2024-03-29T09:56:39Z
https://nagoya.repo.nii.ac.jp/oai
oai:nagoya.repo.nii.ac.jp:00005331
2023-01-16T03:49:59Z
320:321:322
A stepwise recognition method of library cataloging cards on the basis of various kinds of knowledge
Watanabe, Toyohide
13580
Luo, Qin
13581
Yoshida, Yuuji
13582
Inagaki, Yasuyoshi
13583
It is one of the imporant issues to extract the meanigful data from library cataloging cards automatically and then construct them as a library database, because each library has accomodated a great deal of cataloging cards. The traditional methods based on the character recognition technique can be partly applied to this issue. However, these methods are not always successful for the cataloging cards, specified by different layout structures and various description rules. This paper proposes an experimental methodto extract and classify the data items automatically from cataloging cards.Our basic idea for the recognition strategy is to utilize various kinds of knowledge stepwisely on the basis of the generation/verification process of object hypotheses: in our approach, the knowledge such as layout information of card structures, relatonship information among cataloging items, and property imformation of data items is effectual.
journal article
IEEE
1991-03
application/pdf
Proceedings of the Tenth Annual International Phoenix Conference on Computers and Communications, 27-30 March 1991
821
827
http://hdl.handle.net/2237/6924
https://nagoya.repo.nii.ac.jp/record/5331/files/PCCC_91_821.pdf
eng
https://doi.org/10.1109/PCCC.1991.113900
Copyright © 1991 IEEE. Reprinted from (relevant publication info). This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of Nagoya University’s products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org.