Digital Image Forgery Detection Using SURF and ORB Technique

Authors

  • Jyoti Yadav Ramrao Adik Institute of Technology, D.Y. Patil Vidyapeeth, Nerul, Navi Mumbai
  • Nilima Dongre Ramrao Adik Institute of Technology, D.Y. Patil Vidyapeeth, Nerul, Navi Mumbai

Keywords:

Copy move forgery, Block based, SURF algorithm, ORB algorithm, SVM and EM algorithm

Abstract

Copy-move forgery involves duplicating part of an original image and pasting it elsewhere within the same image to disguise manipulations. Detecting such forgeries is crucial for verifying image authenticity. This research explores keypoint-based approaches for copy-move detection, specifically SURF and ORB. SURF (Speeded Up Robust Features) identifies interest points using the Hessian matrix and describes them with Haar wavelet responses. ORB (Oriented FAST and Rotated BRIEF) uses FAST keypoint detection and binary BRIEF description for efficiency. After extracting SURF and ORB features, SVM and EM classifiers categorize images as forged or genuine. Performance is evaluated using accuracy, precision, recall and F1 score. Results demonstrate ORB+SVM and ORB+EM outperform SURF+EM on all metrics. This highlights ORB's advantages over SURF for copy-move detection when paired with SVM or EM. ORB provides faster feature extraction and description leading to better classification. In conclusion, keypoint methods like ORB show promise for copy-move forgery detection. ORB's efficiency and discriminative power, combined with SVM or EM classification, can effectively identify image manipulations. This research provides valuable insights into optimal feature extraction and machine learning techniques for enhanced forgery detection.

Downloads

Download data is not yet available.

References

. Haipeng Chen, Xiwen Yang, and Yingda Lyu “Copy-Move Forgery Detection Based on Keypoint Clustering and Similar Neighborhood Search Algorithm.” Digital Object Identifier 10.1109/ACCESS. 2020.297480 (2020).

. Meena, K. B., and Tyagi, V. “A hybrid copy-move image forgery detection technique based on Fourier-Mellin and scale invariant feature transforms. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-019-08343-0(2020).

. Qiyue Lyu, Junwei Luo, Ke Liu, Xiaolin Yin, Jiarui Liu, Wei Lu,” Copy Move Forgery Detection based on double matching”, J. Vis. Commun. Image Represent. 76, 103057. doi:10.1016/j.jvcir. (2021).

. Muzaffer, G., Ulutas, G., and Ustubioglu, B. “Copy Move Forgery Detection with Quadtree Decomposition Segmentation,” in 2020 43rd International Conference on Telecommunications and Signal Processing (TSP), Milan, Italy, July 7–9, 2020, 208–211. doi:10.1109/tsp49548.2020.9163516 (2020).

. Tahaoglu, G., Uluas, G., and Ustubioglu, B. (2021). “A New Approach for Localization of Copy-Move Forgery in Digital Images,” in 2021 44th International Conference on Telecommunications and Signal Processing (TSP), Brno, Czechia, July 26–28, 2021, 183–186. doi:10.1109/tsp52935.2021.9522680 (2021).

. Shobhit Tyagi, Divakar Yadav “ForensicNet : Modern CNN-based Image Forgery Detection Network”, https://doi.org/10.21203/rs.3.rs-1802559/v1(2022).

. Liang Xiu-jian and Sun He “Deep Learning Based Image Forgery Detection Methods” DOI: 10.32604/jcs.2022.032915 (2022). 31 Digital Image Forgery Detection Using SURF And ORB Technique

. Kang Hyeon Rhee,” Generation of Novelty Ground Truth Image Using Image Classification and Semantic Segmentation for Copy-Move Forgery Detection”.Digital Object Identifier 10.1109/ACCESS.2021.3136781.(2021).

. Khalid M. Hosny , Akram M. Mortda , Mostafa M. Fouda , And Nabil A. Lashin ” An Efficient CNN Model to Detect Copy-Move Image Forgery”, Digital Object Identifier 10.1109/ACCESS. 2022.3172273(2022).

. Esteban Alejandro Armas Vega , Edgar Gonzalez Fernandez , Ana Lucila Sandoval Orozco , Luis Javier Garcia Villalba,” Passive Image Forgery Detection Based on the Demosaicing Algorithm and JPEG Compression”, Digital Object Identifier 10.1109/ACCESS.2020.2964516(2020).

. Nhan Le and Florent Retraint,” A Statistical Modeling Framework for DCT Coefficients of Tampered JPEG Images and Forgery Localization”, Digital Object Identifier 10.1109/ACCESS. 2022.3188299 (2022).

. Kalyani Kadam, Swati Ahirrao, Ketan Kotecha, And Sayan Sahu, “Detection and Localization of Multiple Image Splicing Using MobileNet V1”, Digital Object Identifier 10.1109/ACCESS. 2021.3130342.(2021)..

. Anh-Thu Phan-Ho and Florent Retraint, “A Comparative Study of Bayesian and Dempster-Shafer Fusion on Image Forgery Detection”, Digital Object Identifier 10.1109/ACCESS.2022.3206543 (2022).

. A-Rom Gu, Ju-Hyeon Nam And Sang-Chul Lee , “FBI-Net: Frequency-Based Image Forgery Localization via Multitask Learning With Self-Attention”, Digital Object Identifier 10.1109/ACCESS. 2022.3182024(2022).

. Savita Walia , Krishan Kumar , Munish Kumar , And Xiao-Zhi Gao, And Sang-Chul Lee , “Fusion of Handcrafted and Deep Features for Forgery Detection in Digital Images”, Digital Object Identifier 10.1109/ACCESS.2021.3096240(2021)

Downloads

Published

12.01.2024

How to Cite

Yadav, J. ., & Dongre, N. . (2024). Digital Image Forgery Detection Using SURF and ORB Technique. International Journal of Intelligent Systems and Applications in Engineering, 12(12s), 696 –. Retrieved from https://www.ijisae.org/index.php/IJISAE/article/view/4553

Issue

Vol. 12 No. 12s (2024)

Section

Research Article

License

Creative Commons License

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

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.