Abstract
A CAD drawing has various drawing features like entity lines, dimensional lines, dimensional arrows, dimensional text, support lines, reference lines, Circles, GD&T symbols and drawing information metadata. The problem of automated or semi-automated recognition of feature entities from 2D CAD drawings in the form of raster images has multiple usages in various scenarios. The present research work explores the ways to extract this information about the entities from 2D CAD drawings raster images and to set up a workflow to do it in automated or semi-automated way. The algorithms and workflow have been tested and refined using a set of test CAD images which are fairly representative of the CAD drawings encountered in practice. The overall success rate of the proposed process is 90% in fully automated mode for the given sample of the test images. The proposed algorithms presented here are evaluated based on F1 scores. The proposed algorithm is used to generate user editable DXF CAD file from raster images of CAD drawings which could be then used to update/edit the CAD model when required using CAD packages. The research work also provides use cases of this workflow for other applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
AutoCAD (2012) DXF Reference autocad 2012. https://images.autodesk.com/adsk/files/autocad_2012_pdf_dxf-reference_enu.pdf
Ballard, D.H.: Generalizing the hough transform to detect arbitrary shapes. Pattern Recognit. 13(2), 111–122 (1981)
Bessmeltsev, M., Solomon, J.: Vectorization of line drawings via polyvector fields. ACM Trans. Graphics (TOG) 38(1), 9 (2019)
Chen, J., Du, M., Qin, X., Miao, Y.: An improved topology extraction approach for vectorization of sketchy line drawings. Vis. Comput. 34(12), 1633–1644 (2018). https://doi.org/10.1007/s00371-018-1549-z
Chhabra, A.K., Phillips, I.T.: Performance evaluation of line drawing recognition systems. In: 2000 15th International Conference on Pattern Recognition, Proceedings, vol. 4, pp. 864–869. IEEE (2000)
Donati, L., Cesano, S., Prati, A.: A complete hand-drawn sketch vectorization framework. Multimedia Tools Appl. 78(14), 19083–19113 (2019)
Goutsias, J., Heijmans, H.J., Sivakumar, K.: Morphological operators for image sequences. Comput. Vis. Image Underst. 62(3), 326–346 (1995)
Intwala, A.M., Magikar, A.: A review on process of 3D model reconstruction. In: International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT), pp 2851–2855. IEEE (2016)
Intwala, A.M., Kharade, K., Chaugule, R., Magikar, A.: Dimensional arrow detection from CAD drawings. Indian J. Sci. Technol. 9(21), 1–7 (2016)
Narayan, K., Kannaiah, P., Venkata Reddy, K.: Machine Drawing. New Age International Publishers, New Delhi (2006)
Shen, Z., Shah, J.J., Davidson, J.K.: Analysis neutral data structure for GD&T. J. Intell. Manuf. 19(4), 455–472 (2008)
Suzuki, K.: Pixel-based artificial neural networks in computer-aided diagnosis. In: Artificial Neural Networks-Methodological Advances and Biomedical Applications, pp 71–92. InTech (2011)
Trajković, M., Hedley, M.: Fast corner detection. Image Vis. Comput. 16(2), 75–87 (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Intwala, A. (2020). Image to CAD: Feature Extraction and Translation of Raster Image of CAD Drawing to DXF CAD Format. In: Nain, N., Vipparthi, S., Raman, B. (eds) Computer Vision and Image Processing. CVIP 2019. Communications in Computer and Information Science, vol 1147. Springer, Singapore. https://doi.org/10.1007/978-981-15-4015-8_18
Download citation
DOI: https://doi.org/10.1007/978-981-15-4015-8_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-4014-1
Online ISBN: 978-981-15-4015-8
eBook Packages: Computer ScienceComputer Science (R0)