Robust and accurate vectorization of line drawings

This paper presents a method for vectorizing the graphical parts of paper-based line drawings. The method consists of separating the input binary image into layers of homogeneous thickness, skeletonizing each layer, segmenting the skeleton by a method based on random sampling, and simplifying the result. The segmentation method is robust with a best bound of 50 percent noise reached for indefinitely long primitives. Accurate estimation of the recognized vector's parameters is enabled by explicitly computing their feasibility domains. Theoretical performance analysis and expression of the complexity of the segmentation method are derived. Experimental results and comparisons with other vectorization systems are also provided.

[1]  Karl Tombre,et al.  Graphics Recognition Algorithms and Systems , 1997, Lecture Notes in Computer Science.

[2]  Dov Dori,et al.  A System for Performance Evaluation of Arc Segmentation Algorithms , 2001 .

[3]  Suzanne Collin,et al.  Analysis of Technical Documents: The REDRAW System , 1992 .

[4]  Ihsin T. Phillips,et al.  The Second International Graphics Recognition Contest - Raster to Vector Conversion: A Report , 1997, GREC.

[5]  Edouard Thiel Les distances de chanfrein en analyse d'images : fondements et applications. (Chamfer distances in image analysis : basis and applications) , 1994 .

[6]  Karl Tombre,et al.  Improving the Accuracy of Skeleton-Based Vectorization , 2001, GREC.

[7]  Jisheng Liang,et al.  Performance evaluation for line-drawing recognition systems , 1997, Electronic Imaging.

[8]  Jean Camillerapp,et al.  Kalman filtering for segment detection: application to music scores analysis , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[9]  Erkki Oja,et al.  Randomized Hough Transform (RHT) in Engineering Drawing Vectorization System , 1990, MVA.

[10]  Gabriella Sanniti di Baja Well-Shaped, Stable, and Reversible Skeletons from the (3, 4)-Distance Transform , 1994, J. Vis. Commun. Image Represent..

[11]  Hiromitsu Yamada PAPER-BASED MAP PROCESSING , 1997 .

[12]  David S. Doermann,et al.  A parallel-line detection algorithm based on HMM decoding , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[14]  Salvatore Tabbone,et al.  Stable and Robust Vectorization: How to Make the Right Choices , 1999, GREC.

[15]  Michael Brady,et al.  The Curvature Primal Sketch , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Christian Ah-Soon,et al.  A complete system for the analysis of architectural drawings , 2000, International Journal on Document Analysis and Recognition.

[17]  Albert M. Vossepoel,et al.  Adaptive Vectorization of Line Drawing Images , 1997, Comput. Vis. Image Underst..

[18]  Geoff A. W. West,et al.  Segmentation of edges into lines and arcs , 1989, Image Vis. Comput..

[19]  Michael R. Lyu,et al.  A Hough transform based line recognition method utilizing both parameter space and image space , 2005, Pattern Recognit..

[20]  Dave Elliman TIF2VEC, An Algorithm for Arc Segmentation in Engineering Drawings , 2001, GREC.

[21]  S. H. Joseph Unbiased Least Squares Fitting of Circular Arcs , 1994, CVGIP Graph. Model. Image Process..

[22]  Peter Veelaert Concurrency of Line Segments in Uncertain Geometry , 2002, DGCI.

[23]  A. Smeulders,et al.  Discrete straight line segments: parameters, primitives and properties , 1991 .

[24]  Sung-Bae Cho,et al.  Geometric Structure Analysis of Document Images: A Knowledge-Based Approach , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Rangachar Kasturi,et al.  A Robust Algorithm for Text String Separation from Mixed Text/Graphics Images , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Dov Dori,et al.  Genericity in Graphics Recognition Algorithms , 1997, GREC.

[27]  James R. Gattiker,et al.  A System for Interpretation of Line Drawings , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Bart Lamiroy,et al.  Text/Graphics Separation Revisited , 2002, Document Analysis Systems.

[29]  Dov Dori,et al.  Sparse Pixel Vectorization: An Algorithm and Its Performance Evaluation , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  Michael R. Lyu,et al.  Effective multiresolution arc segmentation: algorithms and performance evaluation , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Shijie Cai,et al.  An Object-Oriented Progressive-Simplification-Based Vectorization System for Engineering Drawings: Model, Algorithm, and Performance , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Ihsin T. Phillips,et al.  Empirical Performance Evaluation of Graphics Recognition Systems , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Noshir A. Langrana,et al.  Engineering Drawing Processing and Vectorization System , 1990, Comput. Vis. Graph. Image Process..

[34]  Dov Dori,et al.  Orthogonal Zig-Zag: an algorithm for vectorizing engineering drawings compared with Hough Transform , 1997 .

[35]  Xavier Hilaire Segmentation robuste de courbes discrètes 2D et applications à la rétroconversion de documents techniques , 2004 .

[36]  King-Sun Fu,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence Publication Information , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Dov Dori,et al.  Incremental Arc Segmentation Algorithm and Its Evaluation , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[38]  Morakot Pilouk,et al.  Using local deviations of vectorization to enhance the performance of raster-to-vector conversion systems , 2000, International Journal on Document Analysis and Recognition.

[39]  HARRY BLUM,et al.  Shape description using weighted symmetric axis features , 1978, Pattern Recognit..

[40]  MokhtarianFarzin,et al.  A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves , 1992 .

[41]  Tony P. Pridmore,et al.  Knowledge-Directed Interpretation of Mechanical Engineering Drawings , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[42]  A FletcherLloyd,et al.  A Robust Algorithm for Text String Separation from Mixed Text/Graphics Images , 1988 .

[43]  Robert M. Haralick,et al.  A Statistical, Nonparametric Methodology for Document Degradation Model Validation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[44]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[45]  Dov Dori,et al.  A protocol for performance evaluation of line detection algorithms , 1997, Machine Vision and Applications.

[46]  N. Megiddo,et al.  Computing circular separability , 1986 .

[47]  Farzin Mokhtarian,et al.  A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[48]  Roland T. Chin,et al.  On the Detection of Dominant Points on Digital Curves , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[49]  Yuan Chen,et al.  Perfecting Vectorized Mechanical Drawings , 1996, Comput. Vis. Image Underst..

[50]  Karin Wall,et al.  A fast sequential method for polygonal approximation of digitized curves , 1984, Comput. Vis. Graph. Image Process..

[51]  Raymond W. Smith,et al.  Computer processing of line images: A survey , 1987, Pattern Recognit..

[52]  Urs Ramer,et al.  An iterative procedure for the polygonal approximation of plane curves , 1972, Comput. Graph. Image Process..

[53]  Dov Dori,et al.  A Survey of Non-thinning Based Vectorization Methods , 1998, SSPR/SPR.

[54]  Wenyin Liu Report of the Arc Segmentation Contest , 2003, GREC.

[55]  Ching Y. Suen,et al.  Thinning Methodologies - A Comprehensive Survey , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[56]  Paul L. Rosin Techniques for Assessing Polygonal Approximations of Curves , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[57]  Dov Dori,et al.  Extended Summary of the Arc Segmentation Contest , 2001, GREC.

[58]  Osamu Hori,et al.  Raster-to-vector conversion by line fitting based on contours and skeletons , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).