• 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 : 14 / 17

ÇѱÛÁ¦¸ñ(Korean Title) eGAN ¸ðµ¨ÀÇ ¼º´É°³¼±À» À§ÇÑ ¿¡Áö °ËÃâ ±â¹ý
¿µ¹®Á¦¸ñ(English Title) An Edge Detection Technique for Performance Improvement of eGAN
ÀúÀÚ(Author) ¹Ú´ë°æ   ·ù°æÁØ   ½Åµ¿ÀÏ   ½Åµ¿±Ô   ¹ÚÁ¤Âù   ±èÁø±¹   Park DaeKyeong   Ryu KyungJoon   Shin DongIl   Shin DongKyoo   Park JeongChan   Kim JinGoog   ±â¹Î¼Û   ÃÖ¿µ¿ì   Min Song Ki   Yeong Woo Choi   ÀÌÃÊ¿¬   ¹ÚÁö¼ö   ¼ÕÁø°ï   Lee Cho Youn   Ji Su Park   Jin Gon Shon  
¿ø¹®¼ö·Ïó(Citation) VOL 10 NO. 03 PP. 0109 ~ 0114 (2021. 03)
Çѱ۳»¿ë
(Korean Abstract)
GAN(Generative Adversarial Network, »ý¼ºÀû Àû´ë ½Å°æ¸Á)Àº À̹ÌÁö »ý¼º¸ðµ¨·Î¼­ »ý¼º±â ³×Æ®¿öÅ©¿Í ÆǺ°±â ³×Æ®¿öÅ©·Î ±¸¼ºµÇ¸ç ½ÇÁ¦ °°Àº À̹ÌÁö¸¦ »ý¼ºÇÑ´Ù. GAN¿¡ ÀÇÇØ »ý¼ºµÈ À̹ÌÁö´Â ½ÇÁ¦ À̹ÌÁö¿Í À¯»çÇØ¾ß ÇϹǷΠ»ý¼ºµÈ À̹ÌÁö¿Í ½ÇÁ¦ À̹ÌÁöÀÇ ¼Õ½Ç ¿ÀÂ÷¸¦ ÃÖ¼ÒÈ­ÇÏ´Â ¼Õ½ÇÇÔ¼ö (loss function)¸¦ »ç¿ëÇÑ´Ù. ±×·¯³ª GANÀÇ ¼Õ½ÇÇÔ¼ö´Â À̹ÌÁö¸¦ »ý¼ºÇÏ´Â ÇнÀÀ» ºÒ¾ÈÁ¤ÇÏ°Ô ¸¸µé¾î À̹ÌÁöÀÇ Ç°ÁúÀ» ¶³¾î¶ß¸°´Ù´Â ¹®Á¦Á¡ÀÌ ÀÖ´Ù. ÀÌ·¯ÇÑ ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇØ º» ³í¹®¿¡¼­´Â GAN °ü·Ã ¿¬±¸¸¦ ºÐ¼®ÇÏ°í ¿¡Áö °ËÃâ(edge detection)À» ÀÌ¿ëÇÑ eGAN(edge GAN)À» Á¦¾ÈÇÑ´Ù. ½ÇÇè °á°ú eGAN ¸ðµ¨ÀÌ ±âÁ¸ÀÇ GAN ¸ðµ¨º¸´Ù ¼º´ÉÀÌ °³¼±µÇ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
GAN(Generative Adversarial Network) is an image generation model, which is composed of a generator network and a discriminator network, and generates an image similar to a real image. Since the image generated by the GAN should be similar to the actual image, a loss function is used to minimize the loss error of the generated image. However, there is a problem that the loss function of GAN degrades the quality of the image by making the learning to generate the image unstable. To solve this problem, this paper analyzes GAN-related studies and proposes an edge GAN(eGAN) using edge detection. As a result of the experiment, the eGAN model has improved performance over the existing GAN model.
Å°¿öµå(Keyword) ±â°èÇнÀ   È£½ºÆ® ±â¹Ý ħÀÔ Å½Áö ½Ã½ºÅÛ   ³×Æ®¿öÅ© ±â¹Ý ħÀÔ Å½Áö ½Ã½ºÅÛ   LID-DS   Machine Learning   HIDS   NIDS   ¾ó±¼ ÀÎÁõ   Àû¿Ü¼± À̹ÌÁö   ¸ÖƼ ¼­Æ÷Æ® º¤ÅÍ ¸Ó½Å   Á¤¸é±¤ ³ëÃâ   Face Identification   Near-infrared Image   Multi Support Vector Machine (Multi-SVM)   Light Overexposure   »ý¼ºÀû Àû´ë ½Å°æ¸Á   ¼Õ½Ç ÇÔ¼ö   ¿¡Áö °ËÃâ   eGAN   Generative Adversarial Network   Loss Function   Edge Detection   eGAN  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå