A Hybrid Steganography System based on LSB Matching and Replacement

Crowd counting considers one of the most significant and challenging issues in computer vision and deep learning communities, whose applications are being utilized for various tasks. While this issue is well studied, it remains an open challenge to manage perspective distortions and scale variations. How well these problems are resolved has a huge impact on predicting a high-quality crowd density map. In this study, a hybrid and modified deep neural network (U-ASD Net), based on U-Net and adaptive scenario discovery (ASD), is proposed to get precise and effective crowd counting. The U part is produced by replacing the nearest upsampling in the encoder of U-Net with max-unpooling. This modification provides a better crowd counting performance by capturing more spatial information. The max-unpooling layers upsample the feature maps based on the max locations held from the downsampling process. The ASD part is constructed with three light pathways, two of which have been learned to reflect various densities of the crowd and define the appropriate geometric configuration employing various sizes of the receptive field. The third pathway is an adaptation path, which implicitly discovers and models complex scenarios to recalibrate pathway-wise responses adaptively. ASD has no additional branches to avoid increasing the complexity. The designed model is end-to-end trainable. This integration provides an effective model to count crowds in both dense and sparse datasets. It also predicts an elevated quality density map with a high structural similarity index and a high peak signal-to-noise ratio. Several comprehensive experiments on four popular datasets for crowd counting have been carried out to demonstrate the proposed method's promising performance compared to other state-of-the-art approaches. The proposed model achieves the lowest count error in terms of the MAE in ShanghaiTech Part A, Part B, and Mall datasets with 64.6, 7.5, and 1.8, respectively. Moreover, it achieves the lowest count error in terms of the MSE in ShanghaiTech Part B, UCF CC 50, UCSD, and Mall datasets with 12.4, 217.8, 2.1, 2.2, respectively. In addition, the proposed model accomplishes the best quality density maps on all the utilized datasets. Furthermore, a new dataset with its manual annotations, called Haramain with three different scenes and different densities, is introduced and used for evaluating the U-ASD Net.

show abstract

“…Mathieu et al [44] argued that the PSNR is a better metric for assessing quality. The PSNR is defined as follows [45], [46]:…”

Section: A Evaluation Metricsmentioning

confidence: 99%

U-ASD Net: Supervised Crowd Counting Based on Semantic Segmentation and Adaptive Scenario Discovery

Hafeezallah

Al-Dhamari²,

Abu-Bakar

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…The LSBsubstitution increases and decreases or leave without changing (the bit of secret data is matching the LSB of cover image) of pixels value. In LSB-matching method, a secret data is embedded of cover image if the LSB of the cover image pixel matches the bit of secret data, no occurred changing, otherwise increases and decreases of pixels value (Ker, 2005;Hiary et al, 2016).…”

Section: Lsb Steganography Techniquementioning

confidence: 99%

A Multiple-Chaotic Approach for Steganography

Alwan¹,

Hussain²

2019

Journal of Computer Science

View full text Add to dashboard Cite

In a recent work, chaos has been utilized to modify addresses of message bits while hidden in a cover image. In this study, we extend the above technique to include multiple chaotic maps for increased security. Three systems have been modified using chaotic-address mapping for image steganography in the spatial domain. The first system, the well-known LSB technique, is based on the selection of pixels and then hides secret message in the Least Significant Bits LSBs of the given pixel. The second system is based on searching for the identical bits between the secret message and the cover image. The third system is based on the concept of LSB substitution. It employs mapping of secret data bits onto the cover pixel bits. To increase the security performance of the above chaos-based steganographic techniques, multiple-chaotic maps are introduced in this study by using multiple formulas to generate chaotic sequences used to track the addresses of shuffled bits. The generated chaotic sequences were evaluated to determine the randomness (using correlation tests) and the chaotic characteristics of a nonlinear system (using Lyapunov exponent, Poincaré section and 0-1 test). The performance and security levels of the proposed techniques were evaluated by using Peak Signal-to-Noise Ratio (PSNR), Mean Square Error (MSE), histogram analysis and correlative analysis. The results show that the proposed method performs existing systems.

show abstract

“…Initially introduced by Mielikainen in 2006, the LSB matching method [10][11][12][13][14] embeds messages by altering the least significant bit (LSB) of the cover pixel. This technique, also recognized as ± embedding, adjusts the pixel value by randomly adding or subtracting one to ensure the message bit aligns with the cover pixel's LSB when they do not match.…”

Section: Introductionmentioning

confidence: 99%

“…Such a strategy is designed to minimize pixel value alterations, thereby reducing the image distortion. After Mielikainen's foundational LSB matching approach, various methods [11][12][13][14] have emerged that enhance the technique's utility and application.…”

Section: Introductionmentioning

confidence: 99%

Advanced Dual Reversible Data Hiding: A Focus on Modification Direction and Enhanced Least Significant Bit (LSB) Approaches

Kim,

Cavazos Quero,

Jung

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In this study, we investigate advances in reversible data hiding (RDH), a critical area in the era of widespread digital data sharing. Recognizing the inherent vulnerabilities such as unauthorized access and data corruption during data transmission, we introduce an innovative dual approach to RDH. We use the EMD (Exploiting Modification Direction) method along with an optimized LSB (Least Significant Bit) replacement strategy. This dual method, applied to grayscale images, has been carefully developed to improve data hiding by focusing on modifying pixel pairs. Our approach sets new standards for achieving a balance between high data embedding rates and the integrity of visual quality. The EMD method ensures that each secret digit in a 5-ary notational system is hidden by 2 cover pixels. Meanwhile, our LSB strategy finely adjusts the pixels selected by EMD to minimize data errors. Despite its simplicity, this approach has been proven to outperform existing technologies. It offers a high embedding rate (ER) while maintaining the high visual quality of the stego images. Moreover, it significantly improves data hiding capacity. This enables the full recovery of the original image without increasing file size or adding unnecessary data, marking a significant breakthrough in data security.

show abstract

A Hybrid Steganography System based on LSB Matching and Replacement

Cited by 8 publications

References 37 publications

U-ASD Net: Supervised Crowd Counting Based on Semantic Segmentation and Adaptive Scenario Discovery

U-ASD Net: Supervised Crowd Counting Based on Semantic Segmentation and Adaptive Scenario Discovery

A Multiple-Chaotic Approach for Steganography

Advanced Dual Reversible Data Hiding: A Focus on Modification Direction and Enhanced Least Significant Bit (LSB) Approaches

Contact Info

Product

Resources

About