Prateek Sarkar
ABSTRACT
Digital Libraries have many forms -- institutional libraries for information dissemination, document repositories for record-keeping, and personal digital libraries for organizing personal thoughts, knowledge, and course of action. Digital image content (scanned or otherwise) is a substantial component of all of these libraries. Processing and analyzing these images include tasks such as document layout understanding, character recognition, functional role labeling, image enhancement, indexing, organizing, restructuring, summarizing, cross linking, redaction, privacy management, and distribution.
At the Palo Alto Research Center, we conduct research on several aspects of document analysis for Digital Libraries ranging from raw image transformations to linguistic analysis to interactive sensemaking tools. I shall describe a few recent research activities in the realm of document image analysis or their use in digital libraries.
- List of digital library projects. http://en.wikipedia.org/wiki/List_of_digital_library_projects.Google Scholar
- Steven C. Bagley and Gary E. Kopec. Editing images of text. Communications of the ACM, 37(2):63--72, December 1994. Google ScholarDigital Library
- Henry S. Baird. Document image defect models. In H. Bunke H. S. Baird and K. Yamamoto, editors, Structured Document Image Analysis, pages 546--556. Springer-Verlag, New York, 1992.Google ScholarCross Ref
- Thomas M. Breuel, William C. Janssen, Kris Popat, and Henry S. Baird. Paper to PDA. In ICPR '02: Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1, page 10476, Washington, DC, USA, 2002. IEEE Computer Society. Google ScholarDigital Library
- Jindong Chen and Yizhou Wang. Exploiting Fisher kernels in decoding severely noisy document images. Personal communication, Palo Alto Research Center, 2006.Google Scholar
- Darrin L. Dimmick, Michael D. Garris, and Charles L. Wilson. Structured Forms Database. Technical Report Technical Report Special Database 2, SFRS, National Institutte of Standards and Technology, December 1991.Google Scholar
- Michael D. Garris and Darrin L. Dimmick. Form design for high accuracy Optical Character Recognition. IEEE Trans. PAMI, 18(6):653--656, 1996. Google ScholarDigital Library
- A. D. Holub, M. Welling, and P. Perona. Combining generative models and Fisher kernels for object recognition. In Proceedings of the International Conference on Computer Vision (ICCV), 2005. Google ScholarDigital Library
- T. S. Jaakkola and D. Haussler. Exploiting generative models in discriminative classifiers. In Advances in Neural Information Processing Systems 10, 1998. Google ScholarDigital Library
- William C. Janssen. Collaborative extensions for the UpLib system. In JCDL 2004: Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries, pages 239--240, June 2004. Google ScholarDigital Library
- William C. Janssen. Document icons and page thumbnails: Issues in construction of document thumbnails for page-image digital libraries. In ECDL 2004: Proceedings of the Eighth European Conference on Digital Libraries, pages 111--121, 2004.Google ScholarCross Ref
- William C. Janssen and Kris Popat. UpLib: A universal personal digital library system. In DocEng 2003: Proceedings of the ACM symposium on Document Engineering, pages 234--242. ACM Press, November 2003. Google Scholar
- E. T. Jaynes. Probability Theory: The Logic of Science. Cambridge University Press, 2003.Google Scholar
- G. Kopec and P. Chou. Document image decoding using Markov source models. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-16:602--617, June 1994. Google ScholarDigital Library
- Gary E. Kopec. Multilevel character templates for document image decoding. In L. Vincent and J. Hull, editors, Document Recognition IV: Proc. SPIE, 1997.Google ScholarCross Ref
- Gary E. Kopec and Anthony C. Kam. Separable source models for Document Image Decoding. In Luc M. Vincent and Henry S. Baird, editors, Proceedings of the International Society for Optical Engineering (SPIE): Document Recognition II, pages 84--97, San Jose, CA, 1995.Google Scholar
- G. Nagy, M. Krishnamoorthy, S. Seth, and M. Viswanathan. Syntactic segmentation and labeling of digitized pages from technical journals. IEEE Trans. PAMI, 15(7):737--747, 1993. Google ScholarDigital Library
- George Nagy and Prateek Sarkar. Document style census for OCR. In Proceedings of the First International Workshop on Document Image Analysis for Libraries, pages 134--147, Palo Alto, California, January 2004. Google ScholarDigital Library
- Tomohiro Nakai, Koichi Kise, and Masakazu Iwamura. Use of affine invariants in locally likely arrangement hashing for camera-based document image retrieval. In Proceedings of the 7th IAPR Workshop on Document Analysis Systems, Nelson, New Zealand, 2006. Google ScholarDigital Library
- Toni M. Rath, R. Manmatha, and Victor Lavrenko. A search engine for historical manuscript images. In SIGIR '04: Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval, pages 369--376, New York, NY, USA, 2004. ACM Press. Google ScholarDigital Library
- P. Sarkar and H. S. Baird. Decoder banks: Versatility, automation, and high accuracy without supervised training. In Proceedings of the 17th International Conference on Pattern Recognition, pages 646--649, Cambridge, U.K., 2004. Google ScholarDigital Library
- P. Sarkar and G. Nagy. Style consistent classification of isogenous patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(1):88--98, January 2005. Google ScholarDigital Library
- Prateek Sarkar. An iterative algorithm for optimal style conscious field classification. In Proceedings of the 16th International Conference on Pattern Recognition, pages 243--246, Quebec City, Canada, 2002. Google ScholarDigital Library
- Prateek Sarkar. Image classification: Classifying distributions of visual features. In Proceedings of the 18th International Conference on Pattern Recognition, Hong Kong, 2006. Google ScholarDigital Library
- Prateek Sarkar, Henry S. Baird, and John Henderson. Triage of OCR output using 'confidence' scores. In Proceedings of SPIE/IS&T 2002 Document Recognition & Retrieval IX Conf. (DR&R IX), San Jose, California, USA, January 20--25 2002.Google Scholar
- Prateek Sarkar, Henry S. Baird, and Xiaohu Zhang. Training on severely degraded text-line images. In Proceedings of the Seventh ICDAR, pages 38--43, Edinburgh, Scotland, August 2003. Google ScholarDigital Library
- Prateek Sarkar and Eric Saund. Perceptual organization in semantic role labeling. In Proceedings of 2005 Symposium on Document Image Understanding Technology, College Park, Maryland, USA, November 2005.Google Scholar
- Eric Saund. Logic and MRF circuitry for labeling occluding and thinline visual contours. In Advances in Neural Information Processing Systems 18, 2005.Google Scholar
- Eric Saund, David Fleet, Daniel Larner, and James Mahoney. Perceptually-supported image editing of text and graphics. ACM Trans. Graph., 23(3):728--728, 2004. Google ScholarDigital Library
- Michael Shilman, Percy Liang, and Paul Viola. Learning non-generative grammatical models for document analysis. In ICCV '05: Proceedings of the Tenth IEEE International Conference on Computer Vision, pages 962--969, Washington, DC, USA, 2005. IEEE Computer Society. Google ScholarDigital Library
- Kazem Taghva, Julie Borsack, Allen Condit, and Srinivas Erva. The effects of noisy data on text retrieval. Journal of the American Society for Information Science, 45(1):50--58, 1994. Google ScholarDigital Library
- S. Veeramachaneni and G. Nagy. Style context with second order statistics. IEEE Trans. PAMI, 27(1):14--22, January 2005. Google ScholarDigital Library
- Paul A. Viola and Michael J. Jones. Rapid object detection using a boosted cascade of simple features. In Proc. CVPR, pages 511--518, 2001.Google Scholar
Index Terms
- Document image analysis for digital libraries
Recommendations
The UpLib personal digital library system
JCDL '05: Proceedings of the 5th ACM/IEEE-CS joint conference on Digital librariesWe demonstrate the operation of UpLib, a visually-oriented personal digital library system.
Digital Libraries and Document Image Analysis
ICDAR '03: Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1The rapid growth of digital libraries (DLs) worldwideposes many new challenges for document image analysis(DIA) research and development. DLs promise to offermore people access to larger document collections, and atfar greater speed, than physical ...
Comments