Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
ÇѱÛÁ¦¸ñ(Korean Title) |
»õ·Î¿î °ü½É¿µ¿ª ÃßÃâ ¹æ¹ýÀ» ÀÌ¿ëÇÑ ¿ª±¤º¸Á¤ |
¿µ¹®Á¦¸ñ(English Title) |
Backlight Compensation by Using a Novel Region of Interest Extraction Method |
ÀúÀÚ(Author) |
°í½ÂÇö
À±Àdzç
Jumabek Alikhanov
Á¶±Ù½Ä
Seunghyun Ko
Ui-Nyoung Yoon
Jumabek Alikhanov
Geun-Sik Jo
¼ºÁظð
À̼º½Å
À̼º¿í
Joon Mo Seong
Seong Shin Lee
Songwook Lee
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 06 NO. 06 PP. 0321 ~ 0328 (2017. 06) |
Çѱ۳»¿ë (Korean Abstract) |
¿ì¸®´Â ºûÀÇ Á¤µµ¿¡ µû¶ó À̹ÌÁöÀÇ ¹à±â¿Í äµµ, ´ëºñ¸¦ º¸Á¤ÇÏ°í ´õ ³ª¾Æ°¡ ¿ª±¤À» º¸Á¤ÇÏ´Â ±â¼úÀ» ±¸ÇöÇÏ¿´´Ù. ¿ª±¤º¸Á¤Àº ÀÚµ¿À̳ª ¼öµ¿À¸·Î ÇÒ ¼ö Àִµ¥, ¼öµ¿À¸·Î ¿ª±¤º¸Á¤À» Àû¿ëÇϱâ À§Çؼ´Â ¸ÕÀú °ü½É¿µ¿ªÀ» ÁöÁ¤ÇØ ÁÖ¾î¾ß ÇÑ´Ù. °ü½É¿µ¿ªÀº »çÁø ¼Ó ¿øÇÏ´Â »ç¹°ÀÇ À±°û¼±À» À̾îÁÜÀ¸·Î½á ¼±ÅÃÇÑ´Ù. ¿ì¸®´Â ÀÚ¼® ¿Ã°¡¹Ì¸¦ ÀÌ¿ëÇÏ¿© »ç¿ëÀÚ°¡ ¼¶¼¼ÇÑ ¼±ÅÃÀ» °¡´ÉÇÏ°Ô ÇÏ¿´´Ù. ±âÁ¸ ¿Ã°¡¹Ì ±â´ÉÀº ½ÃÀÛÁ¡°ú ³¡Á¡À» ÀÏÄ¡½ÃÄÑ ÁÖ¾î¾ß ÇÏ´Â ´ÜÁ¡ÀÌ ÀÖ¾úÀ¸³ª Á¦¾ÈÇÏ´Â ¿Ã°¡¹Ì ±â´ÉÀº ½ÃÀÛÁ¡°ú ³¡Á¡À» ÀÏÄ¡½ÃÅ°Áö ¾Ê¾Æµµ °ü½É¿µ¿ªÀ» ¼±ÅÃÇÒ ¼ö ÀÖ´Â ÀåÁ¡ÀÌ ÀÖ´Ù. ¶ÇÇÑ »ç¿ëÀÚ°¡ ÀÌÁøÈ ÀÓ°è°ª°ú Áú°¨ÃßÃâÀ» À§ÇÑ k-means ±ºÁýÀÇ °³¼ö¸¦ ¼±ÅÃÇÒ ¼ö ÀÖµµ·Ï ÇÏ¿© ´Ù¾çÇÑ ¿ª±¤º¸Á¤ °á°ú¸¦ ÀÚµ¿À¸·Î ¾òÀ» ¼ö ÀÖ°Ô ÇÏ¿´´Ù. |
¿µ¹®³»¿ë (English Abstract) |
We have implemented a technique to correct the brightness, saturation, and contrast of an image according to the degree of light, and further compensate the backlight. Backlight compensation can be done automatically or manually. For manual backlight compensation, we have to select the region of interest (ROI). ROI can be selected by connecting the outline of the desired object. We make users select the region delicately with the new magnetic lasso tool. The previous lasso tool has a disadvantage that the start point and the end point must be connected. However, the proposed lasso tool has the advantage of selecting the region of interest without connecting the start point and the end point. We can automatically obtain various results of backlight compensation by adjusting the number of k-means clusters for texture extraction and the threshold value for binarization.
|
Å°¿öµå(Keyword) |
RANSAC
CS_RANSAC
K-Means Clustering
°ü½É¿µ¿ª
¿ª±¤º¸Á¤
ÀÚ¼®¿Ã°¡¹Ì
Áú°¨ÃßÃâ
K-Means ±ºÁýÈ
Region of Interest
Backlight Compensation
Magnetic Lasso
Texture Extraction
K-Means Clustering
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|