• 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 > IPIU (¿µ»óó¸® ¹× ÀÌÇØ¿¡ °üÇÑ ¿öÅ©¼¥) > IPIU 2018 (Á¦30ȸ ¿µ»óó¸® ¹× ÀÌÇØ¿¡ °üÇÑ ¿öÅ©¼¥)

IPIU 2018 (Á¦30ȸ ¿µ»óó¸® ¹× ÀÌÇØ¿¡ °üÇÑ ¿öÅ©¼¥)

Current Result Document : 153 / 282 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ·£´ý ¹®ÀÚ ¼±ÅÃÀ» È°¿ëÇÑ YOLO v2 ±â¹Ý Çʱâü ÇÑÀÚ °ËÃâ
¿µ¹®Á¦¸ñ(English Title)
ÀúÀÚ(Author) ·ùÁØȯ   ±è¹Î¼º   ÃÖÇöö   ±è¼ºÈ£  
¿ø¹®¼ö·Ïó(Citation) VOL 30 NO. 01 PP. P2 ~ 0040 (2018. 02)
Çѱ۳»¿ë
(Korean Abstract)
¿µ¹®³»¿ë
(English Abstract)
In this paper, we propose a deep learning-based method to detect Chinese characters. There are some previous researches related to general chinese character detection, but there are no precedent studies to detect Chinese characters. In addition, there is a difficulty in that the experts have difficulty in reading because of the mixed use of languages of different ethnic groups, and it takes more time for education, budget, and manpower than experts. Therefore, we propose a detection method using the deep learning method which shows the superior performance in recent detection technology. You Only Look Once (YOLO) is a suitable method for object detection and recognition in images because a single neural network predicts bounding boxes directly through a single evaluation in the whole image and calculates the probability of a class in real-time. So, we propose a fine-tuned method to detect Chinese character based on the YOLO v2 framework.
Å°¿öµå(Keyword)
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå