TY - JOUR ID - TI - False Matches Removing in Copy-Move Forgery Detection Algorithms AU - Muthana S. Mahdi AU - Saad N.Alsaad PY - 2020 VL - 31 IS - 1 SP - 47 EP - 53 JO - Al-Mustansiriyah Journal of Science مجلة علوم المستنصرية SN - 1814635X 25213520 AB - Today the technology age is characterized by spreading of digital images. The most common form of transfer the information in magazines, newspapers, scientific journals and all types of social media. This huge use of images technology has been accompanied by an evolution in editing tools of image processing which make modifying and editing an image is very simple. Nowadays, the circulation of such forgery images, which distort the truth, has become common, intentionally or unintentionally. Nowadays many methods of copy-move forgery detection which is one of the most important and popular method of image forgery are available. Most of these methods suffer from the problem of producing false matches as false positives in flat regions. This paper presents an algorithm of the Copy-Move forgery detection using SIFT algorithm with effective method to remove the false positives by rejecting all key-points in matches list that own a neighbor less than the threshold. The accuracy of the proposed algorithm was 95 %. The experimental results refer that the proposed method of false positives removing can remove false matches accurately and quickly.

ER -