• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document : 2 / 747 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) CKFont2: ÇÑ±Û ±¸¼º¿ä¼Ò¸¦ ÀÌ¿ëÇÑ °³¼±µÈ Ç»¼¦ ÇÑ±Û ÆùÆ® »ý¼º ¸ðµ¨
¿µ¹®Á¦¸ñ(English Title) CKFont2: An Improved Few-Shot Hangul Font Generation Model Based on Hangul Composability
ÀúÀÚ(Author) ¹ÚÀå°æ   Ammar Ul Hassan   ÃÖÀ翵   Jangkyoung Park   Ammar Ul Hassan   Jaeyoung Choi  
¿ø¹®¼ö·Ïó(Citation) VOL 11 NO. 11 PP. 0499 ~ 0508 (2022. 12)
Çѱ۳»¿ë
(Korean Abstract)
µö·¯´×À» ÀÌ¿ëÇÑ ÇÑ±Û »ý¼º ¸ðµ¨¿¡ ´ëÇÑ ¿¬±¸°¡ ¸¹ÀÌ ÁøÇàµÇ¾úÀ¸¸ç, ÃÖ±Ù¿¡´Â ÇÑ±Û 1¹úÀ» »ý¼ºÇϱâ À§ÇÏ¿© ÀԷµǴ ±ÛÀÚ ¼ö¸¦ ¾ó¸¶³ª ÃÖ¼ÒÈ­ÇÒ ¼ö ÀÖ´ÂÁö(Few-Shot Learning)¿¡ ´ëÇÏ¿© ¿¬±¸µÇ°í ÀÖ´Ù. º» ³í¹®Àº 28°³ ±ÛÀÚ¸¦ »ç¿ëÇÏ´Â CKFont (ÀÌÇÏ CKFont1) ¸ðµ¨À» ºÐ¼®ÇÏ°í °³¼±ÇÏ¿© 14°³ ±ÛÀÚ¸¸À» »ç¿ëÇÏ´Â CKFont2 ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. CKFont2 ¸ðµ¨Àº 28±ÛÀÚ·Î 51°³ ÇÑ±Û ±¸¼º¿ä¼Ò¸¦ ÃßÃâÇÏ¿© ¸ðµç ÇѱÛÀ» »ý¼ºÇÏ´Â CKFont1 ¸ðµ¨À», 24°³ÀÇ ±¸¼º¿ä¼Ò(ÀÚÀ½ 14°³¿Í ¸ðÀ½ 10°³)¸¦ Æ÷ÇÔÇÑ 14°³ÀÇ ±ÛÀÚ¸¸À» ÀÌ¿ëÇÏ¿© ¸ðµç ÇѱÛÀ» »ý¼ºÇÏ´Â ¸ðµ¨·Î ¼º´ÉÀ» °³¼±ÇÏ¿´À¸¸ç, ÀÌ´Â ÇöÀç ¾Ë·ÁÁø ¸ðµ¨·Î¼­´Â ÃÖ¼ÒÇÑÀÇ ±ÛÀÚ¸¦ »ç¿ëÇÑ´Ù. ÇѱÛÀÇ ±âº» ÀÚ/¸ðÀ½À¸·ÎºÎÅÍ ½ÖÀÚÀ½(5), º¹ÀÚÀ½(11)/º¹¸ðÀ½(11) µî 27°³¸¦ µö·¯´×À¸·Î ÇнÀÇÏ¿© »ý¼ºÇÏ°í, »ý¼ºµÈ 27°³ ±¸¼º¿ä¼Ò¸¦ 24°³ÀÇ ±âº» ÀÚ/¸ðÀ½°ú ÇÕÇÑ 51°³ ±¸¼º¿ä¼Ò·ÎºÎÅÍ ¸ðµç ÇѱÛÀ» ÀÚµ¿ »ý¼ºÇÑ´Ù. zi2zi, CKFont1, MX-Font ¸ðµ¨ »ý¼º °á°ú¿Í ºñ±³ ºÐ¼®ÇÏ¿© ¼º´ÉÀÇ ¿ì¼ö¼ºÀ» ÀÔÁõÇÏ¿´À¸¸ç, ±¸Á¶°¡ °£°áÇÏ°í ½Ã°£°ú ÀÚ¿øÀÌ Àý¾àµÇ´Â È¿À²ÀûÀÎ ¸ðµ¨·Î ÇÑÀÚ³ª ű¹¾î, ÀϺ»¾î¿¡µµ È®Àå Àû¿ëÀÌ °¡´ÉÇÏ´Ù.
¿µ¹®³»¿ë
(English Abstract)
A lot of research has been carried out on the Hangeul generation model using deep learning, and recently, research is being carried out how to minimize the number of characters input to generate one set of Hangul (Few-Shot Learning). In this paper, we propose a CKFont2 model using only 14 letters by analyzing and improving the CKFont (hereafter CKFont1) model using 28 letters. The CKFont2 model improves the performance of the CKFont1 model as a model that generates all Hangul using only 14 characters including 24 components (14 consonants and 10 vowels), where the CKFont1 model generates all Hangul by extracting 51 Hangul components from 28 characters. It uses the minimum number of characters for currently known models. From the basic consonants/vowels of Hangul, 27 components such as 5 double consonants, 11/11 compound consonants/vowels respectively are learned by deep learning and generated, and the generated 27 components are combined with 24 basic consonants/vowels. All Hangul characters are automatically generated from the combined 51 components. The superiority of the performance was verified by comparative analysis with results of the zi2zi, CKFont1, and MX-Font model. It is an efficient and effective model that has a simple structure and saves time and resources, and can be extended to Chinese, Thai, and Japanese.
Å°¿öµå(Keyword) µö·¯´×   Ç»¼¦ÇнÀ   Ãʼº/Áß¼º/Á¾¼º   CKFont   ÇÑ±Û 14±ÛÀÚ   Deep Learning   Few-Shot   Initial/Middle/Final Components   CKFont   Korean 14 Characters  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå