The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Robust perceptual image hashing via matrix invariants
Abstract
In this paper we suggest viewing images (as well as attacks on them) as a sequence of linear operators and propose novel hashing algorithms employing transforms that are based on matrix invariants. To derive this sequence, we simply cover a two dimensional representation of an image by a sequence of (possibly overlapping) rectangles R/sub i/ whose sizes and locations are chosen randomly/sup 1/ from a suitable distribution. The restriction of the image (representation) to each R/sub i/ gives rise to a matrix A/sub i/. The fact that A/sub i/'s will overlap and are random, makes the sequence (respectively) a redundant and non-standard representation of images, but is crucial for our purposes. Our algorithms first construct a secondary image, derived from input image by pseudo-randomly extracting features that approximately capture semi-global geometric characteristics. From the secondary image (which does not perceptually resemble the input), we further extract the final features which can be used as a hash value (and can be further suitably quantized). In this paper, we use spectral matrix invariants as embodied by singular value decomposition. Surprisingly, formation of the secondary image turns out be quite important since it not only introduces further robustness (i.e., resistance against standard signal processing transformations), but also enhances the security properties (i.e. resistance against intentional attacks). Indeed, our experiments reveal that our hashing algorithms extract most of the geometric information from the images and hence are robust to severe perturbations (e.g. up to %50 cropping by area with 20 degree rotations) on images while avoiding misclassification. Our methods are general enough to yield a watermark embedding scheme, which will be studied in another paper.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Venkatesan, R., Koon, S.-M., Jakubowski, M. H., & Moulin, P. (2002) · Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101) · doi:10.1109/icip.2000.899541 · Cited by 497
Self-citationRobust hash functions for digital watermarking
Fridrich, J., & Goljan, M. (2002) · Proceedings International Conference on Information Technology: Coding and Computing (Cat. No.PR00540) · doi:10.1109/itcc.2000.844203 · Cited by 336
New Iterative Geometric Methods for Robust Perceptual Image Hashing
Mıhçak, M. K., & Venkatesan, R. (2002) · Lecture notes in computer science · doi:10.1007/3-540-47870-1_2 · Cited by 150
Self-citationA Perceptual Audio Hashing Algorithm: A Tool for Robust Audio Identification and Information Hiding
Mıhçak, M. K., & Venkatesan, R. (2001) · Lecture notes in computer science · doi:10.1007/3-540-45496-9_5 · Cited by 106
Self-citation
Cited by
Robust and secure image hashing
Swaminathan, A., Mao, Y., & Wu, M. (2006) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2006.873601 · Cited by 552
Perceptual Image Hashing Via Feature Points: Performance Evaluation and Tradeoffs
Monga, V., & Evans, B. L. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881948 · Cited by 363
Robust and Secure Image Hashing via Non-Negative Matrix Factorizations
Monga, V., & Mihcak, M. K. (2007) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2007.902670 · Cited by 295
Self-citationThe Design and Implementation of a Wireless Video Surveillance System
Zhang, T., Chowdhery, A., Bahl, P. (., Jamieson, K., & Banerjee, S. (2015) · Proceedings of the 21st Annual International Conference on Mobile Computing and Networking · doi:10.1145/2789168.2790123 · Cited by 272
Robust Image Hashing With Ring Partition and Invariant Vector Distance
Tang, Z., Zhang, X., Li, X., & Zhang, S. (2016) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2015.2485163 · Cited by 247
Robust Image Hashing with Tensor Decomposition
Tang, Z., Chen, L., Zhang, X., & Zhang, S. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2837745 · Cited by 134
Perceptual image hashing based on virtual watermark detection
Khelifi, F., & Jiang, J. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2009.2038637 · Cited by 107
Robust image hashing using non-uniform sampling in discrete Fourier domain
Qin, C., Chang, C.-C., & Tsou, P.-L. (2013) · Digital Signal Processing · doi:10.1016/j.dsp.2012.11.002 · Cited by 81
“The scheme first constructs one secondary image from the input image by randomly extracting features that reflect the image’s semi-global geometric characteristics, and then the final features of the spectral matrix invariants are extracted further from the secondary image by SVD to produce the hash value.”
MethodInfluentialRobust image hashing with multidimensional scaling
Tang, Z., Huang, Z., Zhang, X., & Lao, H. (2017) · Signal Processing · doi:10.1016/j.sigpro.2017.02.008 · Cited by 80
Huang, Z., & Liu, S. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3027001 · Cited by 56
Adversarial collision attacks on image hashing functions
Dolhansky, B., & Ferrer, C. C. (2020) · arXiv · doi:10.48550/arxiv.2011.09473 · Cited by 13
“…one of two ways - either via a deep hashing algorithm [23, 44], where the embeddings from the penultimate layer of a deep network are encoded and binarized, or with what we denote as a “shallow” hashing function, which uses deterministic image operations to produce a fixed-length hash [16, 26, 27].”
BackgroundBiometrics-based identifiers for digital identity management
Bhargav-Spantzel, A., Squicciarini, A., Bertino, E., Kong, X., & Zhang, W. (2010) · Proceedings of the 9th Symposium on Identity and Trust on the Internet · doi:10.1145/1750389.1750401 · Cited by 11
A High-Performance Region Recognition Network-Enhanced Deep CNN for Image Content Perceptual Hashing
Yang, M., Qi, B., Ma, B., Xu, J., Xian, Y., & Li, X. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3559675 · Cited by 6
“Kozat et al. [18] extracted semi-global robust features based on singular value decomposition (SVD) and generate perceptual hash codes based on stable low-order SVD coefficients.”
Metadata
- Authors
- Kozat, S. S., Venkatesan, R., & Mihcak, M. K.
- Venue
- 2004 International Conference on Image Processing, 2004. ICIP '04.
- Publisher
- IEEE
- Published
- 2005-04-19
- Volume
- 5
- Pages
- 3443-3446
- ISSN
- 1522-4880 (ISSN-L)
- OpenAlex
- W1551558511
- Cited by
- 255
- References
- 4
- FWCI
- 7.29
- Type
- conference paper
- Language
- en
- Open access
- closed
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.