CALL FOR PAPERS DOCUMENT RECOGNITION AND RETRIEVAL VII Part of IS&T/SPIE's Electronic Imaging 2000 San Jose, CA January 26-27, 2000 http://www.spie.org/web/meetings/calls/pw00/confs/ei18.html Conference Chairs: Daniel P. Lopresti, Lucent Technologies/Bell Labs.; Jiangying Zhou, Summus, Ltd. Program Committee: Francine R. Chen, Xerox Palo Alto Research Ctr.; David S. Doermann, Univ. of Maryland/College Park; Jonathan J. Hull, Ricoh California Research Ctr.; Paul Kantor, Rutgers University; Jan Pedersen, Infoseek; Larry Spitz, Document Recognition Technologies, Inc.; Kazem Taghva, Univ. of Nevada/Las Vegas; Ellen Voorhees, National Institute of Standards and Technology The fields of document recognition and retrieval have grown rapidly in recent years. This growth has been fueled by increasing accuracy rates for omnifont and handprint optical character recognition (OCR), decreasing costs for the computational power needed to run such sophisticated algorithms, and the emergence of new application areas such as the World Wide Web (WWW) and digital libraries. The use of OCR is spreading from restricted, high-volume domains to more general tasks, including the processing of noisy "real-world" documents, photocopies, faxes, and microfiches. Beyond OCR, document recognition includes the recovery of a document's logical structure and format. This encompasses decomposing a document into its various basic components (paragraphs, figures, tables, etc.), tagging these units, and then determining a higher-level structure for the document as a whole. The analysis of these entities may include attempting to understand the structure of tables and equations, or the conversion of line drawings from raster to vector format. The synergy between document retrieval and document recognition is a key theme of this conference, since retrieval plays a crucial role as the driving application for much current research in document recognition, as can be seen in the WWW and digital libraries. This includes access to scanned text documents as well as direct search over graphical elements and other multi-media search methods. Papers are solicited in the following areas: Recognition: - algorithms and systems for machine-printed and handwritten character and word recognition, especially for degraded documents (e.g., faxes) - character segmentation techniques - segmentation-free recognition - identification and analysis of tables and equations - page segmentation, including text and graphics separation, hierarchical decomposition of documents, and segmentation of halftones and line-art, particularly for noisy and complex documents - logical structure analysis - raster-to-vector conversion of line-art, maps, and technical drawings - filtering and enhancement techniques for document images - document image compression - extraction of information from compressed images - document degradation models - document recognition and the WWW - applications of recognition technologies to the building of digital libraries. Retrieval: - impact of recognition accuracy on retrieval effectiveness - keyword spotting in document images - recovery and use of logical structure for retrieval - use of metadata in retrieval - relevance feedback techniques for document retrieval - multi-lingual retrieval - document image categorization - approximate string matching algorithms for OCR-generated text - non-textual retrieval methods - image and multimedia search - benchmarking and evaluation issues. Important dates: Submissions due: June 14, 1999 Notification of acceptance via WWW: September 27, 1999 Notification of acceptance via postal mail: October 15, 1999 Camera-ready manuscripts due: November 1, 1999 Submissions to Document Recognition and Retrieval VII should be extended abstracts (6 pages / 2,500 words maximum). While June 14, 1999 is the official due date, late submissions may be permitted depending on the program. For more information and submission instructions, please see the Electronic Imaging 2000 Web site at: http://www.spie.org/info/ei.