NDSL 9 Link page¿¡¼­ [¿ø¹®º¸±â] ¹öÆ°À» Ŭ¸¯Çϼ¼¿ä.

[±¹³»³í¹®]

º» ³í¹®¿¡¼­´Â Ŭ¸³¾ÆÆ® À̹ÌÁö¿¡¼­ ¸ð¾ç Á¤º¸¸¦ ÃßÃâÇÏ°í ÀÌ Á¤º¸¸¦ ÀÌ¿ëÇÏ¿© Ŭ¸³¾ÆÆ® À̹ÌÁöÀÇ À¯»çµµ¸¦ ÃøÁ¤ÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÏ¿´´Ù. º» ³í¹®¿¡¼­ »ç¿ëÇϴ Ŭ¸³¾ÆÆ® À̹ÌÁö´Â ÀÚ¿¬¿µ»ó¿¡ ºñÇØ ¿Ü°û¼±À» ¸íÈ®ÇÏ°Ô ÃßÃâÇÒ ¼ö ÀÖ´Ù´Â ÀåÁ¡ÀÌ ÀÖ´Ù. À̹ÌÁö¿¡¼­ ¸ð¾ç Á¤º¸¸¦ ÃßÃâÇÏ´Â ÀÌÀüÀÇ ¹æ¹ýÀº ¸ð¾çÀÇ ¿Ü°û¼±À» ÀÌ¿ëÇÏ´Â °Í°ú ¿µ¿ªÀ» ÀÌ¿ëÇÏ´Â °ÍÀ¸·Î ºÐ·ùÇÒ ¼ö Àִµ¥ º» ³í¹®¿¡¼­´Â ¸ð¾çÀÇ ¿Ü°û¼±À» ÀÌ¿ëÇÏ´Â °ÍÀ¸·Î ¿Ü°û¼±ÀÇ ¿À¸ñÇÑ ºÎºÐ°ú º¼·ÏÇÑ ºÎºÐÀ» Á÷»ç°¢ÇüÀÇ ºñÀ²·Î Ç¥ÇöÇÏ´Â ¹æ½ÄÀ» Á¦¾ÈÇÏ¿´´Ù. ÀÌ·¸°Ô ÇÔÀ¸·Î¼­ ±âÁ¸ÀÇ ¿Ü°û¼± ±â¹Ý Ư¡À» ÀÌ¿ëÇÏ´Â ¹æ½Äº¸´Ù ¸ð¾ç Á¤º¸¸¦ ´õ¿í Àß Ç¥ÇöÇÒ ¼ö ÀÖ¾ú´Ù.

[±¹³»³í¹®]

This paper presented a method of extracting shape information from a clipart image and then measured the similarity between clipart images using the extracted shape information. The results indicated that the outlines of the extracted clipart images were clearer that those of the original images. Previous methods of extracting shape information could be classified into outline-based methods and region-based methods. Included in the former category, the proposed method expressed the convex and concave aspects of an outline using the ratio of a rectangle. Accordingly, the proposed method was superior in expressing shape information than previous outline-based feature methods.

[±¹³»³í¹®]

º» ³í¹®Àº Ŭ¸³¾ÆÆ® À̹ÌÁö·ÎºÎÅÍ »ö»óÁ¤º¸¿Í ¸ð¾çÁ¤º¸¸¦ ÃßÃâÇÑ ÈÄ¿¡ ´Ù¸¥ Ŭ¸³¾ÆÆ® À̹ÌÁö·ÎºÎÅÍ ÃßÃâµÈ »ö»óÁ¤º¸¿Í ¸ð¾çÁ¤·Ä »çÀÌÀÇ À¯»ç¼ºÀ» ÃøÁ¤ÇÏ´Â ¹æ¹ý¿¡ ´ëÇØ Á¦¾ÈÇÑ´Ù. Ŭ¸³¾ÆÆ® À̹ÌÁöÀÇ ¸ð¾çÁ¤º¸¸¦ Ç¥ÇöÇϱâ À§Çؼ­, Á¦¾ÈµÈ ¹æ¹ýÀº »ç°¢ÇüÀÇ ºñÀ²À» ÀÌ¿ëÇؼ­ ¿Ü°¢¼±À» ¿À¸ñ¸é°ú º¼·Ï¸éÀÇ ºñÀ²·Î Ç¥ÇöÇÑ´Ù. ¸ð¾çÀÇ ¿Ü°¢¼±Àº »ç°¢ÇüÀ¸·Î Ç¥ÇöµÇ°í üÀÎ ÄÚµå·Î º¯È¯ÇÑ´Ù. ¹Ý¸é¿¡, »ö»óÀº HSV »ö»ó ÁÂÇ¥°è·Î ¾çÀÚÈ­µÈ °£ »ö»ó ¿µ¿ª»çÀÌÀÇ À§Ä¡ Á¤º¸ ±×¸®°í »ö»ó ¿µ¿ª»çÀÌÀÇ Å©±â·Î Ç¥ÇöµÈ´Ù. ÀÌ »ö»óÁ¤º¸´Â ÀÚ¿¬ À̹ÌÁöº¸´Ù ÀûÀº Ä®¶ó¼ö¸¦ °¡Áö´Â Ŭ¸²¾ÆÆ®¸¦ Ç¥ÇöÇÏ´Â µ¥ ÀÖ¾î º¸´Ù ³ªÀº Á¤È®¼ºÀ» °®´Â´Ù. ½ÇÇè °á°ú´Â ¸ð¾ç°ú »ö»óÀ» Ç¥ÇöÇÏ´Â µ¥ ÀÖ¾î ÀÌÀü¿¡ ¿¬±¸µÇ¾ú´ø ¹æ¹ýº¸´Ù Á¦¾ÈµÈ ¹æ¹ýÀÌ ¿ìÀ§¿¡ ÀÖÀ½À» º¸¿©ÁØ´Ù.

[±¹³»³í¹®]

Áö±Ý±îÁöÀÇ Á¤º¸°Ë»ö ¿¬±¸¿¡¼­ µ¥ÀÌÅÍ À¶ÇÕ ±â¹ýÀ» ÀÌ¿ëÇÑ ¹®¼­ °Ë»öÀº ÇϳªÀÇ ¾Ë°í¸®Áò¿¡ ÀÇÇÑ °Ë»ö¿¡ ºñÇÏ¿© ¸¹Àº °æ¿ì¿¡ È¿À²¼ºÀÌ ³ôÀº °á°ú¸¦ ¾òÀ» ¼ö ÀÖ¾ú´Ù. ÇÏÁö¸¸ À̹ÌÁö °Ë»ö¿¡¼­ »óÀÌÇÑ ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÑ ´Ù¼öÀÇ °Ë»ö °á°ú¸¦ ÇÕÃÄ ÇϳªÀÇ °Ë»ö°á°ú¸¦ ¾ò´Â µ¥ÀÌÅÍ À¶ÇÕ ±â¹ýÀÇ »ç¿ëÀº ¸¹Áö ¾Ê¾Ò´Ù. ÀÌ ¿¬±¸¿¡¼­´Â ¼Òº§ ¿¬»êÀÚ¸¦ ÀÌ¿ëÇÑ À±°û¼± °ËÃâ°ú ÀÚ±âÁ¶Á÷È­ Áöµµ ¾Ë°í¸®Áò¿¡ ÀÇÇÑ µÎ °Ë»ö °á°ú¸¦ À¶ÇÕÇÏ¿© °¢°¢ÀÇ ¾Ë°í¸®Áò¿¡ ÀÇÇÑ °Ë»ö°á°ú º¸´Ù ³ôÀº È¿À²¼ºÀ» º¸¿©ÁÖ´Â ¹æ¹ýÀ» Á¦½ÃÇÏ¿´´Ù. ÀÌ ¿¬±¸¿¡¼­´Â »ó¿ë Ŭ¸³¾ÆÆ® À̹ÌÁö¸¦ ÀÌ¿ëÇÏ¿© »ç¶÷ÀÇ ÁÖ°üÀûÀÎ ÀûÇÕ¼º ÆÇ´ÜÀ» ¹èÁ¦ÇÑ °Ë»ö ½ÇÇè µ¥ÀÌÅ͸¦ ¸¸µé¾î »ç¿ëÇÏ¿´´Ù.

[±¹³»³í¹®]

Á¤º¸Åë½ÅºÎ´Â 1/4ºÐ±â µðÁöÅÐÄÜÅÙÃ÷ ´ë»ó¿¡ ¿µ±¸¾ÆÆ®ÀÇ 'D-WAR', ¾Æ¸®¼ö¹Ìµð¾îÀÇ '¾Æ¸®¼ö ÇѱÛ', ¿£ÆÄÀÎÀÇ '¾ÆÀÌŬ¸¯¾ÆÆ®'¸¦ ¼±Á¤Çß´Ù.¿µ»óºÎ¹® ¼ö»óÀÛÀÎ ¿µ±¸¾ÆÆ®ÀÇ D-WAR´Â °³±×¸Ç ½ÉÇü·¡¾¾°¡ Á¦ÀÛÁßÀÎ ÄÄÇ»Åͱ׷¡ÇÈÀ» °¡¹ÌÇÑ SF¿µÈ­·Î, Áö³­ 99³â Á¦ÀÛ¿¡ µé¾î°¡ ³»³â 7¿ù Àü ¼¼°è¿¡¼­ °³ºÀµÉ ¿¹Á¤ÀÌ´Ù. ¿£ÆÄÀÎÀÇ '¾ÆÀÌŬ¸¯¾ÆÆ®'´Â ±¤°í, À¥, ÃâÆÇ, Àμâ, ÆÒ½Ã, ±³À° µî¿¡ »ç¿ëµÇ´Â ´Ù¾çÇÑ Æ÷Åä, À̹ÌÁö, Ŭ¸³¾ÆÆ®, ij¸¯ÅÍ µîÀ» Á¦°øÇÏ´Â µðÁöÅÐ À̹ÌÁö Æ÷Å»»çÀÌÆ®(www.iclickart.co.kr)·Î Áö³­ÇØ 11¿ù ¹Ì±¹¿¡ ¼öÃâµÅ 50¸¸´Þ·¯ÀÇ ½ÇÀûÀ» ¿Ã¸®°í ÀÖ´Ù

[±¹³» ÇÐÀ§³í¹®]

À½¾Ç °¨»óÀº ´Ü¼øÈ÷ À½¾ÇÀ» µè´Â °ÍÀÌ ¾Æ´Ï¶ó ÀÛ°î°¡ÀÇ °¨Á¤°ú »ç»ó, ´À³¦±îÁö °¨ÁöÇÏ´Â À½¾ÇÀû ÇàÀ§ÀÌ´Ù. À½¾Ç °¨»óÀ» ÅëÇÏ¿© À½¾ÇÀû °æÇè¿¡ ´Ù°¡°¥ ¼ö ÀÖ°í ÀÌ·¯ÇÑ ¹ÌÀûüÇèÀº Á¤¼­ÀûÀÎ ¾ÈÁ¤°ú ½É½ÅÀÇ Á¶È­·Î¿î ¹ß´ÞÀ» °¡Á®¿Â´Ù. À½¾Ç¸¸ µè´Â ¼öµ¿Àû ÀÚ¼¼°¡ ¾Æ´Ï¶ó À½¾ÇÀ» µè°í Ç¥ÇöÇÏ¸ç ¼³¸íÇÒ ¼ö ÀÖ´Â ´Éµ¿Àû ÀÚ¼¼°¡ µÇ¾î¾ß ÇÑ´Ù. À½¾Ç °¨»óÀº À½¾ÇÀÇ ±âº» ´É·Â¹è¾ç°ú âÀÇÀûÀ¸·Î Ç¥ÇöÇÏ°í °¨»óÇÏ´Â ´É·ÂÀ» ±æ·¯ À½¾ÇÀ» »ýÈ°È­ÇÏ´Â ¹Ù¶÷Á÷ÇÑ Åµµ¸¦ ±â¸£´Âµ¥ ÀÖ´Ù. µû¶ó¼­ º» ¿¬±¸´Â ÁßÇб³ À½¾Ç±³°ú¼­ Áß¿¡¼­ ¼­¾çÀ½¾ÇÀ» Áß½ÉÀ¸·Î È¿°úÀûÀÎ °¨»ó ¼ö¾÷ °³¼± ¹æ¾È¿¡ ´ëÇÑ ¹æ¹ýÀ» ¸ð»öÇÏ¿´´Ù.Á¤º¸È­ ½Ã´ë¿¡ »ì¸é¼­ ÇнÀ ÀڷḦ ¸¸µå´Â ÀÏÀº Áß¿äÇϸç, ±× ÀڷḦ È°¿ëÇÏ¿© È¿°úÀûÀÎ ¼ö¾÷À» À̲ø¾î ³ª°¡´Â °ÍÀº ´õ¿í Áß¿äÇÏ´Ù. ±×·¯³ª ½ÇÁ¦·Î ±³»ç°¡ ÇнÀÇöÀå¿¡¼­ ÇнÀ ÀڷḦ Á¦ÀÛÇϱ⿡ ¿©·¯ ¾î·Á¿òÀÌ ÀÖ´Ù.º» ¿¬±¸´Â ´Ù¸¥ ÇÁ·Î±×·¥¿¡ ºñÇÏ¿© ºñ±³Àû ½±°Ô ÀÚ·á Á¦ÀÛÀÌ ¿ëÀÌÇÏ°í Çлýµé¿¡°Ô ¼ö¾÷ÀÇ ÁýÁ߷°ú È£ÀÀµµ¸¦ ³ôÀÏ ¼ö ÀÖµµ·Ï ÆÄ¿öÆ÷ÀÎÆ®¸¦ È°¿ëÇÏ¿© ¼ö¾÷ÀÚ·á °³¹ßÀ» ¸ð»öÇÏ¿´´Ù.ù°, À½¾Ç±³À°¿ë ¼ÒÇÁÆ®¿þ¾î Áß ÆÄ¿öÆ÷ÀÎÆ® È°¿ë¿¡ ´ëÇØ ¼Ò°³ÇÏ°í Á¦7Â÷ ±³À°°úÁ¤¿¡¼­ ¸ÖƼ¹Ìµð¾î È°¿ëÀÇ Á߿伺À» Á¦½ÃÇÏ¿´´Ù.µÑ°, ÁßÇб³ 1ÇÐ³â ¹× 2Çгâ À½¾Ç °¨»ó¿µ¿ªÀ» Á¦½ÃÇÏ°í ±× Áß¿¡¼­ º£Å亥 ±³Çâ°î Á¦9¹ø <ÇÕâ>°ú ÇÁ·ÎÄÚÇÇ¿¡ÇÁÀÇ À½¾Çµ¿È­ <ÇÇÅÍ¿Í ´Á´ë>¸¦ Áß½ÉÀ¸·Î ¼ö¾÷Áöµµ¾ÈÀ» ÀÛ¼ºÇÏ°í, ÆÄ¿öÆ÷ÀÎÆ® ¼ö¾÷ ÀڷḦ Á¦ÀÛÇÏ¿´´Ù.¼Â°, ÆÄ¿öÆ÷ÀÎÆ®·Î ÇнÀÀÚ·á Á¦ÀÛ ½Ã ÇÊ¿äÇÑ ½½¶óÀÌµå ¼­½Ä°ú ÅؽºÆ®, Ŭ¸³¾ÆÆ®, ¼Ò¸®, ¾Ö´Ï¸ÞÀÌ¼Ç µî ¿©·¯ °¡Áö È°¿ë¹æ¹ýÀ» À½¾Ç °¨»ó ÀÚ·áÁ¦ÀÛ°ú ÇÔ²² Á¦½ÃÇÏ¿© º¸´Ù ½±°Ô Á¦ÀÛÀÌ °¡´ÉÇϵµ·Ï ÇÏ¿´´Ù.¸¶Áö¸·À¸·Î ÆÄ¿öÆ÷ÀÎÆ®¸¦ È°¿ëÇÑ ÇнÀ ÀÚ·á·Î ¼ö¾÷À» ÁøÇàÇÑ ÈÄ ±× °á°ú¸¦ Á¶»çÇÏ¿© È¿°úÀûÀÎ ¼ö¾÷ÀÌ ÀÌ·ç¾îÁ³´ÂÁö¸¦ Çлýµé¿¡°Ô ¼³¹®Áö¸¦ ÅëÇÏ¿© È®ÀÎÇÏ¿´À¸¸ç, ±× °á°ú ¸¹Àº ÇлýµéÀÌ ¸ÖƼ¹Ìµð¾î¸¦ È°¿ëÇÑ ¼ö¾÷¿¡ °ü½É°ú È£ÀÀÀ» º¸¿´À½À» ¾Ë ¼ö ÀÖ¾ú´Ù. ÀÌ·¯ÇÑ È¿°úÀûÀÎ ¼ö¾÷ÀÌ Áö¼ÓÀûÀ¸·Î ÀÌ·ç¾îÁö·Á¸é ÇлýÁß½ÉÀÇ ÀÚ±â ÁÖµµÀû ÇнÀ°ú âÀÇ·Â ½ÅÀå¿¡ ±³»çÀÇ Áö¼ÓÀûÀÎ ¿¬±¸¿Í ³ë·ÂÀÌ ÇÊ¿äÇÏ´Ù°í »ý°¢µÈ´Ù.

[±¹³»³í¹®]

ÇÁ·Î½ÃÀú ÅؽºÃ³(Procedural Textures)´Â °ÔÀÓ¾÷°èÀÇ ¸¹Àº ¾ÆƼ½ºÆ®¿¡°Ô ¾Ç¸íÀÌ ³ô´Ù. ÀÌ°ÍÀº ÀϺΠ»ç¿ëÇϱⰡ ¾î·Æ±â ¶§¹®ÀÌ´Ù. ÇÁ·Î½ÃÀú ÅؽºÃ³´Â ÆäÀÎÆú¸´Ù´Â ÇÁ·Î±×·¡¹Ö¿¡ °¡±õ´Ù. ƯÈ÷ ÇÕ¼º ÅؽºÃ³¿¡¼­ Àß ¾Ë·ÁÁø ·»´õ¸¸ (Renderman)Àº ¿ÏÀüÈ÷ º¯ÇüµÈ ¾ð¾îÀ̸ç ÆÐÅ°Áö°¡ Áö¿øÇÏ´Â ´Ù¾çÇÑ ÇÁ·ÐÆ® ¿£µå´Â °ÅÀÇ C++ ¼öÁØ ¸Å´º¾óó·³ ¹Ì½ºÅ׸®ÇÏ´Ù. ¶ÇÇÑ ÇÁ·Î½ÃÀú´Â ¾ÆƼ½ºÆ® Ãø¸é¿¡¼­ ¸¹Àº ÀÇȤÀ» ºÒ·¯ÀÏÀ¸Å²´Ù. ÁøºÎÇÏ°í °ÅÀÇ ºÒ°¡ÇÇÇÑ º£ÀÌ´Ï ¸¶ºí°ú ÇÁ·¢Å» ÀâÀ½Àº ÆÄ¿öÆ÷ÀÎÆ® Ŭ¸³¾ÆÆ®ÀÇ CG ´ëÀÀºÎ´Ù. ÀÌ·¯ÇÑ ±¸Á¶¸¦ ÀÌ¿ëÇÒ ¶§ ¿Ö ÇÁ·Î½ÃÀú ÅؽºÃ³¿¡ Ä÷³À» ÇÒ¾ÖÇß´ÂÁö ±Ã±ÝÇÒ ¼öµµ ÀÖÀ» °ÍÀÌ´Ù. À̹ø È£¿¡´Â ÇÁ·Î½ÃÀú ÅؽºÃ³¸¦ »ìÆìºÁ¾ß ÇÏ´Â ¼¼ °¡Áö ÀÌÀ¯¸¦ Á¤¸®Çß´Ù.

[±¹³» ÇÐÀ§³í¹®]

±â¾÷°æ¿µÀÇ Çʼö¿ä¼Ò·Î ºÎ°¢µÇ°í ÀÖ´Â À¥»çÀÌÆ®´Â ´õ ÀÌ»ó »õ·Î¿ï °Íµµ ¾ø´Ù. ÇÏÁö¸¸ ¼ö¸¹Àº ±â¾÷µéÀÌ À¥»çÀÌÆ®¸¦ ±â¼úÀûÀÎ Ãø¸é¿¡¼­ Á¢±ÙÇÏ°í ÀÖÀ¸¸ç ¼³°è´Â ÇÁ·Î±×·¡¸Ó¿¡°Ô ¸Ã±â°í ¸¸µé¾îÁø »çÀÌÆ®¸¦ ¿î¿µ¸¸ ÇÏ°í ÀÖ´Â »óȲÀÌ´Ù. µû¶ó¼­ º» ³í¹®¿¡¼­´Â ±×µ¿¾È ¿©·¯ À¥»çÀÌÆ® Á¦ÀÛÀ» ÅëÇØ ¹ß°ßÇÑ ³ëÇÏ¿ì¿Í ½ÇÁ¦ À¥»çÀÌÆ® ¼³°è¿¡ µû¶ó ´Þ¶óÁö´Â µ¥ÀÌÅ͸¦ ±Ù°Å·Î ȸ»ç »çÁ¤À» °¡Àå Àß ÆľÇÇÏ°í ÀÖ´Â ¸¶ÄÉÅÍ°¡ À¥»çÀÌÆ®¸¦ Á÷Á¢ ±âȹÇÏ°í ¼³°èÇÒ ¼ö ÀÖ´Â ¹æ¹ýÀ» Á¦½ÃÇÏ°í ±×°ÍÀ» ÀÚ½ÅÀÌ ±Ù¹«ÇÏ´Â ±â¾÷ÀÇ Æ¯¼º¿¡ ¸Â°Ô²û CUSTOMIZING ÇÒ ¼ö ÀÖ´Â ±â¹ýÀ» Á¦½ÃÇÏ°íÀÚ ÇÑ´Ù. À̸¦ À§ÇØ À¥»çÀÌÆ®¸¦ ±¸¼ºÇϴµ¥ ÇʼöÀûÀÎ ±¸¼º¿ä¼Ò¿Í ±âȹ¹æÇâ, ÀÌ·¯ÇÑ ³»¿ëÀ» °í°´ÀÌ Àß ÀÎÁöÇÏ°í ¼ö¿ëÇÒ ¼ö ÀÖµµ·Ï À¯Àú ÀÎÅÍÆäÀ̽º¸¦ ¼³°èÇÏ´Â ±â¹ý°ú »ç·Ê¸¦ Áß½ÉÀ¸·Î ¼³¸íÇÏ°í ¸¶Áö¸·À¸·Î ÀÎÅÍ³Ý À¯Àú ƯÀ¯ÀÇ ½É¸®¿Í ÇൿƯ¼º ºÐ¼®À» ÅëÇØ À¥»çÀÌÆ®·Î À¯ÀÔµÈ °í°´Àº ¹°·Ð ÀÌÅ»ÇÑ °í°´ÀÇ °æ·Î±îÁö ÃßÀûÇÏ¿© ´Ù½Ã À¥»çÀÌÆ®·Î À¯ÀÔµÇ¾î ±Ã±ØÀûÀ¸·Î »óÇ°±¸¸Å ȤÀº ¼Òºñ·Î À̾îÁú ¼ö ÀÖ´Â ¹æ¾ÈÀ» ¸ð»öÇÏ°íÀÚ ÇÑ´Ù.

[ÇØ¿Ü³í¹®]

In many information retrieval experiments, the data fusion techniques have been used to achieve higher effectiveness in comparison to the single evidence-based retrieval. However, there had not been many image retrieval studies using the data fusion techniques especially in combining retrieval results based on multiple retrieval methods. In this paper, we describe how the image retrieval effectiveness can be improved by combining two sets of the retrieval results using the Sobel operator-based edge detection and the Self Organizing Map(SOM) algorithms. We used the clip art images from a commercial collection to develop a test data set. The main advantage of using this type of the data set was the clear cut relevance judgment, which did not require any human interven- tion.

/ 1

Filters

º¸±âÇü½Ä

Á¤·Ä¼ø¼­

Æ÷¸Ë

¸®½ºÆ® ¼ö