Showing papers on "Document processing published in 1980"

Automatic recognition of handprinted characters—The state of the art

Abstract: Based on a study of the extensive literature in handprint recognition, this paper presents a survey in this challenging field. Recognition algorithms, data bases, character models, and handprint standards are examined. Achievements in the recognition of handprinted numerals, alphanumerics, Fortran, and Katakana characters are analyzed and compared. Data quality and constraints, as well as human and machine factors are also described. Characteristics, problems, and actual results on on-line recognition of handprinted characters for different applications are discussed. New emphases and directions are suggested.

Control system for document data

Abstract: PURPOSE:To reduce the time from the formation of a program to registration, by making easy the check of data through the display of data read-in according to the document read-in format on a display screen with the screen format CONSTITUTION:A screen design 21 of the data in a document 20 is made to form a screen difinition sheet 22 describing the screen format and the field control sheet 23 describing document read-in format, and the sheet describing them is input to an optical character reader OCR24 for read-in and it is edited and stored in an auxiliary memory unit 25 Next, in case of actual document processing, the format corresponding to the document 20 processed from the auxiliary memory unit 25 is read-out and read-in to the OCR24 The data read-in is displayed on a display unit 26 with the screen format according to the document read-in format

Recognition of handprinted characters for automated cartography A progress report

Abstract: A research program for developing handwritten character recognition techniques is reported. The generation of cartographic/hydrographic manuscripts is overviewed. The performance of hardware/software systems is discussed, along with future research problem areas and planned approaches.

Document processing in the automated office: implications for mis research and education

Abstract: Document processing is an integral part of the automated office. Because document-based information systems are composed largely of unstructured text as opposed to structured data, the techniques which have been successfully applied to the design of current database systems are not adequate for the design of office information systems. The paper identifies issues related to the storage and retrieval of office documents, and the management of information in the automated office. Strategies for broadening MIS research and education to address these issues are suggested. INTRODUCTION More recently, office automation has been defined by the EDP Analyzer as a "new Document and text processing are structured way of handling business integral parts of the automated office. documents and person-to-person The purpose of this paper is to identify communication." The scope of the research issues related to document automated office includes formal and· processing in the office, and to suggest informal correspondence and communication, ways to broaden MIS curricula to address storage and retrieval of office documents, these issues. and links to various corporate files and outside information services. (14)· At the Office automation has only recently organizational level, the automated office become an important MIS issue. The provides a way to support the corporate initial conceptualization of such systems, memory, which Morgan and Root described as however, precedes the widespread use of the totality of information sources such computers for business data processing. as those mentioned above, for all the For example, the following quotation by individuals in the organization. The Vannever Bush appeared in the Atlantic corporate memory is viewed as an active Monthly in 1945: system which both responds to user requests as well as initiating Consider a future device for interactions with organizational individual use which is sort of a members.(16) At the individual level, the mechanized private file and library. automated office may be viewed as a It needs a name, and, to coin one at terminal-based system designed to provide random, "memex" will do. A memex is decision-makers with access to both a device in which an individual intr a-organizationa 1 a n d stores all his books, records, and extra-organizational information. communications, and which is mechanized so that it may be While documents are central to the consulted with exceeding speed and automated office, document-based flexibility. It is an enlarged information systems have largely been intimate supplement to his neglected in the MIS literature.(20) memory. (3) Rather, the majority of current management information systems consist of structured In 1958, Luhn described the design for a databases containing largely internal, business intelligence system which "will often numerical data. The same techniques utilize data-processing machines for which have been successfully applied to auto-abstracting and auto-encoding of the design of these existing information documents and for creating interest systems are not adequate for the design of profiles for each of the 'action points' effective information systems to support in an organization. Both incoming and the automated office, as documents consist internally generated documents are largely of unstructured text. The primary. automatically abstracted, characterized by issue addressed by this paper, then, is a word pattern, and automatically sent to the storage and retrieval of an appropriate action points."(11) organization's office documents. A