Nura Sulaiman, Mustapha Aminu Bagiwa, Salisu Aliyu, Kasim Shafii, Abubakar Muhammed Usman, Shuaibu Mohammed, Auwal Jamilu Abdulsalam


In present days, individuals in the society are becoming increasingly relying on multimedia content, especially digital images and videos, to provide a reliable proof of the occurrence of events. However, the availability of powerful and user-friendly video editing tools makes it easy even for a novice to manipulate the content of a digital video which may be used as evidence during digital investigation. This has led to great concern regarding the trustworthiness of digital videos. A number of techniques have proposed in the literature for different types of digital video forgery detections. In this work, a hybrid technique for detecting and localizing splicing video forgery using convolutional auto-encoder and GOTURN (Generic Object Tracking Using Regression Network) is proposed. The parameters of the auto-encoder are learned during the training phase on original video frames. During the testing phase, the auto-encoder reconstructs the original frames with small reconstruction error and the forged frame with large reconstruction error. The forged material is then tracked in subsequent frames using GOTURN algorithm. The result of the experiments demonstrates that the proposed detection technique can adequately detect video splicing with an AUROC (Area Under the Receiver Operating Characteristics) value of 0.9307.

Full Text:



Bagiwa, M. A., Abdul Wahab, A. W., Idna Idris, M. Y., Khan, S., & Choo, K.-K. R. (2016). Chroma key background detection for digital video using statistical correlation of blurring artifact. Digital Investigation, 29-43.

Choras, R. S. (2007). Image feature extraction techniques and their applications for CBIR and biometrics systems. INTERNATIONAL JOURNAL OF BIOLOGY AND BIOMEDICAL ENGINEERING, 1, 1-11.

Cozzolino, D., Poggi, G., & Verdoliva, L. (2014). Copy-move forgery detection based on patch match. ICIP, 5247-5251.

D'Avino, D., Cozzolino, D., Poggi, G., & Verdoliva, L. (2017). Autoencoder with recurrent neural networks for video forgery detection. 1-8.

Jessica, F., & Jan, K. ( 2012). Rich models for steganalysis of digital images. IEEE Transactions on Information Forensics and Security, 7(3), 868–882.

Junyu, X., Yanru, Y., Yuting, S., B, D., & Xingang, Y. (2012). Detection of blue screen special effects in videos International Conference on Medical Physics and Biomedical Engineering, 1316-1322.

Kaur, R., & Kaur, E. J. (2016). Video forgery detection using hybrid techniques. International Journal of Advanced Research in Computer and Communication Engineering, 5, 112-117.

Mary, G. J. J., & Begum, A. R. (2015). Edge detection using third order difference equation: a new dimension Communications on Applied Electronics (CAE), 10-14.

Pandey, R. C., Singh, S. K., & Shukla, K. K. (2014). Passive copy- move forgery detection in videos International conference on computer and communication technology, 301-306.

Pandey, R. C., Singh, S. K., & Shukla, K. K. (2016). Passive forensics in image and video using noise features: A review. Digital Investigation, 1-28.

Saxena, S., Subramanyam, A. V., & Ravi, H. (2016). Video inpainting detection and localization using inconsistencies in optical flow. . IEEE Region 10 Conference.

Singh, R. D., & Aggarwal, N. (2017). Detection of upscale-crop and splicing for digital video authentication. Digital Investigation, 31-52. doi: doi: 10.1016/j.diin.2017.01.001

Singh, Raahat D., & Aggarwal, N. (2017). Video content authentication techniques: a comprehensive survey 1-30. doi: DOI 10.1007/s00530-017-0538-9

Wu, W., Jiang, X., Sun, T., & Wang, W. (2014). Exposing video inter-frame forgery based on velocity field consistency. International Conference on Acoustic, Speech and Signal Processing Assurance and Security (ICASSP), 2693-2697.


  • There are currently no refbacks.