• 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) ¼öÆÛÇȼ¿ ±â¹ÝÀÇ HDR À̹ÌÁö °ü½É ¿µ¿ª ÃßÃâ ±â¹ý
¿µ¹®Á¦¸ñ(English Title) Superpixel-Based HDR Image Region of Interest Extraction Method
ÀúÀÚ(Author) ¼­½É¿Â   ¿Á½Â·Ä   ±è¿µÁø   Simon Suh   Seung-Ryeol Ohk   Young-Jin Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 47 NO. 09 PP. 0793 ~ 0803 (2020. 09)
Çѱ۳»¿ë
(Korean Abstract)
HDR(High Dynamic Range)À̹ÌÁö¿Í LDR(Low Dynamic Range)À̹ÌÁö¿¡ ä³Î ´ç ºñÆ® ¼öÀÇ Â÷ÀÌ ¶§¹®¿¡ LDR µð½ºÇ÷¹ÀÌ¿¡¼­ HDR À̹ÌÁö¸¦ Ç¥ÇöÇϱâ À§ÇØ Åæ ¸ÅÇÎ °úÁ¤ÀÌ ÇÊ¿äÇÏ´Ù. À̶§ À̹ÌÁö °ü½É ¿µ¿ª°ú ºñ °ü½É ¿µ¿ª¿¡ Â÷À̸¦ µÎ¾î Åæ ¸ÅÇÎ È¿À²À» ³ôÀÏ ¼ö ÀÖ´Ù. itti ¸ðµ¨Àº À̹ÌÁöÀÇ »ö, ¸ð¾ç, ¿òÁ÷ÀÓÀÇ ÃÊÁ¡À» ¸ÂÃß¾î °ü½É ¿µ¿ªÀ» ÃßÃâÇÏ´Â ´ëÇ¥ÀûÀÎ ¹æ¹ýÀÌ´Ù. º» ³í¹®Àº itti¿Í ´Þ¸® °´Ã¼ÀÇ Æ¯Â¡¿¡ ±â¹ÝÇÏ¿© ¼öÆÛÇȼ¿(superpixel)À» ÀÌ¿ëÇØ °ü½É ¿µ¿ªÀ» ÃßÃâÇÑ´Ù. ¼öÆÛÇȼ¿¿¡ ±â¹ÝÇÑ À̹ÌÁö °ü½É ¿µ¿ªµéÀÇ Æ¯Â¡À» ½Ãµå Æ÷ÀÎÆ®·Î ÀÌ¿ëÇØ k-means ±ºÁýÈ­¸¦ ¼öÇàÇÏ°í °á±¹ °´Ã¼ ÁöÇâÀûÀÎ °ü½É ¿µ¿ªÀ» HDR À̹ÌÁö¿¡¼­ ÃßÃâÇÑ´Ù. Á¦¾ÈÇÏ´Â ±â¹ýÀº ittiº¸´Ù ÀüüÀ̹ÌÁö¿¡¼­ Æò±ÕÀûÀ¸·Î Á¤¹Ðµµ¿Í NSS°¡ °¢°¢ 10.7%, 28.14% ³·Áö¸¸, ÀçÇöÀ², SIM, CC°¡ °¢°¢ 44.44%, 19.53%, 7.43% Áõ°¡ÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Because of the difference in the number of bits per channel between high dynamic range (HDR) and low dynamic range (LDR) images, a tone mapping process is required to represent an HDR image on an LDR display. In this case, by using the difference between the image ROI and the non-ROI, the efficiency of the tone-mapping may be increased. The itti model is a representative method of extracting a region of interest by focusing colors, shapes, and movements of an image. Unlike the itti model, this paper extracts the region of interest using superpixels based on the characteristics of the object. The k-means clustering is performed using the features of the superpixel-based image regions of interest as a seed point, and finally the object-oriented region of interest is extracted from the HDR image. In the proposed technique, the precision and NSS are 10.7% and 28.14% lower than those from the itti model on average, but the recall, SIM, and CC increased by 44.44%, 19.53%, and 7.43%, respectively.
Å°¿öµå(Keyword) HDRÀ̹ÌÁö   °ü½É¿µ¿ª   Åæ ¸ÅÇΠ  µð½ºÇ÷¹ÀÌ   Æò°¡Çà·Ä   Àΰ£½Ã°¢ ¸¸Á·µµ   HDR image   region of interest   tone mapping   display   evaluation matrix   human visual satisfaction  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå