Filters








19,421 Hits in 9.3 sec

A Subject-Sensitive Perceptual Hash Based on MUM-Net for the Integrity Authentication of High Resolution Remote Sensing Images

Kaimeng Ding, Yueming Liu, Qin Xu, Fuqiang Lu
2020 ISPRS International Journal of Geo-Information  
To achieve subject-sensitive perceptual hash, we propose a new deep convolutional neural network architecture, named MUM-Net, for extracting robust features of HRRS images.  ...  The robust features extracted by MUM-Net are further compressed and encoded to obtain the perceptual hash sequence of HRRS image.  ...  The edge features extracted by the method in [13] obviously lack a lot of subtle edge features, which greatly improves the robustness of the algorithm.  ... 
doi:10.3390/ijgi9080485 fatcat:qy4bp5pymbgx3drfbefgouvelm

An Improved Perceptual Hash Algorithm Based on U-Net for the Authentication of High-Resolution Remote Sensing Image

Kaimeng Ding, Zedong Yang, Yingying Wang, Yueming Liu
2019 Applied Sciences  
The proposed method consists of a modified U-net model to extract robust feature and a principal component analysis (PCA)-based encoder to generate perceptual hash values for HRRS images.  ...  Moreover, to improve the performance of the network, exponential linear unit (ELU) and batch normalization (BN) are applied to extract more robust and accurate edge feature.  ...  All authors reviewed the manuscript. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app9152972 fatcat:7ltqjctjubbybh4g2whjs6gwqa

Robust image hashing with compressed sensing and ordinal measures

Zhenjun Tang, Hanyun Zhang, Shenglian Lu, Heng Yao, Xianquan Zhang
2020 EURASIP Journal on Image and Video Processing  
This hashing method uses a visual attention model called Itti model and Canny operator to construct an image representation, and exploits CS to extract compact features from the representation.  ...  Finally, the CS-based compact features are quantized via ordinal measures. L2 norm is used to judge similarity of hashes produced by the proposed hashing method.  ...  Acknowledgements The authors would like to thank the anonymous referees for their helpful comments and suggestions, and Miss M. Sun [29] for sharing their code for comparison.  ... 
doi:10.1186/s13640-020-00509-3 fatcat:vqxzlhjipfapxg3kthsnioptie

Semi-U-Net: A Lightweight Deep Neural Network for Subject-sensitive Hashing of HRRS Images

Kaimeng Ding, Shoubao Su, Nan Xu, Tingting Jiang
2021 IEEE Access  
use the same subject-sensitive hashing algorithm process except for the different models for extracting perceptual features.  ...  For subject-sensitive hashing, the function of the deep neural network model is to extract perceptual features for integrity authentication, not for visual effects.  ... 
doi:10.1109/access.2021.3074055 fatcat:5iaxv3babjduvi7had44ammvqy

AAU-Net: Attention-Based Asymmetric U-Net for Subject-Sensitive Hashing of Remote Sensing Images

Kaimeng Ding, Shiping Chen, Yu Wang, Yueming Liu, Yue Zeng, Jin Tian
2021 Remote Sensing  
In this paper, we propose a novel attention-based asymmetric U-Net (AAU-Net) for the subject-sensitive hashing of remote sensing (RS) images.  ...  On the basis of AAU-Net, a subject-sensitive hashing algorithm is developed to integrate the features of various bands of RS images.  ...  The most prominent performance is that for operations that only change one band, for which the robustness of our algorithm is greatly improved.  ... 
doi:10.3390/rs13245109 fatcat:5ly4tcoyqrghjh3lwrlwgx5bfa

Coverless image steganography based on DenseNet feature mapping

Qiang Liu, Xuyu Xiang, Jiaohua Qin, Yun Tan, Yao Qiu
2020 EURASIP Journal on Image and Video Processing  
Towards this goal, a CIS algorithm based on DenseNet feature mapping is proposed. Deep learning is introduced to extract high-dimensional CNN features which are mapped into hash sequences.  ...  For the sender, a binary tree hash index is built to accelerate index speed of searching hidden information and DenseNet hash sequence, and then, all matched images are sent.  ...  Availability of data and materials Please contact author for data requests.  ... 
doi:10.1186/s13640-020-00521-7 fatcat:fleebo5yyrdxpdzqruglc5dfsu

An Encrypted Speech Retrieval Method Based on Deep Perceptual Hashing and CNN-BiLSTM

Qiuyu Zhang, Yuzhou Li, Yinjie Hu, Xuejiao Zhao
2020 IEEE Access  
Firstly, the proposed method extracts the Log-Mel Spectrogram/MFCC features of the original speech and enters the CNN and BiLSTM networks in turn for model training.  ...  Since convolutional neural network (CNN) can only extract local features, and long short-term memory (LSTM) neural network model has a large number of learning calculations, a long processing time and  ...  [24] proposed a CNN-BiLSTM hybrid structure to extract the spatiotemporal features of speech, which could improve the performance of continuous speech recognition. Székely et al.  ... 
doi:10.1109/access.2020.3015876 fatcat:g7tygoebores7c6mwdydfnydkq

CNN Feature-Based Image Copy Detection with Contextual Hash Embedding

Zhili Zhou, Meimin Wang, Yi Cao, Yuecheng Su
2020 Mathematics  
The traditional content-based copy detection methods usually extract local hand-crafted features and then quantize these features to visual words by the bag-of-visual-words (BOW) model to build an inverted  ...  As one of the important techniques for protecting the copyrights of digital images, content-based image copy detection has attracted a lot of attention in the past few decades.  ...  To extract more robust CNN features, one of feasible solutions is to train a proper CNN model with a transfer learning technique for feature extraction.  ... 
doi:10.3390/math8071172 fatcat:vjyoba2tfbbm3nrz7uzkdndauy

An Encrypted Speech Retrieval Scheme Based on Long Short-Term Memory Neural Network and Deep Hashing

2020 KSII Transactions on Internet and Information Systems  
Secondly, the integrated LSTM network model and deep hashing algorithm are used to extract high-level features of speech data.  ...  Due to the explosive growth of multimedia speech data, how to protect the privacy of speech data and how to efficiently retrieve speech data have become a hot spot for researchers in recent years.  ...  The authors also gratefully acknowledge the helpful comments and suggestions of the reviewers, which have improved the presentation.  ... 
doi:10.3837/tiis.2020.06.016 fatcat:alfme7ukibd3tjgxswt3xvprxe

An Improved Hashing Method for the Detection of Image Forgery

Anupama K. Abraham, Rosna P. Haroon
2014 IOSR Journal of Computer Engineering  
Here, we are proposing an improved hashing method for the detection of Copy-move forgery detection and Spliced Image Detection.  ...  We can ensure the credibility of an image with a hashing method by fusing local and global features together. So that it is possible to detect even sensitive image forgeries.  ...  An Improved Hashing Method for the Detection of Image Forgery www.iosrjournals.org  ... 
doi:10.9790/0661-16531319 fatcat:6xkkgngz75hh3ptigi5bqroega

Robust Hashing for Image-based Malware Classification

Wei-Chung Huang, Fabio Di Troia, Mark Stamp
2018 Proceedings of the 15th International Joint Conference on e-Business and Telecommunications  
For both the SVM and robust hashing approaches, we treat each executable file as a two-dimensional image.  ...  Robust Hashing for Image-based Malware Classification.  ...  models, for example, would fit naturally within a robust hashing framework.  ... 
doi:10.5220/0006942206170625 dblp:conf/icete/HuangTS18 fatcat:jf4coyewkzhsdpmiegqqljkhlq

Robust Image Hashing with Low-Rank Representation and Ring Partition

Zhenjun Tang, Zixuan Yu, Zhixin Li, Chunqiang Yu, Xianquan Zhang
2020 Wireless Communications and Mobile Computing  
The results demonstrate that the proposed hashing can reach a good balance between robustness and discrimination and is superior to some state-of-the-art hashing algorithms in terms of the area under the  ...  The proposed hashing finds the saliency map by the spectral residual model and exploits it to construct the visual representation of the preprocessed image.  ...  Acknowledgments This work is partially supported by the National Natural Science Foundation of China (61962008, 61762017, and 61966004), the Guangxi "Bagui Scholar" Team for Innovation and Research, the  ... 
doi:10.1155/2020/8870467 fatcat:zbemnfv5ivhilatos5xffux4wy

Coverless Image Steganography: A Survey

Jiaohua Qin, Yuanjing Luo, Xuyu Xiang, Yun Tan, Huajun Huang
2019 IEEE Access  
, feature extraction, generation of hash sequence and mapping relationships.  ...  Therefore, it radically resist the detection of steganalysis tools and significantly improves the security of the image.  ...  And then, for each image in the database, its hash sequence is generated by a robust hashing algorithm.  ... 
doi:10.1109/access.2019.2955452 fatcat:uu7wjgrolndlvp2he2rpescyfq

Perceptual Image Hashing Based on Multitask Neural Network

Cheng Xiong, Enli Liu, Xinran Li, Heng Yao, Lei Zhang, Chuan Qin, Beijing Chen
2021 Security and Communication Networks  
hash sequence and used prepart of network of pretrained VGG-19 model to extract image features, and then, the image features are transformed into a hash sequence through a convolutional and fully connected  ...  In order to further improve the performance of image hashing and enhance the protection of image data, we proposed an end-to-end dual-branch multitask neural network based on VGG-19 to produce a perceptual  ...  In order to improve the applicability of the neural network model to multiple scenarios and use an excellent pretrained model, based on the pretrained model of VGG-19 neural network, we added a dual-branch  ... 
doi:10.1155/2021/8297244 fatcat:h6qdtkg4xbhcza5xmsvxpzezly

A Review of Hashing based Image Copy Detection Techniques

Mayank Srivastava, Jamshed Siddiqui, Mohammad Athar Ali
2019 Cybernetics and Information Technologies  
In this approach, a hash is constructed by using a set of unique features extracted from the image for identification.  ...  This article provides a comprehensive review of the state-of-the-art image hashing techniques.  ...  Next, the unique features of the image are extracted by using any of the feature extraction mechanisms like DCT. Lastly, extracted features are compressed to form a binary hash, H.  ... 
doi:10.2478/cait-2019-0012 fatcat:tsve3y6tvjccditagetoxkerse
« Previous Showing results 1 — 15 out of 19,421 results