• 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¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë

Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë

Current Result Document : 5 / 7

ÇѱÛÁ¦¸ñ(Korean Title) È¥µ¿±×·¡ÇÁ¸¦ ÀÌ¿ëÇÑ À¯»ç¹®ÀÚ½Ö ±¸ºÐ±â¿Í ÀνıâÀÇ ÅëÇÕ
¿µ¹®Á¦¸ñ(English Title) Integration of Pair-wise Discriminators and Recognizer using Confusion Graph
ÀúÀÚ(Author) Á¶Çý±Ù   ±èÀÎÁß   Heyguen Cho   In-Jung Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 39 NO. 06 PP. 0507 ~ 0514 (2012. 06)
Çѱ۳»¿ë
(Korean Abstract)
¹®ÀÚ ÀÎ½Ä ±â¼úÀº ¿©·¯ ºÐ¾ß¿¡ ³Î¸® ÀÀ¿ëµÇ°í ÀÖ´Ù. ±×·¯³ª, Çʱâ ÇÑ±Û ÀνĿ¡¼­´Â Áö±Ý±îÁö ¸¹Àº ¿¬±¸¿¡µµ ºÒ±¸ÇÏ°í ³ôÀº ¼º´ÉÀ» ¾òÁö ¸øÇÏ°í ÀÖ´Ù. Çʱâ ÇÑ±Û ÀνÄÀÇ ¾î·Á¿ò Áß Çϳª´Â À¯»ç ¹®ÀÚ°£ È¥µ¿ÀÌ´Ù. À̸¦ ±Øº¹Çϱâ À§ÇÏ¿© ´Ù¾çÇÑ À¯»ç¹®ÀÚ½Ö ±¸ºÐ ¹æ¹ýµéÀÌ Á¦¾ÈµÇ¾ú´Ù. À¯»ç¹®ÀÚ½Ö ±¸ºÐ±â´Â ƯÁ¤ È¥µ¿¹®ÀÚ½Ö °£ÀÇ Â÷ÀÌ¿¡ ÁýÁßÇÔÀ¸·Î½á ÇØ´ç ¹®ÀÚ½ÖÀ» Àü¹®ÀûÀ¸·Î ±¸ºÐÇÏ´Â µÎ Ŭ·¡½º Àü¿ë ÀνıâÀÌ´Ù. À¯»ç¹®ÀÚ½Ö ±¸ºÐ±â´Â À¯»ç¹®ÀÚ½ÖÀÇ ±¸ºÐ¿¡ È¿°úÀûÀÌ´Ù. ±×·¯³ª, µÎ °³ÀÇ Å¬·¡½º¸¸À» ±¸ºÐÇÒ ¼ö Àֱ⠶§¹®¿¡, ±âº» Àνıâ¿Í ÅëÇյǾî¾ß¸¸ ½Ç¿ëÀûÀÎ ½Ã½ºÅÛ¿¡ »ç¿ëµÉ ¼ö ÀÖ´Ù. Áö±Ý±îÁö À¯»ç¹®ÀÚ½Ö ±¸ºÐ±â¿Í ±âº» ÀνıâÀÇ ÅëÇÕ¿¡ ´ëÇؼ­´Â ¸¹Àº ¿¬±¸°¡ ÀÌ·ç¾îÁöÁö ¾Ê¾Ò´Ù. º» ³í¹®Àº ±âº» Àνıâ¿Í À¯»ç¹®ÀÚ½Ö ±¸ºÐ±â·ÎºÎÅÍ È¹µæµÈ ´Ù¾çÇÑ Á¤º¸¸¦ ü°èÀûÀ¸·Î È°¿ëÇÔÀ¸·Î½á À¯»ç¹®ÀÚµéÀÌ ¸¹ÀÌ Æ÷ÇÔµÈ ¾ð¾î¿¡ ´ëÇÑ ÀÎ½Ä ¼º´ÉÀ» ±Ø´ëÈ­ÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÏ´Â ¹æ¹ýÀº ¹®ÀÚ°£ È¥µ¿ È®·ü, ±âº» ÀÎ½Ä±â ¹× À¯»ç¹®ÀÚ½Ö ±¸ºÐ±âÀÇ ½Å·Úµµ¸¦ È¥µ¿±×·¡ÇÁ¿¡ ÀúÀåÇÑ ÈÄ À̸¦ È°¿ëÇØ ±âº» Àνıâ¿Í À¯»ç¹®ÀÚ½Ö ±¸ºÐ±âÀÇ °á°ú¸¦ ü°èÀûÀ¸·Î ÅëÇÕÇÔÀ¸·Î½á ÃÖÁ¾ ÀÎ½Ä °á°ú¸¦ ¼±ÅÃÇÑ´Ù. SERI95a ¹®ÀÚ ¿µ»óÀ¸·Î ½ÇÇèÇÑ °á°ú, ÀÎ½Ä ¹æ¹ý°ú À¯»ç¹®ÀÚ ±¸ºÐ ¹æ¹ýÀÇ º¯È­ ¾øÀ̵µ ÅëÇÕ ¹æ¹ýÀÇ °³¼±¸¸À» ÅëÇØ 8.26ÆÛ¼¾Æ®ÀÇ ¿À·ù°¨¼ÒÀ²À» ¾ò¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
Character recognition technology is widely used in many fields. However, researchers couldn't achieve high performance in handwritten Hangul recognition, in spite of many researches so far. One of major difficulties in handwritten Hangul recognition is confusion between similar characters. Various pair-wise discrimination methods were proposed to overcome this problem. A pair-wise discriminator is a two-class recognizer specialized for a particular confusing character pair by focusing on their difference. Pair-wise discriminators are effective to discriminative specific character pairs. However, because a discriminator can discriminate only a pair of classes, it needs to be integrated with a baseline recognizer to be used in a practical system. Until now, there were few researches on integration of pair-wise discriminators and baseline recognizer. This paper proposes a method to maximize overall recognition performance on a language containing lots of similar characters by systematically utilizing various information obtained by the baseline recognizer and pair-wise discriminators. The proposed method stores confusion probability between characters as well as the reliability of the baseline recognizer and pair-wise discriminators in a confusion graph. Then, it selects the final recognition result by systematically integrating outputs of the baseline recognizer and pair-wise discriminators using the confusion graph. In experiments on SERI95a data set, we achieved 8.26% of error reduction rate by only improving integration method, without any modification on recognition nor discrimination methods.
Å°¿öµå(Keyword) ¹®ÀÚ ÀνĠ  À¯»ç¹®ÀÚ½Ö ±¸ºÐ   È¥µ¿±×·¡ÇÁ   character recognition   pair-wise discrimination   confusion graph  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå