Mohiul Islam
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohiul Islam has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Abdul Subhani Shaik
Department of ECE, National Institute of Technology Silchar, Assam, India
2 shared publications Om Prakash Singh
1 shared publicationRabul Hussain Laskar
1 shared publicationRam K. Karsh
Department of Electronics and Communication Engineering, National Institute of Technology (NIT) Silchar, Silchar, Assam, India
1 shared publication- Ram Kumar Karsh
National Institute of Technology Silchar
1 shared publication Saharul Alom Barlaskar
1 shared publication
Latest Publications
- Open Access
- 16 May 2026
- Published by Elsevier in Franklin Open
- Vol. 16
Tensor-based color image decomposition in an advanced hybrid IWT-SVD framework for digital watermarking
- 16 May 2026
- Published by Elsevier in Franklin Open
- Vol. 16
Open AccessTensor-based color image decomposition in an advanced hybrid IWT-SVD framework for digital watermarking
- Open Access
- 8 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 126791-126802
Content Authentication and Tampered Localization Using Ring Partition and CSLBP-Based Image Hashing
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.
- 8 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 126791-126802
Open AccessContent Authentication and Tampered Localization Using Ring Partition and CSLBP-Based Image Hashing
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.
- Open Access
- 1 January 2022
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2022 (1)
A Secure and Robust Autoencoder‐Based Perceptual Image Hashing for Image Authentication
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 f1 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.
- 1 January 2022
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2022 (1)
Open AccessA Secure and Robust Autoencoder‐Based Perceptual Image Hashing for Image Authentication
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 f1 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.