Spatio-temporal digital video hashing using edge orientation histogram and discrete cosine transform
The DOI matches its Crossref record; 22 of the 23 references it cites were found in a registry or an index.
Abstract
In this paper we propose a spatio-temporal digital video hashing scheme. In the proposed scheme, the digital video is treated as a three dimensional signal. Edge Orientation Histogram (EOH) is computed for each frame in the digital video, then a temporal discrete cosine transform (DCT) for the magnitude of each EOH bin is computed. A subset of the resulting DCT coefficients are then pseudo-randomly rearranged to construct the hash. Our experiments show that the proposed system has good discriminating power, is robust against content-preserving attacks but is sensitive to content-altering attacks.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 4×
“The EOH feature extraction used in this paper generally follows the method described in [12], as discussed below.”
MethodInfluentialObject Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.167 · Cited by 9,853
Qidwai, U., & Chen, C. H. (2009) · Chapman & Hall/CRC eBooks · doi:10.1201/9781420079517 · Cited by 1,701
Human Detection Using Oriented Histograms of Flow and Appearance
Dalal, N., Triggs, B., & Schmid, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744047_33 · Cited by 1,652 · cited 2×
“For example, the authors in [12][13][14] proposed the use of these descriptors in human-detection in images.”
BackgroundMethodFast Human Detection Using a Cascade of Histograms of Oriented Gradients
Zhu, Q., Yeh, M.-C., Cheng, K.-T., & Avidan, S. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.119 · Cited by 1,399
Digital Pictures: Representation, Compression, and Standards
Haskell, B. G., & Netravali, A. N. (1995) · Medical Entomology and Zoology · Cited by 279
Netravali, A. N., & Haskell, B. G. (1995) · Springer eBooks · doi:10.1007/978-1-4899-6950-7 · Cited by 227
Spatio–Temporal Transform Based Video Hashing
Coskun, B., Sankur, B., & Memon, N. (2006) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2006.884614 · Cited by 206 · cited 2×
“For example, the authors in [1][2] proposed video hashing schemes based on the three dimensional discrete cosine transform of the video sequences.”
BackgroundRoad Sign Detection from Edge Orientation Histograms
Alefs, B. G., Eschemann, G., Ramoser, H., & Beleznai, C. (2007) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2007.4290246 · Cited by 90 · cited 1×
“The authors in [15][16] have also shown that these descriptors can also be used to detect other classes of objects.”
BackgroundLarge-Scale Video Hashing via Structure Learning
Ye, G., Liu, D., Wang, J., & Chang, S.-F. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.282 · Cited by 81 · cited 1×
“The authors in [10] used a supervised learning system to learn the spatio-temporal structure of the video being processed in order to generate the hash sequence.”
MethodSpatio-temporal features for robust content-based video copy detection
Willems, G., Tuytelaars, T., & Gool, L. V. (2008) · Multimedia Information Retrieval · doi:10.1145/1460096.1460143 · Cited by 38 · cited 1×
“Another approach that divides the video into shots and then generate the hash based on the spatio-temporal properties of these shots is proposed in [8].”
BackgroundVideo Copy Detection Using Temporally Informative Representative Images
Malekesmaeili, M., Fatourechi, M., & Ward, R. K. (2009) · 2009 International Conference on Machine Learning and Applications · doi:10.1109/icmla.2009.32 · Cited by 37 · cited 1×
“Another approach, proposed in [9], generates temporally representative images from a video sequence and use them to construct the hash sequence.”
BackgroundKey-Frame Based Robust Video Hashing Using Isometric Feature Mapping
Nie, X., Liu, J., Sun, J., & Zhao, H. (2011) · Cited by 11
Using edge orientation histograms in face-based gender classification
Timotius, I. K., & Setyawan, I. (2014) · International Conference on Information Technology Systems and Innovation · doi:10.1109/icitsi.2014.7048244 · Cited by 10 · cited 1×
“The EOH can also be used in gender classification application [17].”
MethodSelf-citationRobust video hashing for identification based on MDS
Nie, X., Liu, J., & Sun, J. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5495386 · Cited by 10 · cited 2×
“A different approach is proposed by the authors in [3].”
BackgroundContent based image hashing using companding and gray code
Yang, L., Chen, Q., Tian, J., & Wu, D. O. (2010) · Security and Communication Networks · doi:10.1002/sec.265 · Cited by 10 · cited 1×
“The normalized Hamming distance calculation is performed using the following formula [19] : H d (h, h ) = 1 M M k=1 δ h k , h k (7) where δ h k , h k = 1, h k = h k 0, h k = h k (8) In the previous equations, h and h are two hash sequences, h k and h k are the k-th elements of each sequence and M…”
MethodPerceptual video hashing based on the Achlioptas's random projections
Sandeep, R., & Bora, P. K. (2013) · National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG) · doi:10.1109/ncvpripg.2013.6776252 · Cited by 9 · cited 2×
“The authors in [6] used random projections of spatio-temporal groups of pixels in the video to generate their hash sequence.”
BackgroundMethodDigital image hashing using local histogram of Oriented Gradients
Setyawan, I., & Timotius, I. K. (2014) · doi:10.1109/iciteed.2014.7007903 · Cited by 9 · cited 2×
“Finally, a novel application of HoG for digital image hashing has been proposed in our previous work [18] with good results.”
BackgroundMethodSelf-citationA robust and fast video fingerprinting based on 3D-DCT and LSH
Mao, H., Feng, G., Zhang, X., & Yao, H. (2011) · International Conference on Multimedia Technology (ICMT) · doi:10.1109/icmt.2011.6001986 · Cited by 6 · cited 2×
“For example, the authors in [1][2] proposed video hashing schemes based on the three dimensional discrete cosine transform of the video sequences.”
BackgroundRobust video hashing using the 3D-DWT
Saikia, N., & Bora, P. K. (2011) · National Conference on Communications · doi:10.1109/ncc.2011.5734750 · Cited by 6 · cited 2×
“Video hashing based on spatio-temporal discrete wavelet transform has also been proposed [7].”
BackgroundA robust video hash scheme based on 2D‐DCT temporal maximum occurrence
Chen, Q., Tian, J., Yang, L., & Wu, D. O. (2010) · Security and Communication Networks · doi:10.1002/sec.264 · Cited by 5 · cited 2×
“The authors in [4] divided the video into separate shots, perform two dimensional DCT on each frame and then derive the video hash based on the DCT coefficients that occur most frequently within the shot.”
BackgroundContent-dependent spatio-temporal video watermarking using 3-dimensional discrete cosine transform
Setyawan, I., & Timotius, I. K. (2013) · doi:10.1109/iciteed.2013.6676215 · Cited by 4 · cited 9×
“Our experiments show that the average inter-hash Hamming distance is 0.4054 for the scheme proposed in this paper and 0.5081 for the scheme in [11].”
BackgroundMethodResultInfluentialSelf-citation
Cited by
Video authentication using spatio temporal relationship for tampering detection
Sowmya, K. N., Chennamma, H. R., & Rangarajan, L. (2018) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2018.07.002 · Cited by 30
A review on robust video copy detection
Wary, A., & Neelima, A. (2018) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-018-0159-x · Cited by 21
“Then, the TIRIs were segmented into overlapping blocks of size w × w and the first vertical and the first horizontal DCT coefficients (features) were generated from each block using 2-dimensional discrete cosine transform (2D-DCT) [62, 63].”
MethodVideo hashing with secondary frames and invariant moments
Tang, Z., Zhang, S., Zhang, X., Li, Z., Chen, Z., & Yu, C. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103209 · Cited by 20
High Accuracy Perceptual Video Hashing via Low-Rank Decomposition and DWT
Lv, C., Ye, D., & Jiang, S. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-37731-1_65 · Cited by 15
Perceptual Video Hashing With Secure Anti-Noise Model for Social Video Retrieval
Lv, C., Ye, D., & Shang, Y. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3293609 · Cited by 11
“By computing gradient edge orientation histogram (EOH) and extracting DCT coefficients, Setyawan and Timotius [15] created a hash.”
Method
Metadata
- Authors
- Setyawan, I., & Timotius, I. K.
- Affiliations
- Satya Wacana Christian University (ID)
- Venue
- 2014 International Conference on Information Technology Systems and Innovation (ICITSI)
- Publisher
- IEEE
- Published
- 2014-11
- Pages
- 111-115
- OpenAlex
- W1530672406
- Semantic Scholar
- 4710340b7b71b76027a0fc3a09a814ce3330f904
- Cited by
- 10
- References
- 23
- Citations by year
- 2024: 1 · 2023: 2 · 2022: 1 · 2021: 2 · 2020: 1 · 2019: 1 · 2018: 2
- FWCI
- 0.00
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Information Technology Systems and Innovation (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Chaos-based Image/Signal Encryption
- Keywords
- edge orientation histogram, discrete cosine transform, content integrity verification, hash robustness
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.