le, B. 3D point cloud segmentation: A survey. In Proceedings of the 6th IEEE Conference on Robotics, Automation and Mechatronics (RAM), Manila, Philippine, 12–15 November 2013; pp. 225–230. [Google Scholar]
- Besl, P.J.; Jain, R.C. Segmentation through Variable-Order Surface Fitting. IEEE Trans. Pattern Anal. Mach. Intell. Arch.
**1988**, 10, 167–192. [Google Scholar] [CrossRef] [Green Version] - Nahar, M.; Ali Sujan Rahman, M. Improvement of Single Seeded Region Growing Algorithm on Image Segmentation. Glob. J. Comput. Sci. Technol.
**2018**, 18, 15–22. [Google Scholar] - Adams, R.; Bischof, L. Seeded Region Growing. IEEE Trans. Pattern Anal. Mach. Intell. Arch.
**1994**, 6, 641–647. [Google Scholar] [CrossRef] [Green Version] - Wang, X.; Zoua, L.; Shena, X.; Rena, Y.; Qina, Y. A region-growing approach for automatic outcrop fracture extraction from a three-dimensional point cloud. Comput. Geosci.
**2017**, 99, 100–106. [Google Scholar] [CrossRef] [Green Version] - Xu, J.; Zhou, M.; Wu, Z.; Shui, W.; Ali, S. Robust surface segmentation and edge feature lines extraction from fractured fragments of relics. J. Comput. Des. Eng.
**2015**, 2, 79–87. [Google Scholar] [CrossRef] [Green Version] - Vo, A.V.; Truong-Hong, L.; Laefer, D.F.; Bertolotto, M. Octree-based region growing for point cloud segmentation. ISPRS J. Photogramm. Remote Sens.
**2015**, 104, 88–100. [Google Scholar] [CrossRef] - Ni, H.; Lin, X.; Ning, X.; Zhang, J. Edge Detection and Feature Line Tracing in 3D-Point Clouds by Analyzing Geometric Properties. Remote Sens.
**2016**, 8, 710. [Google Scholar] [CrossRef] [Green Version] - Demaris, K.; Vanderstraeten, D.; Volodine, T.; Roose, D. Detection of closed sharp edges in point clouds using normal estimation and graph theory. Comput. Aided Des.
**2007**, 39, 267–283. [Google Scholar] - Jiang, X.Y.; Bunke, H.; Meier, U. Fast range image segmentation using high-level segmentation primitives. In Proceedings of the Third IEEE Workshop on Applications of Computer Vision, Sarasota, FL, USA, 2–4 December 1996; pp. 83–88. [Google Scholar]
- Schnabel, R.; Wahl, R.; Klein, R. Efficent Ransac for point cloud shape detection. Comput. Graph. Forum
**2007**, 26, 214–226. [Google Scholar] [CrossRef] - Berger, M.; Tagliasacchi, A.; Seversky, L.M.; Alliez, P.; Guennebaud, G.; Levine, J.A.; Silva, C.T. A Survey of Surface Reconstruction from Point Clouds. Comput. Graph Forum
**2016**, 36, 301–329. [Google Scholar] [CrossRef] [Green Version] - Lafarge, F.; Alliez, P. Surface reconstruction through point set structuring. In Computer Graphics Forum; Benes, B., Chen, M., Eds.; Wiley: New York, NY, USA, 2013; pp. 225–234. [Google Scholar]
- Wang, M.; Ju, M.; Fan, Y.; Guo, S.; Liao, M.; Yang, H.; Komura, T. 3D Incomplete Point Cloud Surfaces Reconstruction With Segmentation and Feature-Enhancement. IEEE Access
**2019**, 7, 15272–15281. [Google Scholar] [CrossRef] - Yin, K.; Huang, H.; Zhang, H.; Gong, M.; Cohen-Or, D.; Chen, B. Morfit: Interactive surface reconstruction from incomplete point clouds with curve-driven topology and geometry control. ACM Trans. Graph.
**2014**, 33, 202. [Google Scholar] [CrossRef] - Hildebrandt, K.; Polthier, K.; Wardetzky, M. Smooth features lines on surface meshes. In Eurographics Symposium on Geometry Processing; Desbrun, M., Pottmann, H., Eds.; Eurographics Association: Aire-la-Ville, Switzerland, 2005; pp. 85–90. [Google Scholar]
- Ohtake, Y.; Belyaev, A. Automatic detection of geodesic ridges and ravines on polygonal surface. J. Three Dimens. Images
**2001**, 15, 127–132. [Google Scholar] - Stylianou, G.; Farin, G. Crest lines extraction from 3D triangulated meshes. In Hierarchical and Geometrical Methods in Scientific Visualization; Farin, G., Hamann, B., Hagen, H., Eds.; Springer: Berlin, Germany, 2003; pp. 69–81. [Google Scholar]
- Tootooni, S.; Dsouza, A.; Donovan, R.; Rao, P.K.; Kong, Z.; Borgesen, P. Classifying the Dimensional Variation in Additive Manufactured Parts From Laser-Scanned Three-Dimensional Point Cloud Data Using Machine Learning Approaches. J. Manuf. Sci. Eng.
**2017**, 139, 142–149. [Google Scholar] - Beniere, R.; Subsol, G.; Gesquire, G.; Le Breton, F.; Puech, W. A comprehensive process of reverse engineering from 3D meshes to CAD models. Comput. Aided Des.
**2013**, 45, 1382–1393. [Google Scholar] [CrossRef] [Green Version] - Zhang, Z.; Sanjay, J. An improved slicing algorithm with efficient contour construction using STL files. Int. J. Adv. Manuf. Technol.
**2015**, 80, 1347–1362. [Google Scholar] [CrossRef] - Ma, W.; But, W.C.; He, P. NURBS-based adaptive slicing for efficient rapid prototyping. Comput. Aided Des.
**2004**, 36, 1309–1325. [Google Scholar] [CrossRef] - Oropallo, W.; Piegl Les, A.; Rosen, P.; Rajab, K. Generating point clouds for slicing free-form objects for 3-D printing. Comput. Aided Des. Appl.
**2017**, 14, 242–249. [Google Scholar] [CrossRef] - Shi, K.; Cai, C.; Wu, Z.; Yong, J. Slicing and support structure generation for 3D printing directly on B-rep models. Vis. Comput. Ind. Biomed. Art
**2019**, 2, 3. [Google Scholar] [CrossRef] - Zhao, G.; Ma, G.; Feng, J.; Xiao, W. Nonplanar slicing and path generation methods for robotic additive manufacturing. Int. J. Adv. Manuf. Technol.
**2018**, 96, 3149. [Google Scholar] [CrossRef] - Kresslein, J.; Haghighi, P.; Jaejong, P.; Ramnath, S.; Sutradhar, A.; Shah, J.J. Automated cross-sectional shape recovery of 3D branching structures from point cloud. J. Comput. Des. Eng.
**2018**, 5, 368–378. [Google Scholar] [CrossRef] - Liu, W.; Sun, J.; Li, W.; Hu, T.; Wang, P. Deep Learning on Point Clouds and Its Application: A Survey. Sensors
**2019**, 19, 4188. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Griffiths, D.; Boehm, J. A Review on Deep Learning Techniques for 3D Sensed Data Classification. Remote Sens.
**2019**, 11, 1499. [Google Scholar] [CrossRef] [Green Version] - Guo, Y.; Wang, H.; Hu, Q.; Liu, H.; Liu, L.; Bennamoun, M. Deep Learning for 3D Point Clouds: A Survey. arXiv
**2019**, arXiv:abs/1912.12033. [Google Scholar] [CrossRef] - Lee, D.; Quan, I.; Wu, C.; Wu, J.; Tamir, D.; Rishe, N. Optimizing B-Spline Surface Reconstruction for Sharp Feature Preservation. In Proceedings of the 10th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, 6–8 January 2020; pp. 359–364. [Google Scholar]
- Mineo, C.; Pierce, S.G.; Summan, R. Novel algorithms for 3D surface point cloud boundary detection and edge reconstruction. J. Comput. Des. Eng.
**2019**, 6, 81–91. [Google Scholar] [CrossRef] - Markovic, V.; Jakovijevic, Z.; Miljkovic, Z. Feature sensitive three-dimensional point cloud simplification using support vector regression. Tech. Gaz.
**2019**, 27, 985–994. [Google Scholar] - Bazazian, D.; Casas, J.R.; Ruiz-Hidalgo, J. Fast and Robust Edge Extraction in Unorganized Point Clouds. In Proceedings of the International Conference on Digital Image Computing: Techniques and Applications (DICTA), Adelaide, Australia, 23–25 November 2015; pp. 1–8. [Google Scholar]
- Wang, Y.X.; Wang, J.; Chen, X.; Chu, T.; Liu, M.; Yang, T. Feature Surface Extraction and Reconstruction from Industrial Components Using Multistep Segmentation and Optimization. Remote Sens.
**2018**, 10, 1073. [Google Scholar] [CrossRef] [Green Version] - Mörwald, T.; Balzer, J.; Vincze, V. Modeling connected regions in arbitrary planar point clouds by robust B-spline approximation. Robot. Auton. Syst.
**2008**, 76, 141–151. [Google Scholar] [CrossRef] - Jolliffe, I.T. Principal Component Analysis; Springer: New York, NY, USA, 1986; p. 487. [Google Scholar]
- Banchoff, T.; Gaffney, T.; McCrory, C. Cups of the Gauss Map. In Research Notes in Mathematics; Pitman: London, UK, 1982. [Google Scholar]
- Weber, C.; Hahmann, S.; Hagen, H. Methods for feature detection in point cloud. In Visualization of Large and Unstructured Data Sets–IRTG Workshop; Middel, A., Scheler, I., Hagen, H., Eds.; Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik: Bodega Bay, CA, USA, 2010; pp. 90–99. [Google Scholar]
- Piegl, L.; Tiller, W. The NURBS Book; Springer: New York, NY, USA, 1997. [Google Scholar]
- de Boor, C. A Practical Guide to Splines; Springer: New York, NY, USA, 2001. [Google Scholar]
- Blake, A.; Isard, M. The Active Contours; Springer: New York, NY, USA, 1998. [Google Scholar]
- Wang, W.; Pottmann, H.; Liu, Y. Fitting B-spline curves to point clouds by curvature-based squared distance minimization. ACM Trans. Graph.
**2006**, 25, 214–238. [Google Scholar] [CrossRef]

**Figure 5.**Testing point clouds: (

**a**) ${M}_{\mathrm{ffl}}$, (

**b**) ${M}_{2}$, (

**c**) ${M}_{3}$, (

**d**) ${M}_{4}$, (

**e**) ${M}_{5}$, (

**f**) ${M}_{6}$.

**Figure 7.**(

**a**) Normal vector is on the opposite side of the point ${Q}_{k}$, distance ${d}_{k}$ is negative, (

**b**) the graphs of the functions ${w}_{\phi}$ (red line) and ${f}_{\phi}$ (blue line).

**Figure 9.**Set of testing point clouds: (

**a**) ${C}_{1}$, (

**b**) ${C}_{2}$, (

**c**) ${C}_{3}$, (

**d**) ${C}_{4}$, (

**e**) ${C}_{5}$.

**Figure 10.**(

**a**) The initial B-spline curve of the cloud points (black crosses) and new control points (red crosses), (

**b**) the distance of the point cloud points and the computed curve line.

Model | ${\mathit{M}}_{1}$ | ${\mathit{M}}_{2}$ | ${\mathit{M}}_{3}$ | ${\mathit{M}}_{4}$ | ${\mathit{M}}_{5}$ | ${\mathit{M}}_{6}$ |
---|---|---|---|---|---|---|

${s}_{in}$ | 87,848 | 67,394 | 195,815 | 123,112 | 103,534 | 90,209 |

Input | Output | Input | Output | ||
---|---|---|---|---|---|

${M}_{1}$ | ${M}_{2}$ | ||||

${M}_{3}$ | ${M}_{4}$ | ||||

${M}_{5}$ | ${M}_{6}$ |

(a) | (b) | (c) | (d) |
---|---|---|---|

$th{r}_{{\theta}_{N}}=4$ | $th{r}_{{\theta}_{N}}=1.2$ | $th{r}_{{\theta}_{N}}=1$ | $th{r}_{{\theta}_{N}}=1.5$ |

Model Curve | ${\mathit{C}}_{1}$ | ${\mathit{C}}_{2}$ | ${\mathit{C}}_{3}$ | ${\mathit{C}}_{4}$ | ${\mathit{C}}_{5}$ |
---|---|---|---|---|---|

${s}_{in}$ | 1632 | 1307 | 2560 | 2477 | 3130 |

**Table 5.**Computation of approximation error ${E}_{m}$ and ${E}_{gold}$ using different values of $\sigma $.

$\mathit{\sigma}$ | 0.02 | 0.09 | 0.1 |
---|---|---|---|

${E}_{m}$ | 0.9387 | 0.9661 | 0.9702 |

${E}_{gold}$ | 0.9382 | 0.9560 | 0.9604 |

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Prochazkova, J.; Procházka, D.; Landa, J.
Sharp Feature Detection as a Useful Tool in Smart Manufacturing. *ISPRS Int. J. Geo-Inf.* **2020**, *9*, 422.
https://doi.org/10.3390/ijgi9070422

**AMA Style**

Prochazkova J, Procházka D, Landa J.
Sharp Feature Detection as a Useful Tool in Smart Manufacturing. *ISPRS International Journal of Geo-Information*. 2020; 9(7):422.
https://doi.org/10.3390/ijgi9070422

**Chicago/Turabian Style**

Prochazkova, Jana, David Procházka, and Jaromír Landa.
2020. "Sharp Feature Detection as a Useful Tool in Smart Manufacturing" *ISPRS International Journal of Geo-Information* 9, no. 7: 422.
https://doi.org/10.3390/ijgi9070422