|
|
基于图像识别的SolidWorks三维重建技术研究
|
Abstract:
本研究聚焦于基于图像识别的三维重建技术，强调高层理解的扫描图纸作为重要前提，并在机械知识的引导下实现三维模型的重建。图像识别分为基本图素识别和字符识别两个部分，其中基本图素识别采用改进的Hough变换法，字符识别采用基于卷积神经网络的方法，以适应实际图样的特殊情景。实验结果表明，该模型具有显著的识别效果，能够有效兼容干扰图线，识别率高达98.65%。随后，通过工程图的语义知识，建立基本图素之间的拓扑关系和尺寸约束图形链，实现对扫描图纸的二维重建。最终，在机械领域知识的支持下，充分利用图纸识别后的信息和知识推理，实现三维形体的重建。
This study focuses on 3D reconstruction techniques based on image recognition, with an emphasis on the high-level understanding of scanned drawings as a crucial prerequisite. The aim is to realize the reconstruction of 3D models under the guidance of mechanical knowledge. The image recognition process is divided into two parts: basic pixel recognition and character recognition. The improved Hough transform method is adopted for basic pixel recognition, while character recognition utilizes a method based on convolutional neural networks to adapt to the specific characteristics of actual drawings. Experimental results demonstrate that the model has a significant recognition effect, effectively handling interference lines with a high recognition rate of 98.65%. Furthermore, by leveraging semantic knowledge from engineering drawings, the topological relationship between basic graphic elements and size constraint graph chains is established to achieve two-dimensional reconstruction of scanned drawings. Finally, with support from mechanical domain knowledge, 3D shape reconstruction is realized through comprehensive information utilization and knowledge reasoning following drawing recognition.
| [1] | Kapitanov, A., Kozlova, A. and Tyasto, S. (2018) The Information Model of the Modern Digital Production. MATEC Web of Conferences, 224, Article 02065. https://doi.org/10.1051/matecconf/201822402065 |
| [2] | 杨建鸣, 陆家山, 严鹏贺. 工程图的三维重建方法研究[J]. 机械设计与制造, 2017(12): 216-219. |
| [3] | Idesawa, M. (1973) A System to Generate a Solid Figure from Three View. Bulletin of JSME, 16, 216-225. https://doi.org/10.1299/jsme1958.16.216 |
| [4] | Wesley, M.A. and Markowsky, G. (1981) Fleshing Out Projections. IBM Journal of Research and Development, 25, 934-954. https://doi.org/10.1147/rd.256.0934 |
| [5] | 刘世霞, 胡事民, 汪国平, 孙家广. 基于三视图的三维形体重建技术[J]. 计算机学报, 2000, 23(2): 141-146. |
| [6] | 龚洁晖, 张慧. 基于工程图的三维重建研究[J]. 软件学报, 2008, 19(7): 1794-1805. |
| [7] | Alexei, Z. and Arkady, Z. (2014) Three-Dimensional Reconstruction from Projections Based on Incidence Matrices of Patterns. AASRI Procedia, 9, 72-77. https://doi.org/10.1016/j.aasri.2014.09.013 |
| [8] | Aldefeld, B. (1983) On Automatic Recognition of 3D Structures from 2D Representations. Computer-Aided Design, 15, 59-64. https://doi.org/10.1016/0010-4485(83)90169-0 |
| [9] | 张雪, 赵德胜, 李丽萍. 基于CSG方法的工程图三维形体重建[J]. 西安邮电大学学报, 2015, 20(4): 80-83, 124. |
| [10] | Chen, Z. and Perng, D. (1988) Automatic Reconstruction of 3D Solid Objects from 2D Orthographic Views. Pattern Recognition, 21, 439-449. https://doi.org/10.1016/0031-3203(88)90003-9 |
| [11] | Lin, W. and Fang, C. (2007) Synthesized Affine Invariant Function for 2D Shape Recognition. Pattern Recognition, 40, 1921-1928. https://doi.org/10.1016/j.patcog.2006.03.021 |
| [12] | Chen, G., Zhang, D., Li, P., Chen, C., Wang, Y. and Su, S. (2019) Research on the Knowledge Representation and Retrieval for Mechanical Product Design Based on Ontology. International Journal of Wireless and Mobile Computing, 16, 340. https://doi.org/10.1504/ijwmc.2019.10021628 |
| [13] | 杨海成, 主编. 数字化设计制造技术基础[M]. 西安: 西北工业大学出版社, 2009. |
| [14] | Suresh, K. and Srinivasa rao, P. (2018) Various Image Segmentation Algorithms: A Survey. In: Satapathy, S., Bhateja, V. and Das, S., Eds., Smart Intelligent Computing and Applications, Springer, 233-239. https://doi.org/10.1007/978-981-13-1927-3_24 |
| [15] | Karthikeyan, V. (2013) Hilditchs Algorithm Based Tamil Character Recognition. International Journal of Computer Science & Engineering Technology, 4, 268-273. |
| [16] | Liu, Z., Liang, J. and Pan, Y. (2014) Construction of Thermodynamic Properties Look-Up Table with Block-Structured Adaptive Mesh Refinement Method. Journal of Thermophysics and Heat Transfer, 28, 50-58. https://doi.org/10.2514/1.t4273 |
| [17] | Oh, J.S. (2018) Straight Line Detection Using PCA and Hough Transform. Journal of the Korea Institute of Information and Communication Engineering, 22, 227-232. |
| [18] | Jiang, G., Wang, X., Wang, Z. and Liu, H. (2016) Wheat Rows Detection at the Early Growth Stage Based on Hough Transform and Vanishing Point. Computers and Electronics in Agriculture, 123, 211-223. https://doi.org/10.1016/j.compag.2016.02.002 |
| [19] | Djekoune, A.O., Messaoudi, K. and Amara, K. (2017) Incremental Circle Hough Transform: An Improved Method for Circle Detection. Optik, 133, 17-31. https://doi.org/10.1016/j.ijleo.2016.12.064 |
| [20] | Sagar, S. and Dixit, S. (2019) A Comprehensive Study on Character Segmentation. In: Pandian, D., Fernando, X., Baig, Z. and Shi, F., Eds., Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering 2018 (ISMAC-CVB), Springer International Publishing, 1509-1515. https://doi.org/10.1007/978-3-030-00665-5_141 |
| [21] | Li, P., Peng, L. and Wen, J. (2016) Rejecting Character Recognition Errors Using CNN Based Confidence Estimation. Chinese Journal of Electronics, 25, 520-526. https://doi.org/10.1049/cje.2016.05.018 |
| [22] | Ghiasi-Shirazi, K. (2019) Generalizing the Convolution Operator in Convolutional Neural Networks. Neural Processing Letters, 50, 2627-2646. https://doi.org/10.1007/s11063-019-10043-7 |
| [23] | Jiang, Z., Yin, F., Ge, Y. and Ren, L. (2020) A Multi-Scale Framework with Unsupervised Joint Training of Convolutional Neural Networks for Pulmonary Deformable Image Registration. Physics in Medicine & Biology, 65, Article 015011. https://doi.org/10.1088/1361-6560/ab5da0 |
| [24] | 畅通, 包宏. 基于图形语义理解的三维重建技术[J]. 计算机工程与设计, 2005(9):2274-2276. |
