|
Holo-extraction of information from paper drawings for 3D reconstructionComputer-Aided Design Volume 34, Issue 9, August 2002, Pages 665-677注意：本文已经在英文CAD杂志发表，使用者请注明出处！(SCI已经收录本文)Ke-Zhang Chen,(a), Xi-Wen Zhang(b), Zong-Ying Ou(c) and Xin-An Feng(c) a Department of Mechanical Engineering, The University of Hong Kong, Pokfulam Road, Hong Kongb State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210093, Chinac Faculty of Mechanical Engineering, Dalian University of Technology, Dalian, 116024, China AbstractThe research on the conversion from 2D paper drawings to 3D computer feature models has been stuck in low-level coding. One of the reasons for it is that the three phases of understanding process has been isolated and people have been doing their research on only one of the phases since the whole conversion is very complicated and more difficult. For instance, the vectorization methods for the first phase were developed only for getting straight lines, arcs, circles, etc. so that much information contained in the drawing has been lost after the vectorization. This paper develops a holo-extraction method of information from paper drawings, the networks of single closed regions (SCRs), which can not only provide a unified base for recognizing both the annotations and the outlines of projections of parts, but also build the holo-relationships among SCRs so that it is convenient to extract lexical, syntactic and semantic information in the subsequent phases for 3D reconstruction. Keywords: Engineering drawing understanding; 3D reconstruction; Vectorization; Networks of single closed regions 1、浏览全文需要使用软件－－Abode Acrobat(由于软件较大并常见,我站不提供下载)2、下载全文请点击(445KB)Article Outline1. Introduction2. Review of current vectorization methods2.1. Hough Transform based method [2]2.2. Thinning based method [4, 5, 6 and 7]2.3. Contour based method [8, 9 and 10]2.4. Sparse pixel based method [11]2.5. Mesh pattern based methods [12]2.6. Black pixel region based method [13, 14 and 15]3. Construction of the networks of SCRs3.1. Generating adjacency graphs of runs3.2. Constructing single closed regions (SCRs)3.3. Building adjacency graphs of SCRs3.4. Constructing the networks of SCRs4. A bridge from raster image to understanding and 3D reconstruction4.1. Separation between the annotations and the outlines of projections of parts4.2. Vectorization4.2.1. Recognition of horizontal thick lines and arrowheads4.2.2. Recognition of complete arcs and circles4.2.3. Recognition of complete straight lines4.2.4. Software prototype4.3. 3D reconstruction5. ConclusionsAcknowledgementsReferencesVitaeReferences1. D. Dori and K. Tombre , From engineering drawings to 3D CAD models: are we ready now?. Computer-Aided Design 27 4 (1995), pp. 243ˉ254. Abstract | PDF (1237 K) 2. Hough PVC. A method and means for recognizing complex patterns. USA Patent 3,096,654, 1962.3. W. Liu and D. Dori , From raster to vectors: extracting visual information from line drawings. Pattern Analysis and Applications 2 2 (1999), pp. 10ˉ21.4. L. Lam, S.W. Lee and C.Y. Suen , Thinning methodologiesˉˉA comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 14 9 (1992), pp. 869ˉ887.5. N.J. Naccache and R. Shinghal , SPTA: a proposed algorithm for thinning binary patterns. IEEE Transactions on System, Man, and Cybernetics 14 (1984), pp. 409ˉ418. Abstract-INSPEC | Abstract-PsycINFO 6. S. Peleg and A. Rosenfeld , A min-max medial axis transformation. IEEE Transactions on Pattern Analysis and Machine Intelligence 3 (1981), pp. 208ˉ210. Abstract-Compendex | Abstract-INSPEC 7. E.R. Davies and A.P.N. Plummer , Thinning algorithms: a critique and a new methodology. Pattern Recognition 14 (1981), pp. 53ˉ53.8. C.C. Han and K.C. Fan , Skeleton generation of engineering drawings via contour matching. Pattern Recognition 27 2 (1994), pp. 261ˉ275. Abstract-INSPEC | Abstract-Compendex 9. J. Jimenez and J.L. Navalon , Some experiments in image vectorization. IBM Journal of research and Development 26 (1982), pp. 724ˉ734. Abstract-Compendex | Abstract-INSPEC 10. B. Shapiro, J. Pisa and J. Sklansky , Skeleton generation from x-y boundary sequences. Computer Graphics and Image Processing 15 (1981), pp. 136ˉ153. Abstract-Compendex | Abstract-GEOBASE | Abstract-INSPEC 11. Liu W, Dori D. Sparse pixel tracking: a first vectorization algorithm applied to engineering drawings. Proceedings of the 13th International Conference on Pattern Recognition, Vienna, Austria, 1996. Vol. III (Robotics and Applications), p. 808ˉ11.12. X. Lin, S. Shimotsuji, M. Minoh and T. Sakai , Efficient diagram understanding with characteristic pattern detection. Computer Vision, Graphics and Images Processing 30 (1985), pp. 84ˉ106. Abstract-Compendex | Abstract-GEOBASE | Abstract-INSPEC 13. Monagan G, Roosli M. Appropriate base representation using a run graph. Proceedings of the Second International Conference on Document Analysis and Recognition, Tsukuba, Japan, 1993. p. 623ˉ6.14. H. Bley , Segmentation and preprocessing of electrical schematics using picture graphs. Computer Vision, Graphics, and Image Processing 28 (1984), pp. 271ˉ288. Abstract-GEOBASE | Abstract-INSPEC | Abstract-Compendex 15. S.D. Zenzo, L. Cinque and S. Levialdi , Run-based algorithms for binary image analysis and processing. IEEE Transaction on Pattern Analysis and Machine Intelligence 18 1 (1996), pp. 83ˉ89.16. L.H. Tsoukalas and R.E. Uhrig Fuzzy and neural approaches in engineering, John Wiley & Sons Inc (1997).17. M. Gen and R. Cheng Genetic Algorithms and Engineering Design, John Wiley & Sons Inc, New York (1997).18. M.A. Wesley and G. Markowsky , Fleshing out projections. IBM Journal of Research and Development 25 6 (1981), pp. 934ˉ954. Abstract-Compendex | Abstract-INSPEC 19. K. Preiss , Constructing the solid representation from engineering projections. Computers and Graphics 8 4 (1984), pp. 381ˉ389. Abstract-INSPEC 20. H. Yoshiura, K. Fujimura and L. Kumii , Top-down construction of 3-D mechanical object shapes from engineering drawings. IEEE COMPUTER Magazine 17 12 (1984), pp. 32ˉ40. Abstract-Compendex | Abstract-INSPEC 21. Ah-Soon C., Tombre K. A step towards reconstruction of 3-D CAD models from engineering drawings. Proceedings of the Third International Conference on Document Analysis and Recognition, Montreal, Canada, 1995. p. 331ˉ4.22. C.M. Hoffmann and J.E.H. Hopcroft , Geometric ambiguities in boundary representations. Computer-Aided Design 19 3 (1987), pp. 141ˉ147. Abstract-INSPEC | Abstract-Compendex 23. Z. Chen and D.B. Perng , Automatic reconstruction of 3D solid objects from 2D orthographic views. Pattern Recognition 21 5 (1988), pp. 439ˉ449. Abstract-GEOBASE 24. S.S.P. Shum, W.S. Lau, M.M.F. Yuen and K.M. Yu , Solid reconstruction from orthographic views using 2-stage extrusion. Computer-Aided Design. 33 (2001), pp. 91ˉ102. SummaryPlus | Full Text + Links | PDF (314 K) Ke-Zhang Chen received his PhD degree from the University of Manchester (UMIST), UK in 1984. After he had worked at the University of Manchester (UMIST) (UK), East China University (China), MIT (USA), and the University of California at Davis (USA), he joined the Department of Mechanical Engineering in the University of Hong Kong in 1996. His current research interests include design theory and methodology, concurrent engineering, intelligent CAD, and design for heterogeneous components.Zhang:Xi-Wen Zhang received his BS degree from the Department of Chemical Engineering, Fushun Institute of Petrol, China, in 1995, and PhD degree from the Department of Mechanical Engineering, Dalian University of Technology, China, in 2000. He is now a Postdoctor at State Key Laboratory of Novel Software Technology, the Department of Computer Science and Technology, Nanjing University, China. His research interests include computer vision, artificial intelligence, and understanding of scanned engineering drawings.Ou:Zong-ying Ou received his BS degree from the Department of Mechanical Engineering, Dalian University of Technology, China, in 1956. He has then been working in the university, and is now a Professor, Head of Mechanical Design Division and Director of CAD/CG lab in the Faculty. From 1981 to 1983, he worked as a visiting scholar in University of Wisconsin-Madison, USA. His research interests include intelligent CAD/CAM, solid modeling, geometric reasoning, image processing and understanding, computer vision and 3D reconstruction.Feng:Xin-An Feng received his BS degree from the Department of Mechanical Engineering, Dalian University of Technology, China, in 1956. He has then been working in the university, and is now a Professor, Deputy director of CIMS research center, standing council member of China Association for Mechatronics Technology and Applications, and council member of China Institution for Production Engineering. From 1980 to 1982, he worked as a visiting scholar in the University of Manchester (UMIST), UK. His current research interests include CAD/CAM, intelligent CAD, concurrent engineering, and CIMS.
|
