• 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 > 2018³â Ãá°èÇмú´ëȸ

2018³â Ãá°èÇмú´ëȸ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ¾ó±¼ Ư¡Á¡µéÀ» ÀÌ¿ëÇÑ ±Ù»ç Á¤¸é ¾ó±¼ ¿µ»ó °ËÃâ
¿µ¹®Á¦¸ñ(English Title) Approximate Front Face Image Detection Using Facial Feature Points
ÀúÀÚ(Author) ±è¼öÁø   Á¤¿ë¼®   ¿ÀÁ¤¼ö   Su-jin Kim   Yong-seok Jeong   Jeong-su Oh  
¿ø¹®¼ö·Ïó(Citation) VOL 22 NO. 01 PP. 0312 ~ 0312 (2018. 05)
Çѱ۳»¿ë
(Korean Abstract)
¾ó±¼Àº »ç¶÷À» È®ÀÎÇÒ ¼ö ÀÖ´Â °íÀ¯ÇÑ ¼ºÁúÀ» °®°í ÀÖ¾î ¾ó±¼ ÀνÄÀÌ ÃâÀÔÅëÁ¦, ¹üÁËÀÚ °Ë»ö, ¹æ¹ü¿ë CCTV °°Àº º¸¾È ¿µ¿ª°ú º»ÀÎ ÀÎÁõ ¿µ¿ª¿¡ È°¹ßÈ÷ È°¿ëµÇ°í ÀÖ´Ù. Á¤¸é ¾ó±¼ ¿µ»óÀº °¡Àå ¸¹Àº ¾ó±¼ Á¤º¸¸¦ °®°í ÀÖ¾î ¾ó±¼ ÀνÄÀ» À§ÇØ °¡´ÉÇÑ Á¤¸é ¾ó±¼ ¿µ»óÀ» ÃëµæÇÏ´Â °ÍÀÌ ÇÊ¿äÇÏ´Ù. º» ¿¬±¸¿¡¼­ Çϸ£À¯»ç Ư¡À» ÀÌ¿ëÇÑ Adaboost ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇØ ¾ó±¼ ¿µ¿ªÀÌ °ËÃâµÇ°í mean-shift ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇØ ¾ó±¼À» ÃßÀûÇÑ´Ù. ±×¸®°í ¾ó±¼ ¿µ¿ª¿¡¼­ ´«°ú ÀÔ °°Àº ¾ó±¼ ¿ä¼ÒµéÀÇ Æ¯Â¡Á¡µéÀ» ÃßÃâÇØ ±×µéÀÇ ±âÇÏÇÐÀûÀÎ Á¤º¸¸¦ ÀÌ¿ëÇØ µÎ ´«ÀÇ ºñ¿Í ¾ó±¼ÀÇ È¸Àü Á¤µµ¸¦ °è»êÇÏ°í ½Ç½Ã°£À¸·Î ±Ù»ç Á¤¸é ¾ó±¼ ¿µ»óÀ» Á¦½ÃÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Since the face has a unique property to identify human, the face recognition is actively used in a security area and an authentication area such as access control, criminal search, and CCTV. The frontal face image has the most face information. Therefore, it is necessary to acquire the front face image as much as possible for face recognition. In this study, the face region is detected using the Adaboost algorithm using Haar-like feature and tracks it using the mean-shifting algorithm. Then, the feature points of the facial elements such as the eyes and the mouth are extracted from the face region, and the ratio of the two eyes and degree of rotation of the face is calculated using their geographical information, and the approximate front face image is presented in real time.
Å°¿öµå(Keyword) ¾ó±¼ °ËÃâ   Haar-like features   Ư¡Á¡ ÃßÃâ   Á¤¸é ±Ù»ç ¾ó±¼   Mean-Shift  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå