Comparison of specific segmentation methods used for copy move detection

Eman Abdulazeem Ahmed, Malek Alzaqebah, Sana Jawarneh, Jehad Saad Alqurni, Fahad A. Alghamdi, Hayat Alfagham, Lubna Mahmoud Abdel Jawad, Usama A. Badawi, Mutasem K. Alsmadi, Ibrahim Almarashdeh


In this digital age, the widespread use of digital images and the availability of image editors have made the credibility of images controversial. To confirm the credibility of digital images many image forgery detection types are arises, copy-move forgery is consisting of transforming any image by duplicating a part of the image, to add or hide existing objects. Several methods have been proposed in the literature to detect copy-move forgery, these methods use the key point-based and block-based to find the duplicated areas. However, the key point-based and block-based have a drawback of the ability to handle the smooth region. In addition, image segmentation plays a vital role in changing the representation of the image in a meaningful form for analysis. Hence, we execute a comparison study for segmentation based on two clustering algorithms (i.e., k-means and super pixel segmentation with density-based spatial clustering of applications with noise (DBSCAN)), the paper compares methods in term of the accuracy of detecting the forgery regions of digital images. K-means shows better performance compared with DBSCAN and with other techniques in the literature.


copy move detection; density-based spatial clustering of applications with noise image segmentation; k-means; super pixel segmentation;


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

International Journal of Electrical and Computer Engineering (IJECE)
p-ISSN 2088-8708, e-ISSN 2722-2578