Robust document image understanding technologies

ABSTRACT

No existing document image understanding technology, whether experimental or commercially available, can guarantee high accuracy across the full range of documents of interest to industrial and government agency users. Ideally, users should be able to search, access, examine, and navigate among document images as effectively as they can among encoded data files, using familiar interfaces and tools as fully as possible. We are investigating novel algorithms and software tools at the frontiers of document image analysis, information retrieval, text mining, and visualization that will assist in the full integration of such documents into collections of textual document images as well as "born digital" documents. Our approaches emphasize <i>versatility first</i>: that is, methods which work reliably across the broadest possible range of documents.

REFERENCES

• 1: H. Baird. Model-directed document image analysis. In Proceedings of the DOD-sponsored Symposium on Document Image Understanding Technology (SDIUT 1999), pages 42--49, Annapolis, Maryland, April 1999.
• 2: H. Baird, K. Popat, T. Breuel, P. Sarkar, and D. Lopresti. Assuring high-accuracy document understanding: Retargeting, scaling up, and adapting. In Proceedings of the Symposium on Document Image Understanding Technology, pages 17--29, Greenbelt, MD, April 2003.
• 3: H. S. Baird. Anatomy of a versatile page reader. Proceedings of the IEEE, 80(7):1059--1065, July 1992.
• 4: H. S. Baird, A. L. Coates, and R. Fateman. PessimalPrint: a reverse Turing test. Int'l J. on Document Analysis and Recognition, 5:158--163, 2003.
• 5: H. S. Baird and G. Nagy. A self-correcting 100-font classifier. In Proceedings, IS&T/SPIE Symposium on Electronic Imaging: Science & Technology, pages 106--115, San Jose, CA, February 1994.
• 6: H. S. Baird , K. Thompson, Reading Chess, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.12 n.6, p.552-559, June 1990 [doi>10.1109/34.56191]
• 7: 'Miserable failure' links to Bush: George W Bush has been Google bombed. BBC News, Dec. 2003. http://news.bbc.co.uk/2/hi/americas/3298443.stm.
• 8: Document Image Decoding Using Iterated Complete Path Search with Subsampled Heuristic Scoring, Proceedings of the Sixth International Conference on Document Analysis and Recognition, p.344, September 10-13, 2001
• 9: T. Breuel. Modeling the Sample Distribution for Clustering OCR. In SPIE Conference on Document Recognition and Retrieval VIII, 2001.
• 10: T. Breuel and K. Popat. Recent work in the document image decoding group at xerox parc. In Proceedings of the DOD-sponsored Symposium on Document Image Understanding Technology (SDIUT 2001), Columbia, Maryland, April 2001.
• 11: Thomas M. Breuel , William C. Janssen , Kris Popat , Henry S. Baird, Paper to PDA, Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1, p.10476, August 11-15, 2002
• 12: Sergey Brin , Lawrence Page, The anatomy of a large-scale hypertextual Web search engine, Proceedings of the seventh international conference on World Wide Web 7, p.107-117, April 1998, Brisbane, Australia
• 13: M. Chew and H. S. Baird. Baffletext: a human interactive proof. In Proc., 10th IS&T/SPIE Document Recognition & Retrieval Conf., Santa Clara, CA, January 2003.
• 14: Yi-Ming Chung , William M. Pottenger , Bruce R. Schatz, Automatic subject indexing using an associative neural network, Proceedings of the third ACM conference on Digital libraries, p.59-68, June 23-26, 1998, Pittsburgh, Pennsylvania, United States [doi>10.1145/276675.276682]
• 15: Brian D. Davison, Topical locality in the Web, Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval, p.272-279, July 24-28, 2000, Athens, Greece [doi>10.1145/345508.345597]
• 16: B. D. Davison, A. Gerasoulis, K. Kleisouris, Y. Lu, H. Seo, W. Wang, and B. Wu. DiscoWeb: Applying link analysis to Web search. In Poster proceedings of the Eighth International World Wide Web Conference, pages 148--149, Toronto, Canada, May 1999.
• 17: Digital Bridges. Lehigh University Libraries, April 2004. http://bridges.lib.lehigh.edu/.
• 18: Distributed Proofreaders. Project gutenberg's distributed proofreaders home page. http://www.pgdp.net/, 2004.
• 19: David Doermann, The indexing and retrieval of document images: a survey, Computer Vision and Image Understanding, v.70 n.3, p.287-298, June 1, 1998 [doi>10.1006/cviu.1998.0692]
• 20: Document Understanding Conference (DUC): Workshop on Text Summarization, 2002. http://tides.nist.gov/.
• 21: J. Esakov, D. P. Lopresti, and J. S. Sandberg. Classification and distribution of optical character recognition errors. In Proceedings of Document Recognition I (IS&T/SPIE Electronic Imaging), volume 2181, pages 204--216, San Jose, CA, February 1994.
• 22: Tin Kam Ho , Henry S. Baird, Large-Scale Simulation Studies in Image Pattern Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.19 n.10, p.1067-1079, October 1997 [doi>10.1109/34.625107]
• 23: Y. Ishitani. Model-based information extraction method tolerant of OCR errors for document images. Int. J. Comput. Proc. Oriental Lang., 15(2):165--186, 2002.
• 24: Yasuto Ishitani, Document Transformation System from Papers to XML Data Based on Pivot XML Document Method, Proceedings of the Seventh International Conference on Document Analysis and Recognition, p.250, August 03-06, 2003
• 25: Hongyan Jing , Kathleen R. Mckeown, Cut-and-paste text summarization, 2002
• 26: H. Jing, D. Lopresti, and C. Shih. Summarizing noisy documents. In Proceedings of the Symposium on Document Image Understanding Technology, pages 111--119, Greenbelt, MD, April 2003.
• 27: T. Kanungo, H. Baird, and R. Haralick. Estimation and validation of document degradation models. In Proc. 4th Annual Symposium on Document Analysis and Information Retrieval, Las Vegas, NV, April 1995.
• 28: G. Kopec. An em algorithm for character template estimation. Submitted March 1997; returned for revision, but not revised due to the author's death; available from PARC by request.
• 29: Steve Lawrence , C. Lee Giles , Kurt D. Bollacker, Autonomous citation matching, Proceedings of the third annual conference on Autonomous Agents, p.392-393, April 1999, Seattle, Washington, United States [doi>10.1145/301136.301255]
• 30: Steve Lawrence , C. Lee Giles , Kurt Bollacker, Digital Libraries and Autonomous Citation Indexing, Computer, v.32 n.6, p.67-71, June 1999 [doi>10.1109/2.769447]
• 31: Dan Lopresti, Robust Retrieval of Noisy Text, Proceedings of the 3rd International Forum on Research and Technology Advances in Digital Libraries, p.76, May 13-15, 1996
• 32: D. Lopresti and A. L. Spitz. Comparing the utility of optical character recognition and character shape coding in duplicate document detection. In Proceedings of the Fourth IAPR International Workshop on Document Analysis Systems, pages 439--450, Rio de Janeiro, Brazil, December 2000.
• 33: D. Lopresti and J. Zhou. Retrieval strategies for noisy text. In Proceedings of the Fifth Annual Symposium on Document Analysis and Information Retrieval, pages 255--269, Las Vegas, NV, April 1996.
• 34: Daniel P. Lopresti, A Comparison of Text-Based Methods for Detecting Duplication in Scanned Document Databases, Information Retrieval, v.4 n.2, p.153-173, July 2001 [doi>10.1023/A:1011471129047]
• 35: M. McCord. English Slot Grammar. IBM, 1990.
• 36: P. Metzger. Private communication, April 2004.
• 37: T. P. Minka, D. S. Bloomberg, and K. Popat. Document image decoding using iterated complete path heuristic. In Proceedings of IS&T/SPIE Electronic Imaging 2001: Document Recognition and Retrieval VIII, San Jose, CA, January 2001.
• 38: Open Source Technology Group, Inc. Slashdot home page. http://slashdot.org/, 2004.
• 39: David D. Palmer , Marti A. Hearst, Adaptive multilingual sentence boundary disambiguation, Computational Linguistics, v.23 n.2, p.241-267, June 1997
• 40: K. Popat. Decoding of text lines in grayscale document images. In Proceedings of the 2001 International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2001), Salt Lake City, Utah, May 2001. IEEE. To appear.
• 41: K. Popat, D. Bloomberg, and D. Greene. Adding linguistic constraints to document image decoding. In Proc., 4th International Workshop on Document Analysis Systems, Rio de Janeiro, Brazil, December 2000. International Association of Pattern Recognition.
• 42: K. Popat, D. Greene, J. Romberg, and D. S. Bloomberg. Adding linguistic constraints to document image decoding: Comparing the iterated complete path and stack algorithms. In Proceedings of IS&T/SPIE Electronic Imaging 2001: Document Recognition and Retrieval VIII, San Jose, CA, January 2001.
• 43: Toni M. Rath , R. Manmatha, Features for Word Spotting in Historical Manuscripts, Proceedings of the Seventh International Conference on Document Analysis and Recognition, p.218, August 03-06, 2003
• 44: Jeffrey C. Reynar , Adwait Ratnaparkhi, A maximum entropy approach to identifying sentence boundaries, Proceedings of the fifth conference on Applied natural language processing, p.16-19, March 31-April 03, 1997, Washington, DC [doi>10.3115/974557.974561]
• 45: Michael D. Riley, Some applications of tree-based modelling to speech and language, Proceedings of the workshop on Speech and Natural Language, October 15-18, 1989, Cape Cod, Massachusetts [doi>10.3115/1075434.1075492]
• 46: Prateek Sarkar , George Nagy, Style consistency in pattern fields, 2000
• 47: Prateek Sarkar , Henry S. Baird , Xiaohu Zhang, Training on Severely Degraded Text-Line Images, Proceedings of the Seventh International Conference on Document Analysis and Recognition, p.38, August 03-06, 2003
• 48: John H. Shamilian , Henry S. Baird , Thomas L. Wood, A retargetable table reader, Proceedings of the 4th International Conference on Document Analysis and Recognition, p.158-163, August 18-20, 1997
• 49: Kazem Taghva , Julie Borsack , Allen Condit, Effects of OCR errors on ranking and feedback using the vector space model, Information Processing and Management: an International Journal, v.32 n.3, p.317-327, May 1996 [doi>10.1016/0306-4573(95)00058-5]
• 50: Kazem Taghva , Julie Borsack , Allen Condit, Evaluation of model-based retrieval effectiveness with OCR text, ACM Transactions on Information Systems (TOIS), v.14 n.1, p.64-93, Jan. 1996 [doi>10.1145/214174.214180]
• 51: R. Veltkamp and M. Tanase. Content-based image retrieval systems: A survey. Technical Report UU-CS-2000-34, Dept. of Computing Science, Utrecht University, Oct. 2000. http://citeseer.ist.psu.edu/veltkamp00contentbased.html.
• 52: Tianhao Wu , William M. Pottenger, A semi-supervised active learning algorithm for information extraction from textual data: Research Articles, Journal of the American Society for Information Science and Technology, v.56 n.3, p.258-271, February 2005 [doi>10.1002/asi.v56:3]
• 53: Atsuo Yoshitaka , Tadao Ichikawa, A Survey on Content-Based Retrieval for Multimedia Databases, IEEE Transactions on Knowledge and Data Engineering, v.11 n.1, p.81-93, January 1999 [doi>10.1109/69.755617]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.7 DOCUMENT AND TEXT PROCESSING
      I.7.5 Document Capture

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.6 Library Automation

General Terms:
Algorithms, Design, Experimentation, Management

Keywords:
OCR error management, document analysis, information retrieval