• 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¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Á¢ÇÕ ¿µ»ó °ËÃâÀ» À§ÇÑ ¸¶¸£ÄÚÇÁ õÀÌ È®·ü ¹× µ¿½Ã¹ß»ý È®·ü¿¡ ´ëÇÑ ¼±ÅÃÀû Ư¡ ÃßÃâ ¹æ¹ý
¿µ¹®Á¦¸ñ(English Title) Selective Feature Extraction Method Between Markov Transition Probability and Co-occurrence Probability for Image Splicing Detection
ÀúÀÚ(Author) ÇÑÁ¾±¸   ¾öÀϱԠ  ¹®¿ëÈ£   Çϼ®¿î   Jong-Goo Han   Il-Kyu Eom   Yong-Ho Moon   Seok-Wun Ha  
¿ø¹®¼ö·Ïó(Citation) VOL 20 NO. 04 PP. 0833 ~ 0839 (2016. 04)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â È¿À²ÀûÀÎ Á¢ÇÕ ¿µ»ó °ËÃâÀ» À§ÇÑ ¸¶¸£ÄÚÇÁ õÀÌ ¹× µ¿½Ã¹ß»ý È®·ü¿¡ ´ëÇÑ ¼±ÅÃÀû Ư¡ ÃßÃâ ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÏ´Â ¹æ¹ý¿¡¼­´Â ÀÌ»ê ÄÚ»çÀÎ º¯È¯ ¿µ¿ª¿¡¼­ ºí·Ï°£ °è¼öÀÇ Â÷À̸¦ ÀÌ¿ëÇÏ¿© Ư¡µéÀ» ±¸¼ºÇÏ°í, Ư¡µéÀÇ °¢ À§Ä¡¿¡¼­ ¿ø ¿µ»ó°ú Á¢ÇÕ¿µ»óÀÇ Æ¯Â¡ ºÐÆ÷ÀÇ »óÀ̼ºÀ» È®ÀÎÇϱâ À§ÇØ Kullback-Leibler ¼ö·Å°ªÀ» ±¸ÇÑ´Ù. À̸¦ ¹ÙÅÁÀ¸·Î, ¸¶¸£ÄÚÇÁ È®·ü Ư¡°ú µ¿½Ã¹ß»ý È®·ü Ư¡ °¡¿îµ¥ ÇØ´ç À§Ä¡¿¡¼­ °¡Àå Å« Â÷ÀÌ°ªÀ» °®´Â Ư¡À» ¼±ÅÃÇÏ¿© ÃÖÁ¾ Ư¡À¸·Î ¼±ÅÃÇÏ°í, SVM ºÐ·ù±â¸¦ ÀÌ¿ëÇÏ¿© ÇнÀ ¹× Å×½ºÆ®ÇÑ ÈÄ ±× À¯È¿¼ºÀ» ÆǺ°ÇÑ´Ù. ½ÇÇè °á°ú¸¦ ¹ÙÅÁÀ¸·Î Á¦¾ÈÇÏ´Â ¹æ¹ýÀÌ ±âÁ¸ÀÇ ¹æ¹ýº¸´Ù Á¦ÇÑµÈ Æ¯Â¡¼ö·Î ³ôÀº ¿µ»óÁ¢ÇÕ Á¶ÀÛ °á°ú¸¦ º¸ÀÓÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
In this paper, we propose a selective feature extraction algorithm between Markov transition probability and co-occurrence probability for an effective image splicing detection. The Features used in our method are composed of the difference values between DCT coefficients in the adjacent blocks and the value of Kullback-Leibler divergence(KLD) is calculated to evaluate the differences between the distribution of original image features and spliced image features. KLD value is an efficient measure for selecting Markov feature or Co-occurrence feature because KLD shows non-similarity of the two distributions. After training the extracted feature vectors using the SVM classifier, we determine whether the presence of the image splicing forgery. To verify our algorithm we used grid search and 6-folds cross-validation. Based on the experimental results it shows that the proposed method has good detection performance with a limited number of features compared to conventional methods.
Å°¿öµå(Keyword) ÀÌ»êÄÚ»çÀÎ º¯È¯   ¸¶ÄÚÇÁ Ư¡   µ¿½Ã¹ß»ý Ư¡   ¿µ»ó Á¶ÀÛ   ¿µ»ó Á¢ÇÕÁ¶ÀÛ   SVM   DCT   Markov feature   Co-occurrence feature   Image forgery   Image splicing   SVM  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå