Search Results (184)

This paper addresses the problem of improving the robustness of image steganographic methods under lossy compression while preserving high perceptual quality and low computational complexity. The paper proposes an adaptive code-controlled steganographic method that enables spectrally selective embedding in the spatial domain through structured codewords. The proposed approach introduces block-level adaptivity in which the energy of the embedding codeword is dynamically selected according to the robustness characteristics of each image block. Instead of applying uniform embedding strength, the method determines the minimal codeword energy required to guarantee reliable message extraction under a predefined worst-case JPEG compression level. Experimental evaluation demonstrates that the proposed adaptive strategy significantly improves robustness to compression attacks while preserving high perceptual reliability and strong resistance to statistical steganalysis techniques. In particular, for JPEG quality factor (QF) = 50, the bit error rate is reduced to 1.25% while a high perceptual quality of 52.07 dB peak signal-to-noise ratio (PSNR) is achieved. For stronger attack conditions, QF = 20, the method achieves 6.6% bit errors with a PSNR of 47.7 dB. Overall, the proposed adaptive energy selection provides up to 22.68% fewer errors or up to 6.05 dB higher PSNR compared to the classical code-controlled steganographic method, confirming its effectiveness for practical steganographic applications. Full article

Autonomous systems are expanding rapidly, driving a demand for robust perception technologies capable of navigating challenging, unstructured environments. While urban autonomy has made significant progress, off-road environments pose unique challenges, including dynamic terrain and limited communication infrastructure. This research addresses these challenges by introducing a novel three-part solution for off-road autonomous vehicles. First, we present a large-scale off-road dataset curated to capture the visual complexity and variability of unstructured environments, providing a realistic training ground that supports improved model generalization. Second, we propose a Confusion-Aware Loss (CAL) that dynamically penalizes systematic misclassifications based on class-level confusion statistics. When combined with cross-entropy, CAL improves segmentation mean Intersection over Union (mIoU) on the off-road test set from 68.66% to 70.06% and achieves cross-domain gains of up to ~0.49% mIoU on the Cityscapes dataset. Third, leveraging semantic segmentation as an intermediate representation, we introduce a spatial overlay video encoding scheme that preserves high-fidelity RGB information in semantically critical regions while compressing non-essential background regions. Experimental results demonstrate Peak Signal-to-Noise Ratio (PSNR) improvements of up to +5 dB and Video Multi-Method Assessment Fusion (VMAF) gains of up to +40 points under lossy compression, enabling efficient and reliable off-road autonomous operation. This integrated approach provides a robust framework for real-time remote operation in bandwidth-constrained environments. Full article

In the field of intelligent inspection, high-definition video data collected by quadruped robot dogs face severe transmission and storage constraints. Although existing advanced lossy video coding standards can significantly improve compression efficiency, they inevitably introduce severe compression artifacts in low-bit-rate scenarios. To address this issue, this paper proposes a video decoding quality enhancement network named Video Quality Restoration Network (VQRNet), based on a dual-stream architecture. Specifically, the Local Feature Extraction component incorporates a Progressive Feature Fusion Module (PFFM) with a four-stage progressive structure. By integrating reparameterized convolution and attention mechanisms, PFFM focuses on capturing high-frequency texture details to repair small-scale distortions. Simultaneously, the Multi-Scale Lightweight Spatial Attention Module (MLSA) performs spatial feature recalibration, leveraging multi-scale convolution to adaptively identify and enhance key spatial regions, specifically addressing multi-scale distortion. In the Global Feature Extraction component, the State-Space Attention Module (SSAM) combines State-Space Models (SSMs) with attention mechanisms to capture long-range dependencies and contextual information, for large-scale distortions caused by high-intensity compression. To verify the performance of the proposed algorithm, a dedicated dataset comprising 20 real-world video sequences captured by quadruped robot dogs (partitioned into 15 training and 5 testing sequences) was constructed, and the VTM 23.4 reference software was employed to simulate compression degradation using four quantization parameters (QP 30, 35, 40, and 45). Experimental results demonstrate that VQRNet outperforms state-of-the-art quality enhancement methods in terms of core metrics, including PSNR and SSIM, specifically including MIRNet, NAFNet, TRRHA, and CTNet. In the QP = 30 scenario, VQRNet achieves an average PSNR of 40.33 dB, a significant improvement of 3.32 dB over the VTM 23.4 baseline (37.01 dB), while demonstrating significant advantages in computational complexity and parameter efficiency—requiring only 5.27 G FLOPs and 1.40 M parameters, with an average inference latency of only 11.82 ms per 128 × 128 patch. This work provides robust technical support for the efficient video perception of quadruped robot dogs. Full article

We derive a few extended versions of the Kraft inequality for information lossless finite-state encoders. The main basic contribution is in defining a notion of a Kraft matrix and in establishing the fact that a necessary condition for information losslessness of a finite-state encoder is that none of the eigenvalues of this matrix have modulus larger than unity, or equivalently, the spectral radius of the Kraft matrix cannot exceed one. We then derive several equivalent forms of this condition, which are based on well-known formulas for spectral radius. Even stronger results are presented for the important special case where the finite-state encoder is assumed irreducible. Finally, two extensions are outlined—one concerns the case of side information available to both encoder and decoder, and the other is for lossy compression. Full article

We derive a few extended versions of the Kraft inequality for lossy compression, which pave the way to the derivation of several refinements and extensions of the well-known Shannon lower bound in a variety of instances of rate-distortion coding. These refinements and extensions include sharper bounds for one-to-one codes and D-semifaithful codes, a Shannon lower bound for distortion measures based on sliding-window functions, and an individual-sequence counterpart of the Shannon lower bound. Full article

The advancements in communication and information technologies have substantially enabled the extensive distribution and modification of high-resolution color images. Although this accessibility provides many advantages, it also presents risks related to security. Specifically, when image modification is conducted with malicious intent, exceeding typical artistic or enhancement objectives, it can cause significant moral or economic harm to the image owner. To address this security requirement, this study presents an innovative semi-fragile watermarking algorithm designed specifically for high-resolution color images. The proposed method utilizes Discrete Cosine Transform domain watermarking implemented via Quantization Index Modulation with Dither Modulation. It incorporates several elements, such as convolutional encoding, a denoising convolutional neural network, and a very deep super-resolution neural network. This comprehensive strategy aims to provide ownership verification using a logo watermark, in conjunction with tamper detection and content self-recovery mechanisms. The self-recovery criterion is determined using a thumbnail image, created by downscaling to standard definition and applying JPEG2000 lossy compression. The resultant multifunctional design enhances the overall security of the information. Experimental validation confirms the enhanced imperceptibility, robustness, and capacity of the proposed method. Its efficacy was additionally corroborated through comparative analyses using contemporary state-of-the-art algorithms. Full article

The rapid advancement of imaging sensors and optical filters has significantly increased the number of spectral bands captured in hyperspectral images, leading to a substantial rise in data volume. This creates major challenges for data transmission and storage, making hyperspectral image compression a crucial area of research. Compression techniques can be either lossy or lossless, each employing distinct strategies to maximize efficiency. To provide a more focused and comprehensive analysis, this review concentrates exclusively on lossless compression, which is categorized into transform, prediction, and deep learning-based methods. Each category is systematically examined, with particular emphasis on the underlying principles and the strategies adopted to enhance compression performance. In addition to the core algorithms, encoding and scanning orders are also discussed, which is an essential aspect that is often overlooked in other reviews. By integrating these aspects into a unified framework, this paper offers an up-to-date and in-depth overview of the methodologies, trends, and challenges in lossless hyperspectral image compression. Full article

Traditional hyperspectral image compression methods often struggle to achieve high compression ratios while maintaining satisfactory reconstructed image quality under low-bitrate conditions. With the progressive development of deep learning, it has demonstrated significant advantages in lossy image compression research. Compared to visible light images, hyperspectral images possess rich spectral information. When directly applying visible light image compression models to hyperspectral image compression, the spectral information of hyperspectral images is overlooked, making it difficult to achieve optimal compression performance. In this paper, we combine the characteristics of hyperspectral images by extracting spatial and spectral features and performing fusion-based encoding and decoding to achieve end-to-end lossy compression of hyperspectral images. The structures of the encoding end and the decoding end are in symmetry. Additionally, attention mechanism is incorporated to enhance reconstruction quality. The proposed model is compared with the latest hyperspectral image compression standard algorithms to validate its effectiveness. Experimental results show that, under the same image quality, the proposed method reduces the bpp (bits per pixel) by 4.67% compared to CCSDS123.0-B-2 on the Harvard hyperspectral dataset while also decreasing the spectral angle loss by 13.68%, achieving better performance. Full article

Deep Neural Networks (DNNs) are the primary approach for enhancing the real-time performance and accuracy of Keyword Spotting (KWS) systems in speech processing. However, the exceptional performance of DNN-KWS faces significant challenges related to computational intensity and storage requirements, severely limiting its deployment on resource-constrained Internet of Things (IoT) edge devices. Researchers have sought to mitigate these demands by employing Binary Neural Networks (BNNs) through single-bit quantization, albeit at the cost of reduced recognition accuracy. From an information-theoretic perspective, binarization, as a form of lossy compression, increases the uncertainty (Shannon entropy) in the model’s output, contributing to the accuracy degradation. Unfortunately, even a slight accuracy degradation can trigger frequent false wake-ups in the KWS module, leading to substantial energy consumption in IoT devices. To address this issue, this paper proposes a novel Probability Smoothing Enhanced Binarized Neural Network (PSE-BNN) model that achieves a balance between computational complexity and accuracy, enabling efficient deployment on an FPGA platform. The PSE-BNN comprises two components: a preliminary recognition extraction module for extracting initial KWS features, and a result recognition module that leverages temporal correlation to denoise and enhance the quantized model’s features, thereby improving overall recognition accuracy by reducing the conditional entropy of the output distribution. Experimental results demonstrate that the PSE-BNN achieves a recognition accuracy of 97.29% on the Google Speech Commands Dataset (GSCD). Furthermore, deployed on the Xilinx VC707 hardware platform, the PSE-BNN utilizes only 1939 Look-Up Tables (LUTs), 832 Flip-Flops (FFs), and 234 Kb of storage. Compared to state-of-the-art BNN-KWS designs, the proposed method improves accuracy by 1.93% while reducing hardware resource usage by nearly 65%. The smoothing filter effectively suppresses noise-induced entropy, enhancing the signal-to-noise ratio (SNR) in the information transmission path. This demonstrates the significant potential of the PSE-BNN-FPGA design for resource-constrained edge IoT devices. Full article

With the widespread use of audio editing software and artificial intelligence, it has become very easy to forge audio files. One type of these forgeries is copy-move forgery, which is achieved by copying a segment from an audio file and placing it in a different place in the same file, where the aim is to take the speech content out of its context and alter its meaning. In practice, forged recordings are often disguised through post-processing steps such as lossy compression, additive noise, or median filtering. This distorts acoustic features and makes forgery detection more difficult. This study introduces a robust keypoint-based approach that analyzes Mel-spectrograms, which are visual time-frequency representations of audio. Instead of processing the raw waveform for forgery detection, the proposed method focuses on identifying duplicate regions by extracting distinctive visual patterns from the spectrogram image. We tested this approach on two speech datasets (Arabic and Turkish) under various real-world attack conditions. Experimental results show that the method outperforms existing techniques and achieves high accuracy, precision, recall, and F1-scores. These findings highlight the potential of visual-domain analysis to increase the reliability of audio forgery detection in forensic and communication contexts. Full article

Background: The growing demand for automated microorganism classification in the context of Laboratory 4.0 highlights the potential of convolutional neural networks (CNNs) for accurate and efficient image analysis. However, their effectiveness remains limited by the scarcity of large, labeled datasets. This study addresses a key gap in the literature by investigating how commonly used image preprocessing techniques, such as lossy compression, non-uniform scaling (typically applied to fit input images to CNN input layers), and data augmentation, affect the performance of CNNs in automated microorganism classification. Methods: Using two well-established CNN architectures, AlexNet and DenseNet-121, both frequently applied in biomedical image analysis, we conducted a series of computational experiments on a standardized dataset of high-resolution bacterial images. Results: Our results demonstrate under which conditions these preprocessing strategies degrade or improve CNN performance. Using the findings from this research to optimize hyperparameters and train the CNNs, we achieved classification accuracies of 98.61% with AlexNet and 99.82% with DenseNet-121, surpassing the performance reported in current state-of-the-art studies. Conclusions: This study advances laboratory digitalization by reducing data preparation effort, training time, and computational costs, while improving the accuracy of microorganism classification with deep learning. Its contributions also benefit broader biomedical fields such as automated diagnostics, digital pathology, clinical decision support, and point-of-care imaging. Full article

JPEG images are widely used in multimedia transmission, such as on social media platforms, owing to their efficiency for reducing storage and transmission requirements. However, because such images may contain sensitive information, encryption is essential to ensure data privacy. Traditional image encryption schemes face challenges when applied to JPEG images, as maintaining compatibility with the JPEG structure and managing the effects of lossy compression can distort encrypted data. Existing JPEG-compatible encryption methods, such as Encryption-then-Compression (EtC) and Compression-then-Encryption (CtE), typically employ a single encryption stage, either before or after compression, and often involve trade-offs between security, storage efficiency, and visual quality. In this work, an Encryption–Compression–Encryption algorithm is presented that preserves full JPEG compatibility while combining the advantages of both EtC and CtE schemes. In the proposed method, pixel-block encryption is first applied prior to JPEG compression, followed by selective coefficient encryption after compression, in which the quantized DC coefficient differences are permuted. Experimental results indicate that the second encryption stage enhances the entropy achieved in the first stage, with both stages complementing each other in terms of resistance to attacks. The addition of this second layer does not significantly impact storage efficiency or the visual quality of the decompressed image; however, it introduces a moderate increase in computational time due to the two-stage encryption process. Full article

With the rapid growth of data volume in sensor networks, lossy source coding systems achieve high–efficiency data compression with low distortion under limited transmission bandwidth. However, conventional compression algorithms rely on a two–stage framework with high computational complexity and frequently struggle to balance compression performance with generalization ability. To address these issues, an end–to–end lossy compression method is proposed in this paper. The approach integrates an enhanced belief propagation algorithm with a multi–layer perceptron neural network, aiming to introduce a novel joint optimization architecture described as “encoding–structured encoding–decoding”. In addition, a quantization module incorporating random perturbation and the straight–through estimator is designed to address the non–differentiability in the quantization process. Simulation results demonstrate that the proposed system significantly improves compression performance while offering superior generalization and reconstruction quality. Furthermore, the designed neural architecture is both simple and efficient, reducing system complexity and enhancing feasibility for practical deployment. Full article

The widespread deployment of large language models (LLMs) has raised urgent demands for verifiable content attribution and misuse mitigation. Existing text watermarking techniques often struggle in black-box or sampling-based scenarios due to limitations in robustness, imperceptibility, and detection generality. These challenges are particularly critical in open-access settings, where model internals and generation logits are unavailable for attribution. To address these limitations, we propose CWS (Contrastive Watermarking with Semantic Modeling)—a novel keyless watermarking framework that integrates contrastive semantic token selection and shared embedding space alignment. CWS enables context-aware, fluent watermark embedding while supporting robust detection via a dual-branch mechanism: a lightweight z-score statistical test for public verification and a GRU-based semantic decoder for black-box adversarial robustness. Experiments on GPT-2, OPT-1.3B, and LLaMA-7B over C4 and DBpedia datasets demonstrate that CWS achieves F1 scores up to 99.9% and maintains F1 ≥ 93% under semantic rewriting, token substitution, and lossy compression (ε ≤ 0.25, δ ≤ 0.2). The GRU-based detector offers a superior speed–accuracy trade-off (0.42 s/sample) over LSTM and Transformer baselines. These results highlight CWS as a lightweight, black-box-compatible, and semantically robust watermarking method suitable for practical content attribution across LLM architectures and decoding strategies. Furthermore, CWS maintains a symmetrical architecture between embedding and detection stages via shared semantic representations, ensuring structural consistency and robustness. This semantic symmetry helps preserve detection reliability across diverse decoding strategies and adversarial conditions. Full article

A composite source model consists of an intrinsic state and an extrinsic observation. The fundamental performance limit of reproducing the intrinsic state is characterized by the indirect rate–distortion function. In a remote classification application, a source encoder encodes the extrinsic observation (e.g., image) into bits, and a source decoder plays the role of a classifier that reproduces the intrinsic state (e.g., label of image). In this work, we characterize the general structure of the optimal transition probability distribution, achieving the indirect rate–distortion function. This optimal solution can be interpreted as a “soft classifier”, which generalizes the conventionally adopted “classify-then-compress” scheme. We then apply the soft classification to aid the lossy compression of the extrinsic observation of a composite source. This leads to a coding scheme that exploits the soft classifier to guide reproduction, outperforming existing coding schemes without classification or with hard classification. Full article