A survey of non-thinning based vectorization methods
Document Image Analysis and Recognition
First Online:
Abstract
We survey the methods developed up to date for crude vectorization of document images. We classify them into six categories: thinning based, Hough Transform based, contour-based, run-graph based, mesh-pattern based, and sparse pixel based. The crude vectorization is a relatively mature subject in the Document Analysis and Recognition field, though there are rooms to improve. The purpose of the survey is to provide researchers with a comprehensive overview of this technique for them to choose a suitable method when developing their vectorization algorithms and systems.
Keywords
Vectorization Document Analysis and Recognition Polygonalization Download
to read the full conference paper text
Reference
- [1]Boatto L et al. (1992) An Interpretation System for Land Register Maps. IEEE Computer 25(7):25–32Google Scholar
- [2]Chai I, Dori D (1992) Orthogonal Zig-Zag: An Efficient Method for Extracting Lines from Engineering Drawings. In: Visual Form, eds. Arcelli C, Cordella LP, Sanniti di Baja G, Plenum Press, New York London, pp 127–136Google Scholar
- [3]Di Zenzo S and Morelli A (1989) A useful image representation. In: Proc of 5th Int. Conf. on Image Analysis and Processing, Singapore, pp 170–178.Google Scholar
- [4]Dori D, Liang Y, Dowell J, I. Chai (1993) Spare Pixel Recognition of Primitives in Engineering Drawings. Machine Vision and Applications 6:79–82Google Scholar
- [5]Dori D (1997) Orthogonal Zig-Zag: an Algorithm for Vectorizing Engineering Drawings Compared With Hough Transform. Advances in Engineering Software 28(1):11–24CrossRefGoogle Scholar
- [6]Dunham JG (1986) Optimum uniform piecewise linear approximation of planar curves. IEEE PAM 18(1):67–75Google Scholar
- [7]Hough PVC (1962) A method and means for recognizing complex patterns, ]USA Patent 3,096,654, 1962.Google Scholar
- [8]Hung SHY and Kasvand T (1983) Critical points on a perfectly 8-or perfectly 6connected thin binary line. Pattern Recognition 16:297–284.CrossRefGoogle Scholar
- [9]Jaisimha MY et al. (1993) A Methodology for the Characterization of the Performance of Thinning Algorithms. In: Proc. of 2nd ICDAR, pp 282–286Google Scholar
- [10]Jimenez J and Navalon JL (1982) Some Experiments in Image Vectorization. IBM J. Res. Develop 26:724–734Google Scholar
- [11]Kasturi R et al. (1990) A System for Interpretation of Line Drawings. IEEE PAMI 12(10):978–992Google Scholar
- [12]Lam L, Lee SW, and Suen CY (1992) Thinning methodologies — A comprehensive survey. IEEE PAMI:14(9):869–887.Google Scholar
- [13]Lam L, Suen CY (1993) Evaluation of Thinning Algorithms from an OCR Viewpoint. In: Proc. of 2nd ICDAR, Tsukuba, Japan, pp 287–290Google Scholar
- [14]Lee S et al. (1991) Performance Evaluation of Skeletonization Algorithms for Document Image Processing. In: Proc. of Ist ICDAR, France, pp 260–271Google Scholar
- [15]Lin X et al. (1985) Efficient Diagram Understanding With Characteristic Pattern Detection. Computer Vision, Graphics and Image Processing 30:84–106Google Scholar
- [16]Liu W et al. (1995) Object Recognition in Engineering Drawings Using Planar Indexing. In: Proc. of GREC'95, Penn. State Univ., USA, pp 53–61Google Scholar
- [17]Liu W, Dori D (1996) Sparse Pixel Tracking: A Fast Vectorization Algorithm Applied to Engineering Drawings. In: Proc. 13th ICPR, Vienna, Austria, Volume III (Robotics and Applications, pp 808–811Google Scholar
- [18][18]Liu W, Dori D (1997) A Protocol for Performance Evaluation of Line Detection Algorithms. Machine Vision Applications 9(5/6):240–250CrossRefGoogle Scholar
- [19]Monagan G and Roosli M (1993) Appropriate Base Representation Using a Run Graph. In: Proc. of 2nd ICDAR, Tsukuba, Japan, 1993, pp 623–626Google Scholar
- [20]Montanari U (1970) A note on the minimal length polygonal approximation to a digitized contour. CACM 13(l):41–47.Google Scholar
- [21]Sklansky J and Gonzalez V (1980) Fast Polygonal Approximation of Digitized Curves. Pattern Recognition 12:327–331CrossRefGoogle Scholar
- [22]Smith RW (1987) Computer Processing of Line Images: A Survey. Pattern Recognition 20(1):7–15CrossRefGoogle Scholar
- [23]Tamura H (1978) A Comparison of Line Thinning Algorithms from Digital Geometry Viewpoint. In: Proc. of 4th ICPR, Kyoto, Japan, pp 715–719Google Scholar
- [24]Vaxiviere P and Tombre K (1992) Cellestin: CAD Conversion of Mechanical Drawings. IEEE Computer 25(5): 46–54Google Scholar
- [25]Vaxiviere P and Tombre K (1995) Subsampling: A Structural Approach to Technical Document Vectorization. In: Shape, Structure and Pattern Recognition, eds. Dori D and Bruckstein A, World Scientific, 1995, pp 323–332Google Scholar
- [26]Yoo J-Y et al. (1998) Information Extraction from a Skewed Form Document in the Presence of Crossing Characters. In: Graphics Recognition—Algorithms and Systems, eds. K. Tombre and A. Chhabra, Lecture Notes in Computer Science, Vol. 1389, pp139–148, Springer, April, 1998Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 1998