An attempt to segmentation of semiographic characters of printed Japanese script for recognition by GedNLC grammars

• Autorzy: Iwanowski M.
• Konferencja: Conference on Computer Graphics and Image Processing, GKPO' 98 (5 ; 18-22.05.1998 ; Borki, Poland)
• Języki publikacji: EN

Abstrakty

EN

In the paper three methods of an automated segmentation of kanji graphs are described. The first two of them yield divisions at the levelclose to the traditional components of kanji graphs. But a too large number of kanji graphs which do not lend themselves to devision makes one assign to these methods an auxiliary role in the system under construction. The third method divides a kanji graph into segments which approximately correspond to fragments of traditional strokes. Hance almost every kanji graph lends itself to division into segments, and the description thus obtained can be used for their recognition by GedNLC grammars (R. Tadeusiewicz, M. Flasiński, [7]).

Słowa kluczowe

EN

Kanji graph; segmentation; measure of distance

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 1998
• Tom: Vol. 7, No. 1/2
• Strony: 355--365
• Opis fizyczny: Bibliogr. 7 poz.

Twórcy

autor

Iwanowski M.

• Departamwnt of Information and Book Studies, University of Warsaw, 00-046 Warszawa, ul. Nowy Świat 69, Poland