CALL FOR PAPERS DIAL 2006 2nd International Workshop on on Document Image Analysis for Libraries 27-28 April 2006 Lyon (France) The rapid spread of Digital Libraries (DL) across the world motivates research in computer vision and especially in Document Image Analysis (DIA). The DL and DIA research community share common objectives, namely to digitize paper documents and convert them into electronic formats which can be reserved, retrieved, consulted, shared, and reused. Without computer assistance, manual processing of the large quantities of available digitized documents would be expensive and time consuming. The DIA research community has developed many technologies applicable to digital libraries which are ripe to be collected, compared, and shared. DIAL'06 will bring together DL and DIA researchers, practitioners, and users who are interested in new technologies that assist the integration of digitized documents within DLs, so that, ideally, all documents that contribute to human knowledge can be easily accessed and queried by using Web based search engines. The workshop will cover all technical aspects of document image processing from digitization, image restoration, text recognition, and extraction of metadata from images, up to document encoding and specification of file formats for digitized documents. This workshop will also attempt to describe the state of the art, to identify urgent open problems in image analysis suited to DLs and to collect all available information on document digitization projects across the world. The workshop is open to researchers from both the DL and DIA communities on the following topics: Surveys : - Document Image Analysis (DIA) methods useful for Digital Libraries (DLs) - Technical reviews of digitization projects around the world - Critical surveys of the state of the art of DLs & DIA - Challenging open problems in the DL community requiring new DIA research strategies - End-user requirements for document images provided via DLs - Performance evaluation & cost of document image processing for DLs Methodologies : - Automatic quality control during document image capture, modeling of document image degradation, digital image restoration, etc - Document image enhancement (unwarping, deskewing, cropping, color & contrast improvement) - Text segmentation and/or recognition (OCR, keyword spotting, word retrieval or recognition, text-image alignment, etc) for printed or handwritten documents - Document layout segmentation and logical structure recognition for DL applications - Metadata extraction and recognition from digitized documents - Methodologies to improve accessibility and navigation within/among on- line digital libraries - Imaging & compression standards for document preservation, analysis, etc - Guaranteeing authenticity of document images; rights management - File formats & representations of document images - Methodologies for specific image content (tables, graphs, mathematics, multilingual documents, etc) - Style identification (typography of printed text, handwriting style recognition for manuscript authentication or authors identification^Ĺ) - Searching/querying, retrieval, summarizing/condensing of document images - Other topics related to the retrieval of document images Applications : - Historical document collections (medieval manuscripts, books of the Renaissance, author manuscripts, old newspapers or 'gazettes', archives, etc) - Documents from the world cultural heritage - Scientific, technical and educational documents for digital libraries - Other digitized documents used by digital libraries Deadlines for Regular Papers (up to 20 pages,refereed, archivally published, long presentation) Submission : December 20, 2005 Acceptance : January 10, 2006 Camera-ready copy : February 10, 2006 Deadlines for Abstracts of Remarks (1-5 pages, not refereed, unpublished, brief presentation) Submission : March 20, 2006 Contact : dial2006@liris.cnrs.fr Website : http://liris.cnrs.fr/dial2006/ Conference Chairs : Frank Le Bourgeois & Hubert Emptoz (France) LIRIS INSA de Lyon Program Committee Chair : Henry BAIRD (USA) Lehigh Univ. Frédéric BAPST (Switzerland) Ecole d'Ingenieurs, Fribourg Elisa H. BARNEY SMITH (USA) Boise State Univ. Sayeed CHOUDHURY (USA) Johns Hopkins Univ. Michael DROETTBOOM (USA) Johns Hopkins Univ. Richard FATEMAN (USA) Univ. of California at Berkeley Hiromichi FUJISAWA (Japan) Hitachi CRL Joël GARDES (France) France Telecom Venu GOVINDARAJU (USA) Univ. at Buffalo, NY Jonathan HULL (USA) Ricoh Innovations, Inc. Dolores IORIZZO (UK) Imperial College, London J. V. JAWAHAR (India) IIIT Hyderabad Koichi KISE (Japan) Osaka Prefecture Univ. Michael LESK (USA) Rutgers Univ. Xioafan LIN (USA) Hewlett-Packard Labs Daniel LOPRESTI (USA) Lehigh Univ. Simon LUCAS (UK) Univ. of Essex R. MANMATHA (USA) Univ. of Massachusetts, Amherst Umapada PAL (India) Indian Statistical Inst., Kolkata Toni RATH (USA) Google Alan SMEATON (Ireland) Dublin City Univ. Larry SPITZ (New Zealand) DocRec Technologies Ltd. Sargur SRIHARI (USA) Univ. at Buffalo, NY Chew Lim TAN (Singapore) National Univ. of Singapore