ICSC'95 - TUTORIAL NOTICE ICSC '95 - Third International Computer Science Conference: Image Analysis Applications and Computer Graphics Nikko Hotel, HONG KONG, 11-13 December, 1995 Organised and Sponsored by the IEEE Hong Kong Section, Computer Chapter. In cooperation with IEEE Computer Society, International Association for Pattern Recognition (IAPR), ACM (HK). TUTORIAL Title: Document Image Analysis Techniques: An Overview Prof. Rangachar Kasturi, Professor of computer science and engineering, Pennsylvania State University, U.S.A. Objectives: This course will enable the participant to: 1. learn the basic principles of document image analysis methods for optical character and graphics recognition 2. become familiar with the capabilities and limitations of automatic document image processing techniques 3. understand the relationships among various system components to facilitate systematic evaluation of document image analysis systems 4. know the state-of-the-art in vectorizers for converting engineering drawings and maps. Contents: Document image analysis systems automatically extract formation from scanned images of paper-based documents. Such systems recognize characters, symbols, and lines, establish spatial and semantic relationships, and determine the overall structure. Their output facilitates efficient storage, retrieval, and editing of the documents' contents. The general procedure and sequence of methods used in document image analysis are: data captured preprocessing, segmentation and layout analysis, feature extraction and matching, text and graphics recognition and interpretation. An overview of each of these topics will be presented in this course. Applications of the techniques discussed include automatic processing of business letters and forms, conversion of engineering drawings and maps, input technical manuals and journals for creating digital libraries, automatic handling of mail pieces, and recognition of musical notes, shorthand scripts, etc. However, specific commercial systems will not be discussed. Intended Audience: Anyone who must deal with large volumes of paper-based documents and their conversion into computer readable form for efficient storage, retrieval, and manipulation. The course would help both computer engineers who design document analysis systems and managers who specify and evaluate such systems. Some familiarity with basic principles of digital image processing is helpful. About the Instructor: Rangachar Kasturi is a professor of computer science and engineering at the Pennsylvania State University. He received his Ph.D. degree in electrical engineering from Texas Tech University in 1982. Dr. Kasturi has directed many research projects in the document image analysis area. He is a coauthor of the text, Machine Vision, McGraw-Hill, 1995, and co-editor of the books, Document Image Analysis, Computer Vision: Principles and Applications, and Image Analysis Applications. He is the editor-in-chief of the IEEE Transactions on Pattern Analysis and Machine Intelligence. Text: L. O'Gorman and R. Kasturi, Document Image Analysis Techniques, IEEE Computer Society Press, 1994 (included in the tutorial fee) Duration: Half day. Venue: Hotel Nikko Date: Wednesday 13 December 1995 Time: 1:30pm - 5:00pm Fee: HK$800 for member* ; HK$900 for others; The text book is included * Membership list: IEEE, ACM, IAPR, HKIE, HKCS, HKSMIC. TUTORIAL REGISTRATION FORM AND INQUIRIES Mail to: Joseph Ng, ICSC'95 Registration, Computing Studies Department, Hong Kong Baptist University, 224, Waterloo Road, Kowloon, Hong Kong. Phone: (+852) 2339-7864, Fax: (+852) 2339-7892 E-mail: icsc95@comp.hkbu.edu.hk Name: _____________________________________________________________ (Surname) (First Name) Affiliation: ______________________________________________________ Address: __________________________________________________________ Phone: __________________________ Fax: ____________________________ Email: ____________________________________________________________ Membership and No: ________________________________________________ *List of Membership: IEEE, ACM, IAPR, HKIE, HKCS, HKSMIC. Payment Table for Tutorial: Category Quantity Fee Amount Members Non-members Total NOTE: To save on postage, receipts will be given out at the conference. Payment can be made by money order, or bank draft. Please make money orders payable, in Hong Kong currency, to ICSC'95.