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

»çÀÌÆ®¸Ê

Loading..

Please wait....

Çмú´ëȸ ÇÁ·Î½Ãµù

Ȩ Ȩ > ¿¬±¸¹®Çå > Çмú´ëȸ ÇÁ·Î½Ãµù > Çѱ¹Á¤º¸Åë½ÅÇÐȸ Çмú´ëȸ > 2015³â Ãß°èÇмú´ëȸ

2015³â Ãß°èÇмú´ëȸ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Ư¡, »ö»ó ¹× ÅؽºÃ³ Á¤º¸ÀÇ °¡°øÀ» ÀÌ¿ëÇÑ Bag of Visual Words À̹ÌÁö ÀÚµ¿ ºÐ·ù
¿µ¹®Á¦¸ñ(English Title) Improved Bag of Visual Words Image Classification Using the Process of Feature, Color and Texture Information
ÀúÀÚ(Author) ¹ÚÂùÇõ   ±ÇÇõ½Å   °­¼®ÈÆ   Chan-hyeok Park   Hyuk-shin Kwon   Seok-hoon Kang  
¿ø¹®¼ö·Ïó(Citation) VOL 19 NO. 02 PP. 0079 ~ 0082 (2015. 10)
Çѱ۳»¿ë
(Korean Abstract)
À̹ÌÁö¸¦ ºÐ·ùÇÏ°í °Ë»öÇÏ´Â ±â¼ú(Image retrieval)Áß ÇϳªÀÎ Bag of visual words(BoVW)´Â Ư¡Á¡(feature point)À» ÀÌ¿ëÇÏ´Â ¹æ¹ýÀ¸·Î µ¥ÀÌÅͺ£À̽ºÀÇ À̹ÌÁö Ư¡º¤Å͵éÀÇ ºÐÆ÷¸¦ ÅëÇØ Äõ¸® À̹ÌÁö¸¦ ÀÚµ¿À¸·Î ºÐ·ùÇÏ°í °Ë»öÇØÁÖ´Â ½Ã½ºÅÛÀÌ´Ù. Words¸¦ ±¸¼ºÇϴµ¥ Ư¡º¤Å͸¸À» ÀÌ¿ëÇÏ´Â ±âÁ¸ÀÇ ¹æ¹ýÀº ÀÌ¿ëÀÚ°¡ ¿øÇÏÁö ¾Ê´Â À̹ÌÁö¸¦ °Ë»öÇϰųª ºÐ·ùÇÒ ¼ö ÀÖ´Ù. ÀÌ·¯ÇÑ ´ÜÁ¡À» ÇØ°áÇϱâ À§ÇØ Æ¯Â¡º¤ÅͻӸ¸ ¾Æ´Ï¶ó À̹ÌÁöÀÇ ÀüüÀûÀÎ ºÐÀ§±â¸¦ Ç¥ÇöÇÒ ¼ö ÀÖ´Â »ö»óÁ¤º¸³ª ¹Ýº¹µÇ´Â ÆÐÅÏ Á¤º¸¸¦ Ç¥ÇöÇÒ ¼ö ÀÖ´Â ÅؽºÃ³ Á¤º¸¸¦ Words¸¦ ±¸¼ºÇϴµ¥ Æ÷ÇÔ½ÃÅ´À¸·Î¼­ ´Ù¾çÇÑ °Ë»öÀ» °¡´ÉÇÏ°Ô ÇÑ´Ù. ½ÇÇè ºÎºÐ¿¡¼­´Â Ư¡Á¤º¸¸¸À» °¡Áø words¸¦ ÀÌ¿ëÇØ À̹ÌÁö¸¦ ºÐ·ùÇÑ °á°ú¿Í »ö»óÁ¤º¸¿Í ÅؽºÃ³ Á¤º¸°¡ Ãß°¡µÈ words¸¦ °¡Áö°í À̹ÌÁö¸¦ ºÐ·ùÇÑ °á°ú¸¦ ºñ±³ÇÏ¿´°í »õ·Î¿î ¹æ¹ýÀº 80~90%ÀÇ Á¤È®µµ¸¦ ³ªÅ¸³»¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
Bag of visual words(BoVW) is one of the image classification and retrieval methods, using feature point that automatical sorting and searching system by image feature vector of data base. The existing method using feature point shall search or classify the image that user unwanted. To solve this weakness, when comprise the words, include not only feature point but color information that express overall mood of image or texture information that express repeated pattern. It makes various searching possible. At the test, you could see the result compared between classified image using the words that have only feature point and another image that added color and texture information. New method leads to accuracy of 80~90%.
Å°¿öµå(Keyword) BoVW   Image Classification   TBIR(Text based image retreival)   CBIR(Cotent based image retreival)   GLCM(Gray-Level Co-Occurreence Matrix)   LAB color space  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå