Exposing video inter-frame forgery via histogram of oriented gradients and motion energy image
- PDF / 2,350,211 Bytes
- 20 Pages / 439.37 x 666.142 pts Page_size
- 60 Downloads / 180 Views
Exposing video inter-frame forgery via histogram of oriented gradients and motion energy image Sondos Fadl1,2 · Qi Han1
· Li Qiong1
Received: 17 January 2019 / Revised: 11 February 2020 / Accepted: 14 February 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Inter-frame forgery is a common type of video forgery to destroy the video evidence. It occurs in the temporal domain such as frame deletion, frame insertion, frame duplication, and frame shuffling. These forms of forgery are more frequently produced in a surveillance video because the camera position and the scene are relatively stable, where the tampering process is easy to operate and imperceptible. In this paper, we propose an efficient method for inter-frame forgery detection based on histogram of oriented gradients (HOG) and motion energy image (MEI). HOG is obtained from each image as a discriminative feature. In order to detect frame deletion and insertion, the correlation coefficients are used and abnormal points are detected via Grabb’s test. In addition, MEI is applied to edge images of each shot to detect frame duplication and shuffling. Experimental results prove that the proposed method can detect all inter-frame forgeries and achieve higher accuracy with lower execution time. Keywords Passive forensics · Motion energy image · Anomaly detection · Canny edge detection · Inter-frame forgeries · Histogram of oriented gradients
1 Introduction Surveillance cameras are widely used by many applications for crime control. Nowadays, progress in video surveillance technology has activated the video usage as strong legal evidence in the courts; but the mighty sophistication of computer technology makes the manipulation in videos very easy for anyone by using video editing tools such as Adobe Pro,
B
Qi Han [email protected] Sondos Fadl [email protected] Li Qiong [email protected]
1
School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150080, China
2
Faculty of Computers and Information, Menoufia University, Shebin El-koom 32511, Egypt
123
Multidimensional Systems and Signal Processing
Fig. 1 Inter-frame forgery forms
Avidemux etc. This problem forces the necessity of verifying the authenticity and integrity of a surveillance video. There are two categories of video forgery: intra-frame and inter-frame attacks (Sitara and Mehtre 2016). Intra-frame attack occurs in either spatial or spatio-temporal domain, such as region splicing and copy move. These types of attacks can be detected by image forensics techniques, for example, the methods as in Al-Qershi and Khoo (2019), Fadl and Semary (2017), Ouyang et al. (2019), Zhang et al. (2016), Li et al. (2017). Inter-frame attack occurs in the temporal domain, such as frame insertion, frame deletion, frame duplication, and frame shuffling. As shown in Fig. 1, the forgery is called frame insertion (FI) when a foreign clip was inserted, frame deletion (FE) when some of the frames were deleted, frame duplication (FD) when a clip wa
Data Loading...
