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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ÇÐȸÁö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ÇÐȸÁö > µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

Current Result Document : 986 / 986

ÇѱÛÁ¦¸ñ(Korean Title) PP-YOLO¸¦ ÀÌ¿ëÇÑ ½Ç½Ã°£ µÎÇÇ °¢Áú °ËÃâ ±â¹ý
¿µ¹®Á¦¸ñ(English Title) A Real-time Scalp Keratin Detection Scheme using PP-YOLO
ÀúÀÚ(Author) Á¶¼º±¹   ±èÇüÁØ   ¹Ú¼º¿ì   ȲÀÎÁØ   Seongkuk Cho   Hyungjoon Kim   Sungwoo Park   Eenjun Hwang  
¿ø¹®¼ö·Ïó(Citation) VOL 37 NO. 02 PP. 0052 ~ 0064 (2021. 08)
Çѱ۳»¿ë
(Korean Abstract)
µÎÇÇ Áúº´Àº ´ë°³ °¢Áú°ú ÅëÁõÀ» À¯¹ßÇϸç, Áõ»óÀ» ¹æÄ¡Çϸé Å»¸ð³ª ¸ð³¶¿°À¸·Î ÁøÇàµÉ ¼ö ÀÖ´Ù. µû¶ó¼­, Áúº´ÀÇ Á¶±â ¹ß°ß°ú Ä¡·á°¡ Áß¿äÇÏÁö¸¸, Á¤±âÀûÀ¸·Î Àü¹® ±â°üÀ» ¹æ¹®ÇÏ´Â °ÍÀº ¸¹Àº ½Ã°£°ú ºñ¿ëÀ» ÃÊ·¡ÇÑ´Ù. ÃÖ±Ù, ½º¸¶Æ®Æù¿¡ Çö¹Ì°æ Ä«¸Þ¶ó¸¦ ¿¬µ¿ÇÑ µÎÇÇ »óÅÂÀÇ ÀÚ°¡Áø´ÜÀÌ °¡´ÉÇØÁö¸é¼­, µö·¯´× ±â¹ÝÀÇ µÎÇÇ Áúº´ Áø´Ü ±â¹ýÀÌ Á¦¾ÈµÇ°í ÀÖ´Ù. ±×·¯³ª, ÀÌ·¯ÇÑ ±â¹ýµéÀº ³ôÀº ¿¬»ê·®ÀÌ ¿ä±¸µÇ¾î ½º¸¶Æ®Æù°ú °°Àº Á¦ÇÑÀûÀÎ Çϵå¿þ¾î ȯ°æ¿¡¼­´Â ¸¸Á·½º·¯¿î ¼º´ÉÀ» ¾ò±â°¡ ¾î·Á¿ö, ½Ç½Ã°£ µÎÇÇ »óÅ Áø´Ü°ú °°Àº Çö½ÇÀûÀÎ ¿ä±¸¿¡ ºÎÇÕÇÏÁö ¸øÇÏ°í ÀÖ´Ù. ÀÌ·¯ÇÑ ¹®Á¦¸¦ ÇØ°áÇÏ°íÀÚ, º» ³í¹®¿¡¼­´Â µÎÇÇ Áúº´¿¡¼­ °øÅëÀ¸·Î ¹ß»ýÇÏ´Â °¢ÁúÀÇ À¯¹«¿Í À§Ä¡¸¦ ½Ç½Ã°£À¸·Î ÃßÃâÇÒ ¼ö ÀÖ´Â ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. À̸¦ À§ÇØ, °¢Áú °ËÃâ¿¡ PP-YOLO ¸ðµ¨À» »ç¿ëÇÏ¿´À¸¸ç, ±âÁ¸¿¡ Á¦¾ÈµÈ ¿¬±¸µé°ú °ËÃâ Á¤È®µµ ¹× ó¸® ¼Óµµ¸¦ ºñ±³ÇÏ¿´´Ù. ½ÇÇè°á°ú, º» ³í¹®¿¡¼­ Á¦¾ÈÇÏ´Â ±â¹ýÀº ½Ç½Ã°£ ¼öÁØÀÇ °ËÃâ ¼Óµµ¸¦ ¸¸Á·ÇÒ »Ó¸¸ ¾Æ´Ï¶ó, ±âÁ¸ ¿¬±¸º¸´Ù Á¤È®ÇÏ°Ô µÎÇÇ °¢ÁúÀ» °ËÃâÇÒ ¼ö ÀÖÀ½À» º¸ÀδÙ.
¿µ¹®³»¿ë
(English Abstract)
Symptoms of scalp disease include keratin and pain in the scalp, which leads to hair loss or folliculitis, if left untreated. Therefore, early detection and appropriate treatment are important, but it takes a lot of time and money to visit a medical institution periodically. Recently, as it is possible to self-diagnose the scalp condition by connecting a microscope camera to a smartphone, various deep learning-based scalp disease diagnosis schemes have been proposed. However, such schemes require a large amount of computation, which is a serious obstacle in a limited hardware environment such as a smartphone. For this reason, they do not meet realistic demands such as real-time scalp condition diagnosis. To solve this problem, in this paper, we propose a real-time keratin detection scheme using the PP-YOLO model. To evaluate the performance of the proposed scheme, we compare it with other methods in terms of detection accuracy and processing speed. Experimental results show that our scheme not only achieves the detection speed of the real-time level but also detects scalp keratin more accurately than previous schemes.
Å°¿öµå(Keyword) ½Ç½Ã°£ °´Ã¼ °ËÃâ   PP-YOLO   µÎÇÇ °ü¸®   µÎÇÇ Áúº´   Real-time object detection   PP-YOLO   Haircare   Scalp disease  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå