Extending Page Segmentation Algorithms for Mixed-Layout Document Processing

The goal of this work is to add the capability to segment documents containing text, graphics, and pictures in the open source OCR engine OCRopus. To achieve this goal, OCRopus' RAST algorithm was improved to recognize non-text regions so that mixed content documents could be analyzed in addition to text-only documents. Also, a method for classifying text and non-text regions was developed and implemented for the Voronoi algorithm enabling users to perform OCR on documents processed by this method. Finally, both algorithms were modified to perform at a range of resolutions. Our testing showed an improvement of 15-40% for the RAST algorithm, giving it an average segmentation accuracy of about 80%. The Voronoi algorithm averaged around 70% accuracy on our test data. Depending on the particular layout and idiosyncracies of the documents to be digitized, however, either algorithm could be sufficiently accurate to be utilized.

[1]  Venu Govindaraju,et al.  Dynamic local connectivity and its application to page segmentation , 2004, HDP '04.

[2]  Thomas M. Breuel,et al.  Two Geometric Algorithms for Layout Analysis , 2002, Document Analysis Systems.

[3]  Tapas Kanungo,et al.  The architecture of TrueViz: a groundTRUth/metadata editing and VIsualiZing ToolKit , 2003, Pattern Recognit..

[4]  Apostolos Antonacopoulos,et al.  ICDAR 2009 Page Segmentation Competition , 2003, 2009 10th International Conference on Document Analysis and Recognition.

[5]  Wei Zhang,et al.  Features for neural net based region identification of newspaper documents , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[6]  Motoi Iwata,et al.  Segmentation of Page Images Using the Area Voronoi Diagram , 1998, Comput. Vis. Image Underst..

[7]  Thomas M. Breuel,et al.  The OCRopus open source OCR system , 2008, Electronic Imaging.

[8]  Thomas M. Breuel,et al.  Document image zone classification - a simple high-performance approach , 2007, VISAPP.

[9]  Thomas M. Breuel.  A practical, globally optimal algorithm for geometric matching under uncertainty , 2001, Electron. Notes Theor. Comput. Sci..

[10]  Basilios Gatos,et al.  ICDAR2005 page segmentation competition , 2007, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[11]  Friedrich M. Wahl,et al.  Document Analysis System , 1982, IBM J. Res. Dev..

[12]  Mahesh Viswanathan,et al.  A prototype document image analysis system for technical journals , 1992, Computer.

[13]  Maher A. Sid-Ahmed,et al.  A Neural-based Page Segmentation System , 2005, J. Circuits Syst. Comput..

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