Holo-extraction of information from paper drawings for 3D reconstruction

Computer-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 Kong
b State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210093, China
c Faculty of Mechanical Engineering, Dalian University of Technology, Dalian, 116024, China 

Abstract
The 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 Outline
1. Introduction
2. Review of current vectorization methods
2.1. 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 SCRs
3.1. Generating adjacency graphs of runs
3.2. Constructing single closed regions (SCRs)
3.3. Building adjacency graphs of SCRs
3.4. Constructing the networks of SCRs
4. A bridge from raster image to understanding and 3D reconstruction
4.1. Separation between the annotations and the outlines of projections of parts
4.2. Vectorization
4.2.1. Recognition of horizontal thick lines and arrowheads
4.2.2. Recognition of complete arcs and circles
4.2.3. Recognition of complete straight lines
4.2.4. Software prototype
4.3. 3D reconstruction
5. Conclusions
Acknowledgements
References
Vitae

References
1. 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 , Som

[1] [2] 下一页