• 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 D : µ¥ÀÌŸº£À̽º

Á¤º¸°úÇÐȸ ³í¹®Áö D : µ¥ÀÌŸº£À̽º

Current Result Document : 7 / 8

ÇѱÛÁ¦¸ñ(Korean Title) À§¼º¿µ»ó °Ë»ö¿¡¼­ »ç¿ëÀÚ °ü½É¿µ¿ªÀ» ÀÌ¿ëÇÑ ÀûÇÕ¼º Çǵå¹é
¿µ¹®Á¦¸ñ(English Title) Relevance Feedback using Region-of-interest in Retrieval of Satellite Images
ÀúÀÚ(Author) ±è¼ºÁø   Á¤Áø¿Ï   À̼®·æ   ±è´öȯ   Sung-Jin Kim   Chin-Wan Chung   Seok-Lyong Lee   Deok-Hwan Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 36 NO. 06 PP. 0434 ~ 0445 (2009. 12)
Çѱ۳»¿ë
(Korean Abstract)
³»¿ë ±â¹Ý ¿µ»ó °Ë»ö(content based image retrieval)Àº ¿µ»ó ÀÚüÀÇ Á¤º¸¸¦ ÀÌ¿ëÇÏ¿© À¯»ç ¿µ»óÀ» °Ë»öÇÏ´Â ±â¹ýÀÌ´Ù. ÇÏÁö¸¸ ¸ÖƼ¹Ìµð¾î µ¥ÀÌÅÍ´Â ÅؽºÆ® µ¥ÀÌÅÍ¿Í ´Þ¸® ¾òÀ» ¼ö ÀÖ´Â µ¥ÀÌÅÍ°¡ Á¤È®ÇÏÁö ¾Ê°í ¶ÇÇÑ ½Ã½ºÅÛ¿¡¼­ Ç¥ÇöµÇ´Â µ¥ÀÌÅÍÀÇ ÀúÂ÷¿ø(low-level)ÀÇ Ç¥Çö¹ý°ú »ç¿ëÀÚ°¡ ÀνÄÇÏ´Â °íÂ÷¿ø(high-level)ÀÇ °³³ä(concept)Àº »ó´çÇÑ Â÷À̸¦ ³ªÅ¸³»°Ô µÈ´Ù. Áï ½Ã½ºÅÛ »ó¿¡¼­ º¤Å͵é·Î Ç¥ÇöµÈ ¿µ»ó µ¥ÀÌÅ͵éÀÌ º¤ÅͽºÆäÀ̽º »ó¿¡¼­´Â °¡±õÁö¸¸ ½ÇÁ¦ »ç¿ëÀÚ´Â À¯»çÇÏÁö ¾Ê´Ù°í ÀνÄÇÏ´Â ¹®Á¦Á¡ÀÌ ¹ß»ýÇÑ´Ù. À̸¦ ÀǹÌÀû °£±Ø(semantic-gap) ¹®Á¦¶ó°í ºÎ¸¥´Ù. ÀÌ·± ÀǹÌÀû °£±Ø ¹®Á¦·Î ÀÎÇØ ¿µ»ó°Ë»ö °á°ú´Â ÁÁÁö ¾ÊÀº ¼º´ÉÀ» º¸ÀÌ°Ô µÈ´Ù. À̸¦ ÇØ°áÇϱâ À§ÇØ »ç¿ëÀÚÀÇ Çǵå¹é Á¤º¸¸¦ ÀÌ¿ëÇÏ¿© ÁúÀǸ¦ ¼öÁ¤ÇÏ´Â ÀûÇÕ¼º Çǵå¹é ±â¹ýÀÌ ³Î¸® »ç¿ëµÇ°í ÀÖ´Ù. ÇÏÁö¸¸ ±âÁ¸ÀÇ ÀûÇÕ¼º Çǵå¹éÀº »ç¿ëÀÚÀÇ °ü½É¿µ¿ª(region-of-interest, ÀÌÇÏ ROI)¸¦ °í·ÁÇÏÁö ¾Ê¾Æ ÀûÇÕÇÑ(relevant) ¿µ¿ªÀÇ ¸ðµç ¿µ¿ªµéÀÌ »õ·Î¿î ÁúÀÇ Á¡À» °è»êÇÏ´Â °úÁ¤¿¡¼­ »ç¿ëµÈ´Ù. ½Ã½ºÅÛÀº ±× ½º½º·Î »ç¿ëÀÚ °ü½É¿µ¿ªÀ» ¾ËÁö ¸øÇϱ⠶§¹®¿¡ ÀûÇÕ¼º Çǵå¹éÀ» ¿µ»ó¼öÁØ(image-level)À¸·Î ÁøÇàÇϱ⠶§¹®ÀÌ´Ù. ÀÌ ³í¹®¿¡¼­´Â º¹ÀâÇÑ À§¼º¿µ»ó ¿µ¿ª °Ë»ö¿¡¼­ °ü½É¿µ¿ªÀ» »ç¿ëÀÚ°¡ Á÷Á¢ ¼±ÅÃÇϵµ·Ï À¯µµÇÏ¿© ´õ¿í Á¤È®ÇÑ ÁúÀÇ Á¡À» °è»êÇÏ¿© Á¤È®µµ¸¦ ³ôÀÌ´Â »ç¿ëÀÚ °ü½É¿µ¿ª ÀûÇÕ¼º Çǵå¹é ¹æ¹ýÀ» Á¦½ÃÇÑ´Ù. ¶ÇÇÑ »ç¿ëÀÚ°¡ ¼±ÅÃÇÏÁö ¾ÊÀº ºÎÁ¤È®ÇÑ ¿µ»ó Á¤º¸¸¦ ÀÌ¿ëÇÏ¿© Á¤È®µµ¸¦ Çâ»ó½ÃÅ°´Â ÇÁ·ç´× ±â¹ýµµ ÇÔ²² Á¦½ÃÇÑ´Ù. ½ÇÇèÀ» ÅëÇÏ¿© »ç¿ëÀÚ °ü½É¿µ¿ª ÀûÇÕ¼º Çǵå¹éÀÇ ¿ì¼ö¼º°ú ÇÔ²² Á¦¾ÈÇÑ ÇÁ·ç´× ±â¹ýÀÇ È¿À²¼ºµµ ÇÔ²² º¸¿©ÁØ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Content-based image retrieval(CBIR) is the retrieval technique which uses the contents of images. However, in contrast to text data, multimedia data are ambiguous and there is a big difference between system's low-level representation and human's high-level concept. So it doesn't always mean that near points in the vector space are similar to user. We call this the semantic-gap problem. Due to this problem, performance of image retrieval is not good. To solve this problem, the relevance feedback(RF) which uses user's feedback information is used. But existing RF doesn't consider user's region-of-interest(ROI), and therefore, irrelevant regions are used in computing new query points. Because the system doesn't know user's ROI, RF is proceeded in the image-level. We propose a new ROI RF method which guides a user to select ROI from relevant images for the retrieval of complex satellite image, and this improves the accuracy of the image retrieval by computing more accurate query points in this paper. Also we propose a pruning technique which improves the accuracy of the image retrieval by using images not selected by the user in this paper. Experiments show the efficiency of the proposed ROI RF and the pruning technique.
Å°¿öµå(Keyword) »ç¿ëÀÚ °ü½É¿µ¿ª ÀûÇÕ¼º Çǵå¹é   ÀûÇÕ¼º Çǵå¹é   »ç¿ëÀÚ °ü½É¿µ¿ª   ³»¿ë±â¹Ý ¿µ»ó°Ë»ö   ¿µ¿ª±â¹Ý ¿µ»ó°Ë»ö   À§¼º¿µ»ó   CBIR   RBIR   relevance feedback   region-of-interest relevance feedback   satellite image  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå