A new approach for localization of copy-move forgery in digital images

Tahaoglu, Gul; Uluas, Guzin; Ustubioglu, Bste

doi:10.1109/tsp52935.2021.9522680

Cited by 1 publication

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…for the GRIP database, which is very efficient. We obtain better results than the methods of (Bravo-Solorio and Nandi, 2009; Amerini et al, 2011;Cozzolino et al, 2015a;Li et al, 2015;Silva et al, 2015;Zandi et al, 2016;Li and Zhou, 2019;Diwan et al, 2019) and (Tahaoglu et al, 2021) with F1-scores between 0.2774 and 0.9469. The methods of (Amerini et al, 2011) and (Meena and Tyagi, 2020) which have respectively an F1-score of 0.9538 and 0.9581 are comparable to our method.…”

Section: Methodsmentioning

confidence: 58%

“…Indeed, its descriptor is twice less large and more robust against some image transformation than SIFT descriptor. Tahaoglu et al (2021) presented a method using keypoints and an estimation of the geometric transformations using the RANSAC algorithm to determine whether an image is authentic. If the image is tampered, the estimated homography is used to locate the altered regions.…”

Section: Pioneering Keypoint-based Methodsmentioning

confidence: 99%

“…In this part we compare our method with the method of (Bravo-Solorio and Nandi, 2009;Amerini et al, 2011;Cozzolino et al, 2015a;Li et al, 2015;Silva et al, 2015;Zandi et al, 2016;Diwan et al, 2019;Li and Zhou, 2019;Meena and Tyagi, 2020;Tahaoglu et al, 2021;Chen et al, 2020) and (Gupta and Singh, 2021) on the entire GRIP database.…”

Section: Comparison On the Entire Grip Databasementioning

confidence: 99%

“…in terms of F1-score at pixel level, obtained by our method with the methods (Huang et al, 2008;Amerini et al, 2011;Shivakumar and Baboo, 2011;Li et al, 2015;Pun et al, 2015;Zandi et al, 2016;Li and Zhou, 2019;Mei et al, 2019;Chen et al, 2020;Lyu et al, 2021) and (Diwan et al, 2019) on the entire FAU database. The values in bold are the F1 scores obtained using our method on the different databases (6 difficult images, FAU and GRIP) -Solorio and Nandi, 2009;Amerini et al, 2011;Cozzolino et al, 2015a;Li et al, 2015;Silva et al, 2015;Zandi et al, 2016;Diwan et al, 2019;Li and Zhou, 2019;Meena and Tyagi, 2020;Chen et al, 2020;Tahaoglu et al, 2021) and (Gupta and Singh, 2021) on the entire GRIP database. The values in bold are the F1 scores obtained using our method on the different databases (6 difficult images, FAU and GRIP)…”

Section: Comparison On the Entire Grip Databasementioning

confidence: 99%

See 3 more Smart Citations

A Very Fast Copy-Move Forgery Detection Method for 4K Ultra HD Images

Bertojo

Néraud

Puech

2022

Front. Signal Process.

View full text Add to dashboard Cite

Copy-move forgery detection is a challenging task in digital image forensics. Keypoint-based detection methods have proven to be very efficient to detect copied-moved forged areas in images. Although these methods are effective, the keypoint matching phase has a high complexity, which takes a long time to detect forgeries, especially for very large images such as 4K Ultra HD images. In this paper, we propose a new keypoint-based method with a new fast feature matching algorithm, based on the generalized two nearest-neighbor (g2NN) algorithm allowing us to greatly reduce the complexity and thus the computation time. First, we extract keypoints from the input image. After ordering them, we perform a match search restricted to a window around the current keypoint. To detect the keypoints, we propose not to use a threshold, which allows low intensity keypoint matching and a very efficient detection of copy-move forgery, even in very uniform or weakly textured areas. Then, we apply a new matching algorithm, and finally we compute the cluster thanks to the DBSCAN algorithm. Our experimental results show that the method we propose can detect copied-moved areas in forged images very accurately and with a very short computation time which allows for the fast detection of forgeries on 4K images.

show abstract