A table-form extraction with artefact removal

ABSTRACT

We present a novel methodology for extracting the structure of handwritten filled table-forms. The method identifies the table-form line intersections, detecting and correcting wrong intersections produced by faulty line segments or by table artefacts. Examples of artefacts are overlapping data, broken segments, and smudges. A novel method for artefact identification and deletion is also proposed. The last step performs the extraction of table-form cells.

A database of 350 table-form images was used for evaluation, showing that the artefact identification method improves the performance of the table-forms structure extractor. The proposed approach reached a success rate of 85%.

REFERENCES

• 1: J. F. Arias , A. Chhabra , V. Misra, Interpreting and representing tabular documents, Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96), p.600, June 18-20, 1996
• 2: J. F. Arias , R. Kasturi , A. Chhabra, Efficient techniques for telephone company line drawing interpretation, Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 2), p.795, August 14-15, 1995
• 3: Bertrand Coüasnon, DMOS: A Generic Document Recognition Method, Application to an Automatic Generator of Musical Scores, Mathematical Formulae and Table Structures Recognition Systems, Proceedings of the Sixth International Conference on Document Analysis and Recognition, p.215, September 10-13, 2001
• 4: Kuo-Chin Fan , Jeng-Ming Lu , Liang-Sheng Wang , Hong-Yuan Liao, Extraction of characters from form documents by feature point clustering, Pattern Recognition Letters, v.16 n.9, p.963-970, Sept. 1995 [doi>10.1016/0167-8655(95)00040-N ]
• 5: Field Extraction Method from Existing Forms Transmitted by Facsimile, Proceedings of the Sixth International Conference on Document Analysis and Recognition, p.738, September 10-13, 2001
• 6: O. Hori , D. S. Doermann, Robust table-form structure analysis based on box-driven reasoning, Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 1), p.218, August 14-15, 1995
• 7: J. Hu, R. S. Kashi, D. Lopresti, and G. T. Wilfong. Evaluating the performance of table processing algorithms. International Journal on Document Analysis and Recognition, 4:140--153, 2002.
• 8: Thomas Kieninger , Andreas Dengel, The T-Recs Table Recognition and Analysis System, Selected Papers from the Third IAPR Workshop on Document Analysis Systems: Theory and Practice, p.255-269, November 04-06, 1998
• 9: Jisheng Liang , Jaekyu Ha , Robert M. Haralick , Ihsin T. Phillips, Document Layout Structure Extraction Using Bounding Boxes of Different Entities, Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV '96), p.278, December 02-04, 1996
• 10: L. A. P. Neves. Extração de células de dados manuscritos em tabelas. Master's thesis, Pontifícia Universidade Católica do Paraná - PUCPR, Brazil, 1999.
• 11: L. A. P. Neves. Metodologia de Extração de Recuperação de Tabelas. PHD thesis - Universidade Federal de Campina Grande - UFCG, Paraíba, 2006.
• 12: A. Pizano. Extracting line features from images of business forms and tables. IAPR - In: Proceedings of the 11th International Conference on Pattern Recognition, 3:399--403, 1992.
• 13: S. Shimotsuji , M. Asano, Form Identification Based on Cell Structure, Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276, p.793, August 25-29, 1996
• 14: A Recursive Analysis for Form Cell Recognition, Proceedings of the Sixth International Conference on Document Analysis and Recognition, p.694, September 10-13, 2001
• 15: R. T. V. Thom. Modelisation de Tableaux pour le traitement Automatique des Formulaires. Laboratoire PSI, Universit de Rouen, 1997.
• 16: T. Watanabe, Q. Luo, and N. Sugie. Structure recognition methods for various types of documents. Machine Vision and Applications, 1993.
• 17: T. Watanabe, Q. Luo, and N. Sugie. Toward a practical document understanding of table-form documents: Its framework and knowledge representation. In: Second Conference on Document Analysis and Recognition, pages 510--515, 1993.
• 18: Toyohide Watanabe , Qin Luo , Noboru Sugie, Layout Recognition of Multi-Kinds of Table-Form Documents, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.17 n.4, p.432-445, April 1995 [doi>10.1109/34.385976 ]
• 19: Tukey, J. W.: Exploratory Data Analysis. Addison-Wesley, 1977.
• 20: Neves, L. A. P.; Carvalho, J. M. ; Facon, J.. Bit Block Transfer and Structuring Element Decomposition for Table-form Physical Structure. SIBGRAPI 2003 - XVI Brazilian Symposium on Computer Graphics and Image Processing, 2003, São Carlos, SP.
• 21: Neves, L. A. P.; Carvalho, J. M.; Facon, J.. Recognition of Deteriorated Table-form Documents: A New Approach. SIBGRAPI 2003 - XVI Brazilian Symposium on Computer Graphics and Image Processing, 2003, São Carlos, SP.
• 22: Neves, L. A. P.; Carvalho, J. M.; Facon, J.; Bortolozzi, F.; Ignacio, S. A. Handwritten Artefact Identification Method In Table Interpretation With Little Use of Knowledge. LNCS - DAS 2006 - Seventh International Association For Pattern Recognition on Document Analysis Systems, Nelson, Nova Zelǎndia, 2006.
• 23: Luiz Antônio Pereira Neves , João Marques de Carvalho , Jacques Facon , Flávio Bortolozzi, A new table interpretation methodology with little knowledge base: table interpretation methodology, Proceedings of the 2006 ACM symposium on Applied computing, April 23-27, 2006, Dijon, France [doi>10.1145/1141277.1141470]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
        I.4.10 Image Representation

General Terms:
Algorithms

Keywords:
document segmentation, handwritten data, table-form extraction, table-form recognition