Title: Block Based Technique for Detecting Copy-Move Digital Image Forgeries: Wavelet Transform and Zernike Moments

Year of Publication: Feb - 2016
Page Numbers: 26-33
Authors: Thuong Le-Tien, Marie Luong, Tu Huynh-Kha, Long Pham-Cong-Hoan, An Tran-Hong
Conference Name: The Second International Conference on Electrical and Electronic Engineering, Telecommunication Engineering, and Mechatronics (EEETEM2016)
- Philippines

Abstract:


In this paper, a combination of the Wavelet transform and the Zernike moments is presented for detecting copy–move regions in digital forged images. Assuming that tested images have the JPEG format on both before and after being tampered. The proposed method uses the Wavelet transform to remove unimportant details in the forged images by using the approximate components only. After that, the Zernike moments of each 16 x 16 image block are calculated then compared the Euclidean distances to get pairs of any similar blocks. In order to support efficiently the proposed algorithm, a morphological technique is applied to extract the foreground first as a preprocessing. The evaluation for the theory and effectiveness of the proposed algorithm are demonstrated via experimental results on various images with different properties.