Robust color image hashing using convolutional stacked denoising auto-encoders for image authentication

Paul, Madhumita; Thakuria, Arnab Jyoti; Karsh, Ram Kumar; Talukdar, Fazal A.

doi:10.1007/s00521-021-05956-1

Cited by 12 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, experiments were performed on CASIA Tampered image detection evaluation database [55], NITS Image hashing database [56], USC-SIPI Image database [57], and Ground Truth Database [58] for tampering detection and localization to check the ability of the proposed algorithm (4) A comparative analysis with different state-of-the-art techniques suggests the competitiveness of the proposed algorithm. The performance parameters such as the area under the ROC curve (AUC), truepositive rate (TPR), and false-positive rate (FPR) [59][60][61][62][63] are utilized to evaluate the algorithms…”

Section: The Following Are the Contributions Of The Proposed Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

A Secure and Robust Autoencoder-Based Perceptual Image Hashing for Image Authentication

Shaik

Karsh

Islam

et al. 2022

Wireless Communications and Mobile Computing

Self Cite

View full text Add to dashboard Cite

With the advancement of technology, it has become easier to modify or tamper with digital data effortlessly. In recent times, the image hashing algorithm has gained popularity for image authentication applications. In this paper, a convolutional stacked denoising autoencoder (CSDAE) is utilized for producing hash codes that are robust against different content preserving operations (CPOs). The CSDAE algorithm comprises mapping high-dimensional input data into hash codes while maintaining their semantic similarities. This implies that the images having similar content should have similar hash codes. To demonstrate the effectiveness of the model, the correlation between hash codes of semantically similar images has been evaluated. Subsequently, tampered localization is done by comparing the decoder output of the manipulated image with the hash of the actual image. Then, the localization ability of the model was measured by computing the f 1 scores between the predicted region and the original tampered region. Based on the comparative performance and receiver-operating characteristics (ROC) curve, we may conclude that the proposed hashing proposed algorithm provides improved performance compared to various state-of-the-art techniques.

show abstract

Section: The Following Are the Contributions Of The Proposed Algorithmmentioning

confidence: 99%

“…This is then passed to a decoder network that attempts to reconstruct the image. The decoder has five convolutional units, each of which comprises an upsampling layer [60]. Each of…”

Section: Fully Connected Autoencodermentioning

confidence: 99%

A Secure and Robust Autoencoder-Based Perceptual Image Hashing for Image Authentication

Shaik

Karsh

Islam

et al. 2022

Wireless Communications and Mobile Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…[19], Paul M et al[27], Mengzhu et al[35], Xing, H. et al[36]. The benefits and drawbacks of the methods are summarized in Tables II to V. The algorithms' evaluation and comparison have been done on identical datasets [41] ̶[44], the image sizes are from 256 × 256 to 1024 × 1024, and each comparison technique is simulated on the same computer's MATLAB R2022b platform.…”

mentioning

confidence: 99%

Content Authentication and Tampered Localization Using Ring Partition and CSLBP-Based Image Hashing

Shaik,

Karsh,

Islam

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In the present world, innovation, and creative thinking were pivotal in bringing about the digital revolution. As a result of consistent development in multimedia processing algorithms, altering the contents of digital images has become more accessible. Image hashing has been found to be one of the most suitable approaches for content authentication applications. A ring partition and center-symmetric local binary patterns (CSLBP) approach has been introduced in the work for generating image hash. Our ring-based statistical characteristics remain unchanged when an image is rotated at any angle. As a result, it provides rotation invariant property. CS-LBP considers pairs of symmetrically opposite pixels around the central pixel. This symmetric encoding captures texture information that is invariant to certain rotations. The tampered detection and localization are done by computing the hash correlation between the original and tampered images. The experimental findings demonstrate that the suggested image hashing method can provide desirable robustness and discrimination in all content preserving operations (CPO). In comparison to specific current schemes, the proposed method offers shorter hash length, improved classification performance, and reduced hash generation time. Geometric rectification used in the suggested method can identify tampering even when geometric adjustments occur instantly. The receiver operating characteristics (ROC) curve demonstrates that the suggested model exhibits superior performance compared to other cutting-edge techniques.

show abstract

RETRACTED ARTICLE: A review of hashing based image authentication techniques

Shaik

Karsh

Islam

et al. 2021

Multimed Tools Appl

View full text Add to dashboard Cite

Robust color image hashing using convolutional stacked denoising auto-encoders for image authentication

Cited by 12 publications

References 33 publications

A Secure and Robust Autoencoder-Based Perceptual Image Hashing for Image Authentication

A Secure and Robust Autoencoder-Based Perceptual Image Hashing for Image Authentication

Content Authentication and Tampered Localization Using Ring Partition and CSLBP-Based Image Hashing

RETRACTED ARTICLE: A review of hashing based image authentication techniques

Contact Info

Product

Resources

About