Abstract
A robust video fingerprinting based on graph model is proposed in this paper, where two graph models are constructed for key frames selection and foreground extraction, respectively. First, the video is represented as a complete undirected graph and a binary tree is formed using normalized cut algorithm to select key frames. Then, the pixels of each key frame are modeled as a Markov Random Field and another graph model is formed to extract foreground by graph cut. Finally, the fourth-order cumulant of foreground is computed to generate video fingerprints. Experimental results show that the proposed algorithm has good robustness and discrimination.
Similar content being viewed by others
References
Coskun B, Sankur B, Memon N (2006) Spatio-temporal transform based video hashing. IEEE Trans Multimedia 8(6):1190–1208
Esmaeili MM, Fatourechi M, Ward RK (2011) A robust and fast video copy detection system using content-based fingerprinting. IEEE Trans Info Forensics and Sec 6(1):213–216
Howe NR, Deschamps A (2004) Better foreground segmentation through graph cuts. Technical Report
Jeong KM, Lee J-J, Ha Y-H (2006) Video sequence matching using singular value decomposition. In: Proc. 3rd int. conf. image analysis and recognition (ICIAR), pp 426–435
Kolmogorov V, Zabih R (2004) What energy functions can be minimized via graph cuts? TPAMI 26(2):147–159
Lee S, Yoo CD (2006) Video fingerprinting based on centroids of gradient orientations. In: Proc. int. conf. acoust., speech and signal processing (ICASSP), vol 2, pp 401–404
Maani E, Tsaftaris SA, Katsaggelos AK (2008) Local feature extraction for video copy detection in a database. In: IEEE int. conf. image proc. (ICIP), pp 1716–1719
Nie XS, Liu J, Sun JD et al (2011) Robust video hashing based on double-layer embedding. IEEE Signal Process Lett 18(5):307–310
Nie XS, Qiao JP (2012) Robust video copy detection approach based on local tangent space alignment. Opt Eng 51(4):047001
Ngo CW, Ma YU, Zhang HJ (2005) Video summarization and scene detection by graph modeling. IEEE Trans Circuits Syst Video Technol 15(2):296–305
Oostveen J, Kalker T, Haitsma J (2002) Feature extraction and a database strategy for video fingerprinting. In: Proc. 5th int. conf. recent advance in visual information systems, pp 117–128
Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell 22(8):888–905
Sun JD, Wang J, Zhang J et al (2012) Video hashing algorithm with weighted matching based on visual saliency. IEEE Signal Process Lett 19(6):328–331
Sun YD, Li B, Yuan BZ, Miao ZJ, Wang CZ (2006) Better foreground segmentation for static cameras via new energy form and dynamic graph-cut. In: The 18th international conference on pattern recognition (ICPR06), pp 49–52
Tan HK, Ngo CW, Chua TS (2010) Efficient mining of multiple partial near-duplicate alignments by temporal network. IEEE Trans Circuits Syst Video Technol 20(11):1486–1498
The origin of the video dataset is MUSCLE-VCD-2007. https://www.rocq.inria.fr/imedia/civrbench/benchMuscle.html
Acknowledgments
This work is supported partially by National Natural Science Foundation of China (61101162, 61001180) and Shandong province information fusion and industrialization of special research subject (2012EI025, 2012EI020). We also thanks Nicholas R. Howe for offering their matlab codes in his homepage.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nie, X., Sun, J., Xing, Z. et al. Video fingerprinting based on graph model. Multimed Tools Appl 69, 429–442 (2014). https://doi.org/10.1007/s11042-012-1341-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-012-1341-4