* * * FIRST CALL FOR PARTICIPATION * * * International Workshop on Performance Evaluation Issues in Multilingual OCR Sunday, September 19, 1999 (just before ICDAR'99) Bangalore, India WORKSHOP CHAIRS Tapas KANUNGO University of Maryland, College Park, MD USA Henry S. BAIRD Xerox PARC, Palo Alto, CA USA ORGANIZING COMMITTEE Badr AL-BADR King Abdulaziz City, Saudi Arabia Torsten CAESAR Siemens ElectroCom, Germany Bhabatosh CHANDA ISI Calcutta, India Doug COOPER Southeast Asian Software Research Center, Thailand Andreas DENGEL DFKI, Germany Steve DENNIS U. S. Government, USA Xiaoqing DING Tsinghua University, P.R. China David DOERMANN University of Maryland, USA Michel GILLOUX Service de Recherche Technique de la Poste, France Robert M. HARALICK University of Washington, USA Tin Kam HO Bell Laboratories, Lucent Technologies, USA Donna HARMAN National Institute for Standards & Technology, USA Jonathan HULL Ricoh CRC, USA Fumitaka KIMURA Mie University, Japan Hsi-Jian LEE National Chiao Tung University, R.O. China Seong-Whan LEE Korea University, Korea Tomohiko MORIOKA Japan Advanced Institute for Science & Tech., Japan S. P. MUDUR National Center for Software Technology, India Yasuaki NAKANO Shinshu University, Japan Kris POPAT Xerox PARC, USA Philip RESNIK University of Maryland, USA A. Lawrence SPITZ Document Recognition Technologies, USA Rohini SRIHARI CEDAR, SUNY Buffalo, USA Ching Y. SUEN Concordia University, Montreal, Canada Yuan Yan TANG Hong Kong Baptist University, China Vadim TERESCHENKO ABBYY Software House, Russia Jun TSUKUMO NEC, Kanagawa, Japan Toru WAKAHARA NTT Human Interface Laboratories, Japan TECHNICAL FOCUS This workshop will explore evaluation methodologies for multilingual OCR systems. By `multilingual' we mean to include systems that are capable of reading more than one language in the same document, as well as one-language-per-document systems that can be easily retargeted to new languages. We hope to bring together researchers from many countries to discuss these and related questions: -- What methodologies should be used to evaluate multilingual OCR systems? How do we compare accuracies across languages? -- What ground-truthed data sets are now available in various languages? What kind of datasets need to be collected? How is this to be achieved? Which organizations might be willing to support such an the effort? -- What multilingual OCR evaluation tools and error visualization tools are available or should be developed? -- What OCR evaluation methods and metrics will be useful for OCR-based machine translation and cross-language information retrieval? -- What are the most pressing open research problems, promising dissertation topics, etc? WORKSHOP FORMAT This will be a one-day workshop for a maximum of 70 participants. Each participant will submit an extended abstract which will be distributed at the Workshop. All participants are expected to contribute to the discussions. At the outset of the workshop, three volunteers will present brief, informal summaries of the i) methodologies, ii) corpora, and iii) tools mentioned in the submitted abstracts. Then we will split up into three working groups, focused on these topics, and proceed to discuss key issues, attempt to resolve questions, compile lists of resources, and draw up recommendations. Finally, in a plenary session, representatives of each group will present their recommendations and invite general discussion. There will be several opportunities for informal discussion and socializing. After the workshop, the organizing committee will compile a Workshop Summary, based on the working group notes, and make it available on the Web. It is hoped that the workshop will stimulate cooperative follow-on activities that will accelerate the pace of research in multilingual document image analysis. EXTENDED ABSTRACT SUBMISSION Each potential participant or group of participants should submit an extended abstract, electronically via E-mail (in plain ASCII), no later than March 30, 1999 to: Tapas Kanungo Center for Automation Research University of Maryland College Park, MD 20742 E-mail: mlocr@cfar.umd.edu The abstract should include the name, address, telephone, fax, and email address of the author(s). It should ordinarily be limited to six printed pages including references (no figures, please). Longer submissions may be admitted in special cases, e.g. for catalogues of resources. Accepted abstracts will be distributed at the Workshop and posted on the Workshop website. WORKSHOP WEBSITE http://www.cfar.umd.edu/~kanungo/workshop/mlocr.html