A High-Performance Region Recognition Network-Enhanced Deep CNN for Image Content Perceptual Hashing
Abstract
Perceptual image hashing has emerged as a crucial forensic tool within the Internet of Things (IoT) ecosystem. Traditional perceptual hashing algorithms predominantly rely on global image features to generate hash codes, which limit their ability to represent key features of images effectively. This paper introduces a Perceptual Region Recognition Network (PRRN) to accurately identify key feature regions in images based on their texture distribution characteristics, thereby generating image perceptual hashing codes that reflect the key content of the images. At the same time, a perceptual hashing feature extraction module, which integrates a Residual Network (ResNet) and a Weighted Feature Fusion Network (WFFN), is built to extract deep semantic features of the object image. Where, ResNet is leveraged to extract high-level semantic features, while WFFN ensures the preservation of low-level local features. Furthermore, skip connections are employed to achieve content enhancements for intricate details of critical image regions. Additionally, the Mean Squared Error (MSE) loss is incorporated to enhance the accuracy of key region localization, further improving the sensitivity of image perceptual hash codes and accelerating the network’s convergence speed. Extensive experimental evaluations demonstrate that the proposed PRRN-based perceptual image hashing scheme significantly outperforms other state-of-the-art methods in terms of image feature representation capability. Specifically, it achieves an average improvement of over 1.2 in attack-resistant capability for images compared with other counterparts, making it a promising candidate for practical applications in the IoT environment.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Deep learning and transformer-based hashing techniques demand large-scale labeled data and large amounts of training to learn generalizable representations.
“However, similarity is decided by fixed thresholds during deployment and these techniques demand large-scale labeled data and large amounts of training to learn generalizable representations.”
From DBpHash: a blockchain-based dual-band perceptual hashing framework for copyright protection of purely chromatic background images (2026) · cites this paper as [19]
Cites
A robust content based digital signature for image authentication
Schneider, M., & Chang, S.-F. (2002) · Proceedings of 3rd IEEE International Conference on Image Processing · doi:10.1109/icip.1996.560425 · Cited by 421 · see citing works
Robust perceptual image hashing via matrix invariants
Kozat, S. S., Venkatesan, R., & Mihcak, M. K. (2005) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2004.1421855 · Cited by 256 · see citing works
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 · see citing works
Self-citationRobust Perceptual Image Hashing Based on Ring Partition and NMF
Tang, Z., Zhang, X., & Zhang, S. (2013) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2013.45 · Cited by 199 · see citing works
Graph PCA Hashing for Similarity Search
Zhu, X., Li, X., Zhang, S., Xu, Z., Yu, L., & Wang, C. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2703636 · Cited by 190 · see citing works
Self-citationA Reversible Data Hiding Scheme Based on Code Division Multiplexing
Ma, B., & Shi, Y. Q. (2016) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2016.2566261 · Cited by 176 · see citing works
Self-citationRobust 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 · see citing works
Perceptual image hashing via dual-cross pattern encoding and salient structure detection
Qin, C., Chen, X., Luo, X., Zhang, X., & Sun, X. (2017) · Information Sciences · doi:10.1016/j.ins.2017.09.060 · Cited by 91 · see citing works
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 · see citing works
Robust 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 · see citing works
Qin, C., Liu, E., Feng, G., & Zhang, X. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3047142 · Cited by 78 · see citing works
Robust image hashing with dominant DCT coefficients
Tang, Z., Yang, F., Huang, L., et al. (2014) · Optik · doi:10.1016/j.ijleo.2014.05.015 · Cited by 77 · see citing works
Ma, B., Chang, L., Wang, C., et al. (2020) · Signal Processing · doi:10.1016/j.sigpro.2020.107544 · Cited by 76 · see citing works
Self-citationRobust image hashing based on color vector angle and Canny operator
Tang, Z., Huang, L., Zhang, X., et al. (2016) · AEU - International Journal of Electronics and Communications · doi:10.1016/j.aeue.2016.03.010 · Cited by 69 · see citing works
Perceptual Image Hashing With Texture and Invariant Vector Distance for Copy Detection
Huang, Z., & Liu, S. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.2999188 · Cited by 58 · see citing works
Robust image hashing via DCT and LLE
Tang, Z., Lao, H., Zhang, X., & Liu, K. (2016) · Computers & Security · doi:10.1016/j.cose.2016.07.006 · Cited by 56 · see citing works
Perceptual image hashing with selective sampling for salient structure features
Qin, C., Chen, X., Dong, J., & Zhang, X. (2016) · Displays · doi:10.1016/j.displa.2016.09.003 · Cited by 56 · see citing works
Robust and Secure Image Fingerprinting Learned by Neural Network
Li, Y., Wang, D., & Tang, L. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2890966 · Cited by 52 · see citing works
Perceptual Image Hashing With Locality Preserving Projection for Copy Detection
Huang, Z., Tang, Z., Zhang, X., Ruan, L., & Zhang, X. (2021) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2021.3136163 · Cited by 52 · see citing works
Perceptual Image Hashing Based on Weber Local Binary Pattern and Color Angle Representation
Qin, C., Hu, Y., Yao, H., Duan, X., & Gao, L. (2019) · IEEE Access · doi:10.1109/access.2019.2908029 · Cited by 44 · see citing works
A High-Performance Robust Reversible Data Hiding Algorithm Based on Polar Harmonic Fourier Moments
Ma, B., Tao, Z., Ma, R., et al. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3311483 · Cited by 39 · see citing works
Self-citationRobust image hashing with embedding vector variance of LLE
Tang, Z., Ruan, L., Qin, C., et al. (2015) · Digital Signal Processing · doi:10.1016/j.dsp.2015.05.002 · Cited by 31 · see citing works
Learning to Hash for Personalized Image Authentication
Su, Z., Yao, L., Mei, J., Zhou, L., & Li, W. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3002146 · Cited by 27 · see citing works
Deep Perceptual Hash Based on Hash Center for Image Copyright Protection
Sun, X., & Zhou, J. (2022) · IEEE Access · doi:10.1109/access.2022.3221980 · Cited by 20 · cited 4× · see citing works
“The Research demonstrated that the time efficiency of the PRRN-enhanced perceptual hash generation algorithm exceeded that of the methods proposed by Qin et al. [10], Huang and Liu [25], Sun and Zhou [33], Ma et al. [36], Tang et al. [37], and Tang et al. [38].”
InfluentialMa, B., Wang, H., Xu, J., Wang, X., Li, X., & Li, J. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3508849 · Cited by 15 · see citing works
Self-citationContent-Based Image Copy Detection Using Convolutional Neural Network
Liu, X., Liang, J., Wang, Z., Tsai, Y.-T., Lin, C., & Chen, C.-C. (2020) · Electronics · doi:10.3390/electronics9122029 · Cited by 14 · see citing works
Perceptual Authentication Hashing for Digital Images With Contrastive Unsupervised Learning
Gao, G., Qin, C., Fang, Y., & Zhou, Y. (2023) · IEEE Multimedia · doi:10.1109/mmul.2023.3280669 · Cited by 14 · see citing works
Xiao, Y., Yan, C., Lyu, S., et al. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3227564 · Cited by 12 · see citing works
Robust Perceptual Image Hashing for Screen-Shooting Attack
Liu, T., Yao, H., Li, X., & Qin, C. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3324430 · Cited by 12 · see citing works
Self-citationPerceptual Hashing With Deep and Texture Features
Yu, M., Tang, Z., Liang, X., et al. (2024) · IEEE Multimedia · doi:10.1109/mmul.2024.3354998 · Cited by 12 · see citing works
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 · see citing works
A screen-shooting resilient data-hiding algorithm based on two-level singular value decomposition
Ma, B., Du, K., Xu, J., et al. (2023) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2023.103605 · Cited by 8 · see citing works
Self-citationHigh-Performance Optimization Framework for Reversible Data Hiding Predictor
Ma, B., Duan, H., Ma, R., et al. (2024) · IEEE Signal Processing Letters · doi:10.1109/lsp.2024.3512357 · Cited by 8 · see citing works
Self-citationPerceptual Image Hashing Using Random Forest for Content-based Image Retrieval
Sabahi, F., Ahmad, M. O., & Swamy, M. N. S. (2018) · IEEE International New Circuits and Systems Conference (NEWCAS) · doi:10.1109/newcas.2018.8585506 · Cited by 5 · see citing works
Perceptual Model Hashing: Towards Neural Network Model Authentication
Li, X., Wang, Z., Feng, G., Zhang, X., & Qin, C. (2022) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp55362.2022.9949087 · Cited by 3 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Nainar, M., Sankaranarayanan, S., & Veeramani, K. (2026) · Scientific Reports · doi:10.1038/s41598-026-54102-1
“Deep CNN hashing schemes and pre-trained transformer embeddings aim to align similarity computation with human perceptual judgment 19,20 .”
- Authors
- Yang, M., Qi, B., Ma, B., Xu, J., Xian, Y., & Li, X.
- Affiliations
- Qilu University of Technology (CN)
- Shandong University of Finance and Economics (CN)
- Beijing Jiaotong University (CN)
- Venue
- IEEE Internet of Things Journal
- Published
- 2025-07-15
- Volume
- 12
- Issue
- 14
- Pages
- 26456-26471
- ISSN
- 2327-4662 (ISSN-L)
- 2372-2541
- OpenAlex
- W4409473795
- Semantic Scholar
- 6adba0b05710f494e7361ca07793c914d7371d82
- Cited by
- 6
- References
- 35
- Citations by year
- 2026: 5 · 2025: 1
- FWCI
- 2.09
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Internet of Things Journal (publishedVersion)
- Funders
- Shandong Taishan Scholars Program (tstp20240829)
- National Natural Science Foundation of China (62272255, 62302248)
- Key Project of Nature Foundation of Shandong Province (ZR2022LZH011)
- Key Research and Development Projects of Shandong Province (2023CXGC010102, 2023TZXD049)
- Natural Science Foundation of Shandong Province (ZR2023QF018)
- Jinan “New 20 Universities” Innovation Team Introduction Project (202228016)
- Major Innovation Project of Science, Education and Industry Integration Pilot Project (2024ZDZX08)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- perceptual image hashing, texture distribution, ResNet, skip connections, attack resistance, Internet of Things forensics, image content representation, hash code generation
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
