Relational indexing of vectorial primitives for symbol spotting in line-drawing images

This paper presents a symbol spotting approach for indexing by content a database of line-drawing images. As line-drawings are digital-born documents designed by vectorial softwares, instead of using a pixel-based approach, we present a spotting method based on vector primitives. Graphical symbols are represented by a set of vectorial primitives which are described by an off-the-shelf shape descriptor. A relational indexing strategy aims to retrieve symbol locations into the target documents by using a combined numerical-relational description of 2D structures. The zones which are likely to contain the queried symbol are validated by a Hough-like voting scheme. In addition, a performance evaluation framework for symbol spotting in graphical documents is proposed. The presented methodology has been evaluated with a benchmarking set of architectural documents achieving good performance results.

[1]  Thomas M. Breuel,et al.  Distance measures for layout-based document image retrieval , 2006, Second International Conference on Document Image Analysis for Libraries (DIAL'06).

[2]  Matti Pietikäinen,et al.  An Experimental Comparison of Autoregressive and Fourier-Based Descriptors in 2D Shape Classification , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Georg Lambert,et al.  Line Moments and Invariants for Real Time Processing of Vectorized Contour Data , 1995, ICIAP.

[4]  Georg Lambert,et al.  Discrimination properties of invariants using the line moments of vectorized contours , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[5]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[6]  John C. Russ,et al.  Image Processing Handbook, Fourth Edition , 2002 .

[7]  S. Sadid-Al-Hasan,et al.  Advances in focused retrieval: A general review , 2007, 2007 10th international conference on computer and information technology.

[8]  John C. Russ,et al.  The Image Processing Handbook , 2016, Microscopy and Microanalysis.

[9]  Horst Bunke,et al.  Automatic Learning and Recognition of Graphical Symbols in Engineering Drawings , 1995, GREC.

[10]  Rakesh Mohan,et al.  Multidimensional indexing for recognizing visual shapes , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Jacques Labiche,et al.  Symbol and character recognition: application to engineering drawings , 2000, International Journal on Document Analysis and Recognition.

[12]  D. Stoyan,et al.  Fractals, random shapes and point fields : methods of geometrical statistics , 1996 .

[13]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[14]  Bart Lamiroy,et al.  Graphics recognition - from re-engineering to retrieval , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[15]  Gladys Monagan,et al.  A Retrieval System for Graphical Documents , 1995 .

[16]  Tanveer F. Syeda-Mahmood,et al.  Indexing of Technical Line Drawing Databases , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  David P. Dobkin,et al.  The quickhull algorithm for convex hulls , 1996, TOMS.

[18]  Mohammad F. Daemi,et al.  Global description of edge patterns using moments , 1994, Pattern Recognit..

[19]  Oliver Günther,et al.  Multidimensional access methods , 1998, CSUR.

[20]  Josep Lladós,et al.  A performance evaluation protocol for symbol spotting systems in terms of recognition and location indices , 2009, International Journal on Document Analysis and Recognition (IJDAR).

[21]  Laurent Wendling,et al.  Matching of graphical symbols in line-drawing images using angular signature information , 2003, Document Analysis and Recognition.

[22]  Sanjoy Dasgupta,et al.  Adaptive Control Processes , 2010, Encyclopedia of Machine Learning and Data Mining.

[23]  Ulrich Eckhardt,et al.  Shape descriptors for non-rigid shapes with a single closed contour , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[24]  Linda G. Shapiro,et al.  3D Object Recognition and Pose with Relational Indexing , 2000, Comput. Vis. Image Underst..

[25]  Apostolos Antonacopoulos,et al.  Ground Truth for Layout Analysis Performance Evaluation , 2006, Document Analysis Systems.

[26]  Otto J. M. Smith,et al.  Sparse Solutions Using Hash Storage , 1972 .

[27]  Josep Lladós,et al.  Symbol spotting in vectorized technical drawings through a lookup table of region strings , 2009, Pattern Analysis and Applications.

[28]  Josep Lladós,et al.  Vectorial Signatures for Symbol Discrimination , 2003, GREC.

[29]  Bart Lamiroy,et al.  Pattern Recognition Methods for Querying and Browsing Technical Documentation , 2008, CIARP.

[30]  Ralph Roskies,et al.  Fourier Descriptors for Plane Closed Curves , 1972, IEEE Transactions on Computers.

[31]  Wenyin Liu.  Example-Driven Graphics Recognition , 2002, SSPR/SPR.

[32]  Laurent Najman,et al.  Indexing technical drawings using title block structure recognition , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[33]  P. Héroux,et al.  Frequent Graph Discovery: Application to Line Drawing Document Images , 2005 .

[34]  Guojun Lu,et al.  Review of shape representation and description techniques , 2004, Pattern Recognit..

[35]  R. Bellman,et al.  V. Adaptive Control Processes , 1964 .

[36]  Wenyin Liu,et al.  An interactive example-driven approach to graphics recognition in engineering drawings , 2006, International Journal of Document Analysis and Recognition (IJDAR).

[37]  Laurent Wendling,et al.  Indexing of technical line drawings based on F-signatures , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[38]  H. Buchner.  The Grid File : An Adaptable , Symmetric Multikey File Structure , 2001 .

[39]  Alexei A. Efros,et al.  Discovering objects and their location in images , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[40]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[41]  Th. M. Hupkens,et al.  Noise and intensity invariant moments , 1995, Pattern Recognit. Lett..

[42]  R. Manmatha,et al.  Word image matching using dynamic time warping , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[43]  Chaur-Chin Chen.  Improved moment invariants for shape discrimination , 1993, Pattern Recognit..

[44]  Salvatore Tabbone,et al.  A Method for Symbol Spotting in Graphical Documents , 2006, Document Analysis Systems.

[45]  Josep Lladós,et al.  Symbol Recognition by Error-Tolerant Subgraph Matching between Region Adjacency Graphs , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

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

[47]  Josep Lladós,et al.  Symbol Spotting in Technical Drawings Using Vectorial Signatures , 2005, GREC.

[48]  Jean-Yves Ramel,et al.  Document image characterization using a multiresolution analysis of the texture: application to old documents , 2008, International Journal of Document Analysis and Recognition (IJDAR).