• 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 :

ÇѱÛÁ¦¸ñ(Korean Title) µö·¯´× ±â¹Ý Ä«¸Þ¶ó ¸ðµ¨ ÆǺ°
¿µ¹®Á¦¸ñ(English Title) Camera Model Identification Based on Deep Learning
ÀúÀÚ(Author) À̼öÇö   ±èµ¿Çö   ÀÌÇØ¿¬   Soo Hyeon Lee   Dong Hyun Kim   Hae-Yeoun Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 08 NO. 10 PP. 0411 ~ 0420 (2019. 10)
Çѱ۳»¿ë
(Korean Abstract)
¸ÖƼ¹Ìµð¾î Æ÷·»½Ä ºÐ¾ß¿¡¼­ ¿µ»óÀ» ÃÔ¿µÇÑ Ä«¸Þ¶ó ¸ðµ¨ ÆǺ°À» À§ÇÑ ¿¬±¸°¡ Áö¼ÓµÇ¾î ¿Ô´Ù. Á¡Á¡ °íµµÈ­µÇ´Â ¹üÁË Áß¿¡ ºÒ¹ý ÃÔ¿µ µîÀÇ ¹üÁË´Â Ä«¸Þ¶ó°¡ ¼ÒÇüÈ­µÊ¿¡ µû¶ó ÇÇÇØÀÚ°¡ ¾Ë¾ÆÂ÷¸®±â ¾î·Æ±â ¶§¹®¿¡ ³ôÀº ¹üÁË ¹ß»ý °Ç¼ö¸¦ Â÷ÁöÇÏ°í ÀÖ´Ù. µû¶ó¼­ ƯÁ¤ ¿µ»óÀÌ ¾î´À Ä«¸Þ¶ó·Î ÃÔ¿µµÇ¾ú´ÂÁö¸¦ ƯÁ¤ÇÒ ¼ö ÀÖ´Â ±â¼úÀÌ »ç¿ëµÈ´Ù¸é ¹üÁËÀÚ°¡ ÀÚ½ÅÀÇ ¹üÁË ÇàÀ§¸¦ ºÎÁ¤ÇÒ ¶§, ¹üÁË ÇøÀǸ¦ ÀÔÁõÇÒ Áõ°Å·Î »ç¿ëµÉ ¼ö ÀÖÀ» °ÍÀÌ ´Ù. º» ³í¹®¿¡¼­´Â ¿µ»óÀ» ÃÔ¿µÇÑ Ä«¸Þ¶ó ¸ðµ¨ ÆǺ°À» À§ÇÑ µö·¯´× ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÏ´Â ¸ðµ¨Àº 4°³ÀÇ ÄÁº¼·ç¼Ç °èÃþ°ú 2°³ÀÇ Àü¿¬°á °èÃþÀ¸·Î ±¸¼ºµÇ¾úÀ¸¸ç, µ¥ÀÌÅÍ Àü󸮸¦ À§ÇÑ ÇÊÅÍ·Î High Pass Filter¸¦ »ç¿ëÇÏ¿´´Ù. Á¦¾ÈÇÑ ¸ðµ¨ÀÇ ¼º´É °ËÁõÀ» À§ÇÏ¿© Dresden Image Database¸¦ È°¿ëÇÏ¿´°í, µ¥ÀÌÅͼÂÀº ¼øÂ÷ºÐÇÒ ¹æ½ÄÀ» Àû¿ëÇÏ¿© »ý¼ºÇÏ¿´´Ù. Á¦¾ÈÇÏ´Â ¸ðµ¨À» 3 °èÃþ ¸ðµ¨°ú GLCM Àû¿ë ¸ðµ¨ µî ±âÁ¸ ¿¬±¸µé°ú ºñ±³ ºÐ¼®À» ¼öÇàÇÏ¿© ¿ì¼ö¼ºÀ» º¸¿´°í, ÃֽŠ¿¬±¸ °á°ú¿¡¼­ Á¦½ÃÇÏ´Â ¼öÁØÀÇ 98% Á¤È®µµ¸¦ ´Þ¼ºÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Camera model identification has been a subject of steady study in the field of digital forensics. Among the increasingly sophisticated crimes, crimes such as illegal filming are taking up a high number of crimes because they are hard to detect as cameras become smaller. Therefore, technology that can specify which camera a particular image was taken on could be used as evidence to prove a criminal's suspicion when a criminal denies his or her criminal behavior. This paper proposes a deep learning model to identify the camera model used to acquire the image. The proposed model consists of four convolution layers and two fully connection layers, and a high pass filter is used as a filter for data pre-processing. To verify the performance of the proposed model, Dresden Image Database was used and the dataset was generated by applying the sequential partition method. To show the performance of the proposed model, it is compared with existing studies using 3 layers model or model with GLCM. The proposed model achieves 98% accuracy which is similar to that of the latest technology.
Å°¿öµå(Keyword) µö·¯´×   Ä«¸Þ¶ó ¸ðµ¨ ÆǺ°   ÄÁº¼·ç¼Å³Î ´º·² ³×Æ®¿öÅ©   °íÁÖÆÄ Åë°ú ÇÊÅÍ   ¸í¾Ïµµ µ¿½Ã¹ß»ý Çà·Ä   Deep Learning   Camera Model Identification   Convolutional Neural Network   High Pass Filter   Gray Level Co-Occurrence Matrix  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå