Image Forgery Detection based on Energy Probability


ÜSTÜBİOĞLU B., ULUTAŞ G., NABIYEV V., ULUTAŞ M.

23nd Signal Processing and Communications Applications Conference (SIU), Malatya, Türkiye, 16 - 19 Mayıs 2015, ss.919-922 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Doi Numarası: 10.1109/siu.2015.7129980
  • Basıldığı Şehir: Malatya
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.919-922
  • Karadeniz Teknik Üniversitesi Adresli: Evet

Özet

The development and widespread deployment of easy to use image editing tools has increased image forgery operations in recent years. Many methods have been proposed in the literature to detect the copy move operation, one of the most widely used forgery techniques. Methods exhibit differences from one another by the way they used to represent sub-blocks in the image. One of the most important problems for all techniques in use is to decide the threshold value to use in order to detect similarity successfuly. In this work, DCT energy probability values of overlapping sub-blocks are used to construct feature vectors of size 1x10. Using a similarity ratio instead of trying to decide a static threshold is an advantage of the method compared to similar techniques. The proposed method yields better results compared to other DCT based methods under attacks (such as JPEG compression and blurring) to hide clues of forgery.