ASKME: adaptive sampling with knowledge-driven vectorization of mechanical engineering drawings

详细信息    查看全文

• 作者：Paramita De ; Sekhar Mandal ; Partha Bhowmick…
• 关键词：Vectorization ; Raster ; to ; vector conversion ; Document image analysis ; Engineering drawings ; Graphics recognition ; Graphics classification ; Digital geometry
• 刊名：International Journal on Document Analysis and Recognition
• 出版年：2016
• 出版时间：March 2016
• 年：2016
• 卷：19
• 期：1
• 页码：11-29
• 全文大小：2,496 KB
• 参考文献：1.3rd/5th IAPR international workshop on Graphics RECognition (Arc Contest). http://​www.​cs.​cityu.​edu.​hk/​~liuwy/​ArcContest (2003/2005)
  2.7th IAPR international workshop on Graphics RECognition (Arc Segmentation Contest). http://​www.​iapr.​org/​arcseg2007 (2007) (The dataset was available in the website till 2007)
  3.10th IAPR international workshop on Graphics RECognition (Line and Arc Segmentation Contest). http://​grec2013.​loria.​fr/​GREC2013/​ (2013)
  4.Al-Khaffaf, H., Talib, A.Z., Salam, R.A.: Removing salt-and-pepper noise from binary images of engineering drawings. In: Proceedings of Nineteenth International Conference on Pattern Recognition, pp. 1–4 (2008)
  5.Al-Khaffaf, H.S.M., Talib, A.Z., Abdul. R.: Salt and pepper noise removal from document images. In: Visual Informatics: Bridging Research and Practice, volume 5857 of Lecture Notes in Computer Science, pp. 607–618 (2009)
  6.Ballard, D.H.: Generalizing the hough transform to detect arbitrary shapes. Pattern Recognit. 13(2), 111–122 (1981)CrossRef MATH
  7.Bhowmick, P., Bhattacharya, B.B.: Fast polygonal approximation of digital curves using relaxed straightness properties. IEEE Trans. Pattern Anal. Mach. Intell. 29(9), 1590–1602 (2007)CrossRef
  8.Bhowmick, P., Bhattacharya, B.B.: Number-theoretic interpretation and construction of a digital circle. Discrete Appl. Math. 156(12), 2381–2399 (2008)CrossRef MathSciNet MATH
  9.Chinnasarn, K., Rangsanseri, Y., Thitimajshima, P.: Removing salt-and-pepper noise in text/graphics images. In: Proceedings of the IEEE Asia-Pacific Conference on Circuits and Systems, pp. 459–462 (1998)
  10.Chowdhury, S.P., Mandal, S., Das, A.K., Chanda, B.: Segmentation of text and graphics from document images. In: Proceedings of the Ninth International Conference on Document Analysis and Recognition, vol. 2, pp. 619–623 (2007)
  11.di Baja, G.S.: Well-shaped, stable, and reversible skeletons from the (3, 4)-distance transform. J. Vis. Commun. Image Represent. 5(1), 107–115 (1994)CrossRef
  12.Dori, D.: Orthogonal zig-zag: an algorithm for vectorizing engineering drawings compared with hough transform. Adv. Eng. Softw. 28(1), 11–24 (1997)CrossRef
  13.Dori, D., Liu, W.: Stepwise recovery of arc segmentation in complex line environments. Int. J. Doc. Anal. Recognit. 1(1), 62–71 (1998)
  14.Dori, D., Liu, W.: Sparse pixel vectorization: an algorithm and its performance evaluation. IEEE Trans. Pattern Anal. Mach. Intell. 21(3), 202–215 (1999)CrossRef
  15.Elliman, D.: A really useful vectorization algorithm. In: Proceedings of Third International Workshop on Graphics Recognition, GREC’99, pp. 19–27 (1999)
  16.Elliman, D.: TIF2VEC, an algorithm for arc segmentation in engineering drawings. Gr. Recognit. Algorithms Appl. 2390, 350–358 (2002)CrossRef
  17.Escribano, C., Giraldo, A., Sastre, M.: Digitally continuous multivalued functions, morphological operations and thinning algorithms. J. Math. Imaging Vis. 42(1), 76–91 (2012)CrossRef MathSciNet MATH
  18.Fletcher, L.A., Kasturi, R.: A robust algorithm for text string separation from mixed text/graphics images. IEEE Trans. Pattern Anal. Mach. Intell. 10(6), 910–918 (1988)CrossRef
  19.Haralick, R.M., Shapiro, L.G.: Computer and Robot Vision. Addision-Wesley, Reading (1992)
  20.Henderson, T.C.: Analysis of Engineering Drawings and Raster Map Images. Springer, Berlin (2014)CrossRef MATH
  21.Hilaire, X., Tombre, K.: Robust and accurate vectorization of line drawings. IEEE Trans. Pattern Anal. Mach. Intell. 28(6), 890–904 (2006)CrossRef
  22.Hori, O., Tanigawa, S.: Raster-to-vector conversion by line fitting based on contours and skeletons. In: Proceedings of the Second International Conference on Document Analysis and Recognition, ICDAR’93, pp. 353–358 (1993)
  23.ISO 128: Technical Drawings—General Principles of Presentation (Parts 1, 23, 24). International Organization for Standardization, Geneva (2003)
  24.Joseph, S.H., Pridmore, T.P.: Knowledge-directed interpretation of mechanical engineering drawings. IEEE Trans. Pattern Anal. Mach. Intell. 14(9), 928–940 (1992)CrossRef
  25.Kasturi, R., Bow, S.T., El-Masri, W., Shah, J., Gattiker, J.R., Mokate, U.B.: A system for interpretation of line drawings. IEEE Trans. Pattern Anal. Mach. Intell. 12(10), 978–992 (1990)CrossRef
  26.Klette, R., Rosenfeld, A.: Digital Geometry: Geometric Methods for Digital Picture Analysis. Morgan Kaufmann, San Francisco (2004)
  27.Ko, S., Lee, Y.: Center weighted median filters and their applications to image enhancement. IEEE Trans. Circuits Syst. 38(9), 984–993 (1991)CrossRef
  28.Lam, L., Lee, S.-W., Suen, C.: Thinning methodologies—a comprehensive survey. IEEE Trans. Pattern Anal. Mach. Intell. 14(9), 869–885 (1992)CrossRef
  29.O’Gorman, L.: Image and document processing techniques for the RightPages electronic library system. In: Proceedings of Eleventh IAPR International Conference on Pattern Recognition, pp. 260–263 (1992)
  30.Otsu, N.: A threshold selection method from gray-level histogram. IEEE Trans. Syst. Man Cybernet. 9(1), 62–66 (1979)CrossRef MathSciNet
  31.Pal, S., Bhowmick, P.: Determining digital circularity using integer intervals. J. Math. Imaging Vis. 42(1), 1–24 (2012)CrossRef MathSciNet MATH
  32.Rosenfeld, A.: Digital straight line segments. IEEE Trans. Comput. 23(12), 1264–1269 (1974)CrossRef MathSciNet MATH
  33.Scalable Vector Graphics. http://​en.​wikipedia.​org/​wiki/​Scalable_​Vector_​Graphics (2014)
  34.Simmons, C., Maguire, D., Phelps, N.: Manual of Engineering Drawing (Technical Product Specification and Documentation to British and International Standards, 3rd Edition). Elsevier, Amsterdam (2010)
  35.Song, J., Lyu, M.R., Cai, S.: Effective multiresolution arc segmentation: algorithms and performance evaluation. IEEE Trans. Pattern Anal. Mach. Intell. 26(11), 1491–1506 (2004)CrossRef
  36.Song, J., Su, F., Chen, J., Tai, C.: Line net global vectorization: an algorithm and its performance evaluation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 383–388 (2000)
  37.Song, J., Su, F., Tai, C.L., Cai, S.: An object-oriented progressive-simplification-based vectorization system for engineering drawings: model, algorithm, and performance. IEEE Trans. Pattern Anal. Mach. Intell. 24(8), 1048–1060 (2002)CrossRef
  38.Story, G.A., O’Gorman, L., Fox, D., Schaper, L.L., Jagadish, H.V.: The RightPages image-based electronic library for alerting and browsing. IEEE Comput. 25(9), 17–26 (1992)CrossRef
  39.SVG stands for Scalable Vector Graphics. http://​www.​w3schools.​com/​svg (1999). Copyright 1999–2014 by Refsnes Data
  40.Wenyin, L., Zhang, W., Yan, L.: An interactive example-driven approach to graphics recognition in engineering drawings. Int. J. Doc. Anal. Recognit. 9(1), 13–29 (2007)CrossRef
  41.Yu, Y., Samal, A., Seth, S.: A system for recognizing a large class of engineering drawings. IEEE Trans. Pattern Anal. Mach. Intell. 19(8), 868–890 (1997)CrossRef
  
• 作者单位：Paramita De (1)
  Sekhar Mandal (1)
  Partha Bhowmick (2)
  Amit Das (1)
  
  1. Indian Institute of Engineering Science and Technology, Shibpur, India
  2. Indian Institute Technology, Kharagpur, India
  
• 刊物类别：Computer Science
• 刊物主题：Image Processing and Computer Vision
  Pattern Recognition
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1433-2825

文摘

We propose here an efficient algorithm for high-level vectorization of scanned images of mechanical engineering drawings. The algorithm is marked by several novel features, which merit its superiority over the existing techniques. After preprocessing and necessary refinement of junction points in the image skeleton, it first extracts the graphic primitives, such as lines, circles, and arcs, based on certain digital geometric properties of straightness and circularity in the discrete domain. The primitives are classified into different types with all associated details based on fast and efficient geometric analysis. The vector set is succinctly reduced by such classification in tandem with further consolidation to make out meaningful objects like rectangles and annuli, together with hatching information. Exhaustive testing shows the efficiency of the algorithm and also its robustness and stability toward any affine transformation and injected noise. Easy reconstruction to scalable vector graphics demonstrates its readiness and usability as a state-of-the-art solution.