© The Institution of Engineering and Technology
Multiple-compression detection is of particular importance in video forensics, as it reveals possible manipulations to the content. However, methods for detecting multiple compressions with same quantisation parameters (QPs) are rarely reported. To deal with this issue, a novel method is presented in this study to detect multiple H.264/advanced video coding compressions with the same QPs. First, a new set, named ratio difference set (RDS), is proposed, which is calculated by identifying the quantised DCT coefficients whose values will be changed after re-compression. Then, a discriminative and fixed statistical feature set extracted from RDS of each video is obtained to serve as input for classification. With the aid of support vector machines, the extracted feature set is used to classify the videos that have undergone H.264 compressions twice or more from those compressed just once. Experimental results show that high classification accuracy and robustness against copy-move attack and frame-deletion attack can be achieved with the authors’ proposed method.
References
-
-
1)
-
6. Akrami, F., Zargari, F.: ‘An efficient compressed domain video indexing method’, Multimedia Tools Appl., 2014, 72, (1), pp. 705–721.
-
2)
-
12. Liao, D., Yang, R., Liu, H., et al: ‘Double H.264/AVC compression detection using quantized nonzero AC coefficients’. Proc. SPIE, February 2011, p. 78800Q.
-
3)
-
16. Huang, F., Huang, J., Shi, Y.: ‘Detecting double JPEG compression with the same quantization matrix’, IEEE Trans. Inf. Forensics Sec., 2010, 5, (4), pp. 848–856.
-
4)
-
7. Yahaya, S., Ho, A., Wahab, A.: ‘Advanced video camera identification using conditional probability features’. IET Conf. on Image Processing (IPR), London, Britain, July 2012, pp. 1–5.
-
5)
-
3. Dong, L., Schwartz, S.: ‘DCT-based object tracking in compressed video’. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Toulouse, France, May, 2006, pp. II–II.
-
6)
-
7)
-
11. Jiang, X., Wang, W., Sun, T., et al: ‘Detection of double compression in MPEG-4 videos based on markov statistics’, Signal Process. Lett., 2013, 20, (5), pp. 447–450.
-
8)
-
1. Biswas, S., Babu, R.: ‘Real-time anomaly detection in H.264 compressed videos’. IEEE National Conf. on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), Jodhpur, India, 2013, pp. 1–4.
-
9)
-
17. : ‘Advanced video coding for generic audiovisual services’, 2005.
-
10)
-
15. Yang, J., Xie, J., Zhu, G., et al: ‘An effective method for detecting double JPEG compression with the same quantization matrix’, IEEE Trans. Inf. Forensics Sec., 2014, 9, (11), pp. 1933–1942.
-
11)
-
13. Milani, S., Bestagini, P., Tagliasacchi, M., et al: ‘Multiple compression detection for video sequences’. IEEE Int. Workshop on Multimedia Signal Processing (MMSP), September 2012, pp. 112–117.
-
12)
-
9. Wang, W., Farid, H.: ‘Exposing digital forgeries in video by detecting double quantization’. Proc. 11th ACM Workshop on Multimedia and Security (MM&Sec), ACM, New York, USA, 2009, pp. 39–48.
-
13)
-
4. Qian, X., Liu, G., Wang, H., et al: ‘Text detection, localization, and tracking in compressed video’, Signal Process., Image Commun., 2007, 22, (9), pp. 752–768.
-
14)
-
14. Lai, S., Bohme, R.: ‘Block convergence in repeated transform coding: JPEG-100 forensics, carbon dating, and tamper detection’. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, Canada, May, 2013, pp. 3028–3032.
-
15)
-
2. Biswas, S., Babu, R.: ‘Anomaly detection in compressed H.264/AVC video’, Multimedia Tools Appl., 2014, 74, (22), pp. 11099–111151.
-
16)
-
17)
-
18)
-
10. Chen, W., Shi, Y.: ‘Detection of double MPEG compression based on first digit statistics’, Lect. Notes Comput. Sci., 2009, 5450, pp. 16–30.
-
19)
-
5. Qian, X., Wang, H., Hou, X.: ‘Video text detection and localization in intra-frames of H.264/AVC compressed video’, Multimedia Tools Appl., 2014, 70, (3), pp. 1487–1502.
-
20)
-
8. Wang, W., Farid, H.: ‘Exposing digital forgeries in video by detecting duplication’. Proc. Workshop on Multimedia and Security (MM&Sec), ACM, New York, USA, 2007, pp. 35–42.
-
21)
-
21. Chang, C., Lin, C.: ‘LIBSVM: a library for support vector machines’, ACM Trans. Intell. Syst. Technol., 2011, 2, (3), pp. 35–38.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ifs.2015.0361
Related content
content/journals/10.1049/iet-ifs.2015.0361
pub_keyword,iet_inspecKeyword,pub_concept
6
6