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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ConvNetÀ» È°¿ëÇÑ ¿µ¿ª±â¹Ý ½Å¼Ó/¹ü¿ë ¿µ»óÁ¤ÇÕ ±â¼ú
¿µ¹®Á¦¸ñ(English Title) Fast and All-Purpose Area-Based Imagery Registration Using ConvNets
ÀúÀÚ(Author) ¹é½Âö   Seung-Cheol Baek  
¿ø¹®¼ö·Ïó(Citation) VOL 43 NO. 09 PP. 1034 ~ 1042 (2016. 09)
Çѱ۳»¿ë
(Korean Abstract)
¿µ¿ª±â¹Ý ¿µ»óÁ¤ÇÕÀº ¹Ì¸® Á¤ÀÇµÈ Æ¯Â¡ÀÇ µµ¿ò ¾øÀÌ ¿µ»óÀ» Á¤ÇÕÇÒ ¼ö Àֱ⠶§¹®¿¡, ±â°èÇнÀ°ú Á¢¸ñµÈ´Ù¸é ÀÌ·Ð »ó ´Ù¾çÇÑ ¿µ»óÁ¤ÇÕ ¹®Á¦¿¡ Àû¿ë °¡´ÉÇÏ´Ù. ±×·¯³ª ½Å¼ÓÇÑ Á¤ÇÕÀ» À§ÇÏ¿©, ¹Ì¸® Á¤ÀÇµÈ Æ¯Â¡À» ŽÁöÇÏ¿© ÆÐÄ¡ ½Ö È常¦ ¼±Á¤¿¡ »ç¿ëÇϴµ¥, ÀÌ´Â ¿µ¿ª±â¹Ý ¹æ¹ýÀÇ Àû¿ë¼º¿¡ Á¦¾àÀ» ÁØ´Ù. À̸¦ ÇؼÒÇϱâ À§ÇÏ¿© º» ¿¬±¸¿¡¼­´Â ´Ü¼øÈ÷ µÎ ÆÐÄ¡ÀÇ °ü·Ãµµ »Ó¸¸ ¾Æ´Ï¶ó µÎ ÆÐÄ¡°¡ ¾î´À Á¤µµ °ø°£ »ó ¶³¾îÁ® ÀÖ´ÂÁö¿¡ ´ëÇÑ Á¤º¸¸¦ Á¦°øÇÏ´Â ConvNet Dart¸¦ °³¹ßÇÏ¿´´Ù. ÀÌ·¯ÇÑ Á¤º¸¸¦ ±â¹ÝÀ¸·Î È¿À²ÀûÀ¸·Î ÆÐÄ¡ ½Ö Ž»ö°ø°£À» ÁÙÀÏ ¼ö ÀÖ¾ú´Ù. Ãß°¡·Î Dart°¡ Á¦´ë·Î ÀÛµ¿ÇÒ ¼ö ¾ø´Â ¿µ¿ªÀ» ½Äº°ÇÏ´Â ConvNet Fad¸¦ °³¹ßÇÏ¿© Á¤ÇÕÀÇ Á¤¹Ðµµ¸¦ ³ô¿´´Ù. º» ¿¬±¸¿¡¼­´Â À̵éÀ» µö·¯´×À¸·Î ÇнÀÇÏ¿´À¸¸ç, À̸¦ À§ÇØ ¼Ò¼öÀÇ Á¤ÇÕµÈ ¿µ»ó¿¡¼­ ´Ù·®ÀÇ ¿¹Á¦¸¦ »ý¼ºÇÏ´Â ¹æ¹ýÀ» °³¹ßÇÏ¿´´Ù. ¸¶Áö¸·À¸·Î ´Ü¼øÇÑ ¿µ»óÁ¤ÇÕ ¹®Á¦¿¡ ¼º°øÀûÀ¸·Î Àû¿ëÇÏ¿©, ÀÌ·¯ÇÑ ¹æ¹ý·ÐÀÌ ÀÛµ¿ÇÏ´Â °ÍÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Together with machine-learning frameworks, area-based imagery registration techniques can be easily applied to diverse types of image pairs without predefined features and feature descriptors. However, feature detectors are often used to quickly identify candidate image patch pairs, limiting the applicability of these registration techniques. In this paper, we propose a ConvNet (Convolutional Network) ¡°Dart¡° that provides not only the matching metric between patches, but also information about their distance, which are helpful in reducing the search space of the corresponding patch pairs. In addition, we propose a ConvNet ¡°Fad¡° to identify the patches that are difficult for Dart to improve the accuracy of registration. These two networks were successfully implemented using Deep Learning with the help of a number of training instances generated from a few registered image pairs, and were successfully applied to solve a simple image registration problem, suggesting that this line of research is promising.
Å°¿öµå(Keyword) ¿µ¿ª±â¹Ý ¿µ»óÁ¤ÇÕ   ConvNet   µö·¯´×   ¿µ»ó󸮠  imagery registration   convolutional network   deep learning   image processing  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå