• 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 Ãß°èÇмú´ëȸ

2018³â Ãß°èÇмú´ëȸ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Transfer-Learning ±â¹ýÀ» ÀÌ¿ëÇÑ ¿µ¿ª°ËÃâ ±â¹ý¿¡ °üÇÑ ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) A Study on Area Detection Using Transfer-Learning Technique
ÀúÀÚ(Author) ½Å±¤¼º   ½Å¼ºÀ±   Kwang-seong Shin   Seong-yoon Shin  
¿ø¹®¼ö·Ïó(Citation) VOL 22 NO. 02 PP. 0178 ~ 0179 (2018. 10)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù ÀÚÀ²ÁÖÇà ¹× À½¼ºÀÎ½Ä µî ÀΰøÁö´É ºÐ¾ß¿¡¼­ ±â°èÇнÀÀ» ÀÌ¿ëÇÑ ¹æ¹ýÀÌ È°¹ßÈ÷ ¿¬±¸µÇ°í ÀÖ´Ù. µðÁöÅÐ ¿µ»ó¿¡¼­ ƯÁ¤ »ç¹°À̳ª ¿µ¿ªÀ» ÀνÄÇϱâ À§ÇØ °íÀüÀûÀÎ °æ°è°ËÃâ ¹× ÆÐÅÏÀÎ½Ä µîÀÇ °íÀüÀûÀÎ ¿µ»óó¸® ¹æ¹ýÀ¸·Î´Â ¸¹Àº ÇѰ踦 °¡Áö°í ÀÖÀ¸³ª deep-learning µî ±â°èÇнÀ ¹æ¹ýÀ» ÀÌ¿ëÇÏ¸é »ç¶÷ÀÇ ÀÎÁö¼öÁØ¿¡ ±ÙÁ¢ÇÑ °á°ú¸¦ ¾òÀ» ¼ö ÀÖ´Ù. ÇÏÁö¸¸ ±âº»ÀûÀ¸·Î deep-learning µî ±â°èÇнÀÀº ¹æ´ëÇÑ ¾çÀÇ ÇнÀµ¥ÀÌÅÍ°¡ È®º¸µÇ¾î¾ß ÇÑ´Ù. µû¶ó¼­ ȯ°æ ºÐ¼®À» À§ÇÑ Ç×°ø»çÁøó·³ µ¥ÀÌÅÍÀÇ ¾çÀÌ ¸Å¿ì ÀûÀº °æ¿ì ¿µ¿ª ±¸ºÐÀ» À§ÇØ ±â°èÇнÀÀ» Àû¿ëÇϱ⠾î·Æ´Ù. º» ¿¬±¸¿¡¼­´Â ÀԷ¿µ»óÀÇ dataset Å©±â°¡ Àû°í ÀÔ·Â ¿µ»óÀÇ ÇüÅ°¡ training datasetÀÇ category¿¡ Æ÷ÇÔµÇÁö ¾Ê´Â °æ¿ì »ç¿ëÇÒ ¼ö ÀÖ´Â transfer-learning ±â¹ýÀ» Àû¿ëÇϸç À̸¦ ÀÌ¿ëÇÏ¿© ¿µ»ó ³»¿¡¼­ ƯÁ¤ ¿µ¿ª °ËÃâÀ» ¼öÇàÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Recently, methods of using machine learning in artificial intelligence such as autonomous navigation and speech recognition have been actively studied. Classical image processing methods such as classical boundary detection and pattern recognition have many limitations in order to recognize a specific object or area in a digital image. However, when a machine learning method such as deep-learning is used, Can be obtained. However, basically, a large amount of learning data must be secured for machine learning such as deep-learning. Therefore, it is difficult to apply the machine learning for area classification when the amount of data is very small, such as aerial photographs for environmental analysis. In this study, we apply a transfer-learning technique that can be used when the dataset size of the input image is small and the shape of the input image is not included in the category of the training dataset.
Å°¿öµå(Keyword) transfer-leaning   pattern recognition   image processing  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå