• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document : 4 / 4

ÇѱÛÁ¦¸ñ(Korean Title) ½ÉÃþ ½Å°æ¸ÁÀ» È°¿ëÇÑ ÀüÀÚ¹®¼­ ³» °´Ã¼ÀÇ ÀÚµ¿ ÃßÃâ ¹æ¹ý ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) Automatic Object Extraction from Electronic Documents Using Deep Neural Network
ÀúÀÚ(Author) ÀåÈñÁø   俵ÈÆ   ÀÌ»ó¿ø   Á¶Áø¿ë   Heejin Jang   Yeonghun Chae   Sangwon Lee   Jinyong Jo  
¿ø¹®¼ö·Ïó(Citation) VOL 07 NO. 11 PP. 0411 ~ 0418 (2018. 11)
Çѱ۳»¿ë
(Korean Abstract)
ÀΰøÁö´É ±â¼úÀÇ È®»êÀ¸·Î ÀÎÇØ °úÇбâ¼ú ºÐ¾ß¿¡¼­µµ ¿¬±¸ µ¥ÀÌÅÍÀÇ È®º¸, ÀúÀå ¹× È°¿ëÀÌ Áß¿ä½Ã µÇ°í ÀÖ´Â »óȲÀÌ´Ù. ¿¬±¸ µ¥ÀÌÅ͸¦ È®º¸Çϱâ À§ÇØ ÀüÀÚ¹®¼­ ÇüÅÂÀÇ ¿¬±¸³í¹®À¸·ÎºÎÅÍ ±×·¡ÇÁ, Ç¥¿Í °°Àº À¯ÀǹÌÇÑ °´Ã¼¸¦ ÃßÃâÇÏ´Â ´Ù¾çÇÑ ¹æ¹ýµéÀÌ Á¦¾ÈµÇ°í ÀÖ´Ù. °æÇèÀû ¹æ¹ý·ÐÀ» ÀÌ¿ëÇÏ´Â ±âÁ¸ÀÇ ¿¬±¸µéÀº ¹®¼­ÀÇ ÆíÁý Ư¼ºÀ» ÀϹÝÈ­ÇÏ¿© °´Ã¼µéÀ» ÃßÃâÇϱ⠶§¹®¿¡ ´Ù¼öÀÇ ÀÌÁúÀûÀÎ ÇüŸ¦ °®´Â ÀüÀÚ¹®¼­µéÀ» ´ë»óÀ¸·Î ¿¬±¸°á°ú¸¦ Àû¿ëÇϴµ¥´Â ÇÑ°è°¡ ÀÖ´Ù. º» ³í¹®Àº °æÇèÀû ¹æ¹ý·ÐÀÇ °æÁ÷¼ºÀ» ±Øº¹ÇÏ°í ÀÌÁúÀûÀÎ ÀüÀÚ¹®¼­µé·ÎºÎÅÍ ¸ñÇ¥ °´Ã¼µéÀ» È¿°úÀûÀ¸·Î ÃßÃâÇϱâ À§ÇØ ½ÉÃþ ÇнÀ ±â¹ÝÀÇ °´Ã¼ ÃßÃ⠽ýºÅÛÀ» Á¦¾ÈÇÑ´Ù. ÅÙ¼­ÇÃ·Î¿ì °´Ã¼ ŽÁö APIÀÇ Faster R-CNN ¾Ë°í¸®ÁòÀ» ±â¹ÝÀ¸·Î »õ·Î¿î ÇнÀ¸ðµ¨À» »ý¼ºÇßÀ¸¸ç ½ÉÃþ ÇнÀ°ú Æò°¡¸¦ À§ÇØ ÃÑ 100¿© ÆíÀÇ ¿¬±¸³í¹®µéÀ» ´ë»óÀ¸·Î ¸ñÇ¥ °´Ã¼µéÀ» µ¥ÀÌÅÍÈ­Çß´Ù. ¸¶Áö¸·À¸·Î ¼º´ÉÆò°¡¸¦ ÅëÇØ Á¦¾ÈÇÑ ½Ã½ºÅÛÀÌ °æÇèÀû ¹æ¹ý·ÐÀ» Àû¿ëÇÑ ºñ±³ ´ë»ó¿¡ ºñÇØ ¾à 5.2% ³ôÀº ¼º´ÉÀ» º¸ÀÓÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
With the proliferation of artificial intelligence technology, it is becoming important to obtain, store, and utilize scientific data in research and science sectors. A number of methods for extracting meaningful objects such as graphs and tables from research articles have been proposed to eventually obtain scientific data. Existing extraction methods using heuristic approaches are hardly applicable to electronic documents having heterogeneous manuscript formats because they are designed to work properly for some targeted manuscripts. This paper proposes a prototype of an object extraction system which exploits a recent deep-learning technology so as to overcome the inflexibility of the heuristic approaches. We implemented our trained model, based on the Faster R-CNN algorithm, using the Google TensorFlow Object Detection API and also composed an annotated data set from 100 research articles for training and evaluation. Finally, a performance evaluation shows that the proposed system outperforms a comparator adopting heuristic approaches by 5.2%.
Å°¿öµå(Keyword) °´Ã¼ ÃßÃâ   ½ÉÃþ ÇнÀ   ÅÙ¼­Ç÷ο젠 ÀüÀÚ¹®¼­   Object Extraction   Deep Learning   Tensorflow   PDF Document  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå