Khan Muhammad

Md Tanvir Islam, Nasir Rahim, Saeed Anwar et al.

Reducing the atmospheric haze and enhancing image clarity is crucial for computer vision applications. The lack of real-life hazy ground truth images necessitates synthetic datasets, which often lack diverse haze types, impeding effective haze type classification and dehazing algorithm selection. This research introduces the HazeSpace2M dataset, a collection of over 2 million images designed to enhance dehazing through haze type classification. HazeSpace2M includes diverse scenes with 10 haze intensity levels, featuring Fog, Cloud, and Environmental Haze (EH). Using the dataset, we introduce a technique of haze type classification followed by specialized dehazers to clear hazy images. Unlike conventional methods, our approach classifies haze types before applying type-specific dehazing, improving clarity in real-life hazy images. Benchmarking with state-of-the-art (SOTA) models, ResNet50 and AlexNet achieve 92.75\% and 92.50\% accuracy, respectively, against existing synthetic datasets. However, these models achieve only 80% and 70% accuracy, respectively, against our Real Hazy Testset (RHT), highlighting the challenging nature of our HazeSpace2M dataset. Additional experiments show that haze type classification followed by specialized dehazing improves results by 2.41% in PSNR, 17.14% in SSIM, and 10.2\% in MSE over general dehazers. Moreover, when testing with SOTA dehazing models, we found that applying our proposed framework significantly improves their performance. These results underscore the significance of HazeSpace2M and our proposed framework in addressing atmospheric haze in multimedia processing. Complete code and dataset is available on \href{https://github.com/tanvirnwu/HazeSpace2M} {\textcolor{blue}{\textbf{GitHub}}}.

Md Tanvir Islam, Inzamamul Alam, Simon S. Woo et al.

Low-light image enhancement (LLIE) is essential for numerous computer vision tasks, including object detection, tracking, segmentation, and scene understanding. Despite substantial research on improving low-quality images captured in underexposed conditions, clear vision remains critical for autonomous vehicles, which often struggle with low-light scenarios, signifying the need for continuous research. However, paired datasets for LLIE are scarce, particularly for street scenes, limiting the development of robust LLIE methods. Despite using advanced transformers and/or diffusion-based models, current LLIE methods struggle in real-world low-light conditions and lack training on street-scene datasets, limiting their effectiveness for autonomous vehicles. To bridge these gaps, we introduce a new dataset LoLI-Street (Low-Light Images of Streets) with 33k paired low-light and well-exposed images from street scenes in developed cities, covering 19k object classes for object detection. LoLI-Street dataset also features 1,000 real low-light test images for testing LLIE models under real-life conditions. Furthermore, we propose a transformer and diffusion-based LLIE model named "TriFuse". Leveraging the LoLI-Street dataset, we train and evaluate our TriFuse and SOTA models to benchmark on our dataset. Comparing various models, our dataset's generalization feasibility is evident in testing across different mainstream datasets by significantly enhancing images and object detection for practical applications in autonomous driving and surveillance systems. The complete code and dataset is available on https://github.com/tanvirnwu/TriFuse.

Inzamamul Alam, Md Tanvir Islam, Khan Muhammad et al.

Watermarking embeds imperceptible patterns into images for authenticity verification. However, existing methods often lack robustness against various transformations primarily including distortions, image regeneration, and adversarial perturbation, creating real-world challenges. In this work, we introduce SpecGuard, a novel watermarking approach for robust and invisible image watermarking. Unlike prior approaches, we embed the message inside hidden convolution layers by converting from the spatial domain to the frequency domain using spectral projection of a higher frequency band that is decomposed by wavelet projection. Spectral projection employs Fast Fourier Transform approximation to transform spatial data into the frequency domain efficiently. In the encoding phase, a strength factor enhances resilience against diverse attacks, including adversarial, geometric, and regeneration-based distortions, ensuring the preservation of copyrighted information. Meanwhile, the decoder leverages Parseval's theorem to effectively learn and extract the watermark pattern, enabling accurate retrieval under challenging transformations. We evaluate the proposed SpecGuard based on the embedded watermark's invisibility, capacity, and robustness. Comprehensive experiments demonstrate the proposed SpecGuard outperforms the state-of-the-art models. To ensure reproducibility, the full code is released on \href{https://github.com/inzamamulDU/SpecGuard_ICCV_2025}{\textcolor{blue}{\textbf{GitHub}}}.

Hassan Abid, Khan Muhammad, Muhammad Haris Khan

Effective waste sorting is critical for sustainable recycling, yet AI research in this domain continues to lag behind commercial systems due to limited datasets and reliance on legacy object detectors. In this work, we advance AI-driven waste detection by establishing strong baselines and introducing an ensemble-based semi-supervised learning framework. We first benchmark state-of-the-art Open-Vocabulary Object Detection (OVOD) models on the real-world ZeroWaste dataset, demonstrating that while class-only prompts perform poorly, LLM-optimized prompts significantly enhance zero-shot accuracy. Next, to address domain-specific limitations, we fine-tune modern transformer-based detectors, achieving a new baseline of 51.6 mAP. We then propose a soft pseudo-labeling strategy that fuses ensemble predictions using spatial and consensus-aware weighting, enabling robust semi-supervised training. Applied to the unlabeled ZeroWaste-s subset, our pseudo-annotations achieve performance gains that surpass fully supervised training, underscoring the effectiveness of scalable annotation pipelines. Our work contributes to the research community by establishing rigorous baselines, introducing a robust ensemble-based pseudo-labeling pipeline, generating high-quality annotations for the unlabeled ZeroWaste-s subset, and systematically evaluating OVOD models under real-world waste sorting conditions. Our code is available at: https://github.com/h-abid97/robust-waste-detection.

Tanveer Hussain, Saeed Anwar, Amin Ullah et al.

Salient Object Detection (SOD) domain using RGB-D data has lately emerged with some current models' adequately precise results. However, they have restrained generalization abilities and intensive computational complexity. In this paper, inspired by the best background/foreground separation abilities of deformable convolutions, we employ them in our Densely Deformable Network (DDNet) to achieve efficient SOD. The salient regions from densely deformable convolutions are further refined using transposed convolutions to optimally generate the saliency maps. Quantitative and qualitative evaluations using the recent SOD dataset against 22 competing techniques show our method's efficiency and effectiveness. We also offer evaluation using our own created cross-dataset, surveillance-SOD (S-SOD), to check the trained models' validity in terms of their applicability in diverse scenarios. The results indicate that the current models have limited generalization potentials, demanding further research in this direction. Our code and new dataset will be publicly available at https://github.com/tanveer-hussain/EfficientSOD

Mabrook S. Al-Rakhami, Abdu Gumaei1, Meteb Altaf et al.

Fall prevalence is high among elderly people, which is challenging due to the severe consequences of falling. This is why rapid assistance is a critical task. Ambient assisted living (AAL) uses recent technologies such as 5G networks and the internet of medical things (IoMT) to address this research area. Edge computing can reduce the cost of cloud communication, including high latency and bandwidth use, by moving conventional healthcare services and applications closer to end-users. Artificial intelligence (AI) techniques such as deep learning (DL) have been used recently for automatic fall detection, as well as supporting healthcare services. However, DL requires a vast amount of data and substantial processing power to improve its performance for the IoMT linked to the traditional edge computing environment. This research proposes an effective fall detection framework based on DL algorithms and mobile edge computing (MEC) within 5G wireless networks, the aim being to empower IoMT-based healthcare applications. We also propose the use of a deep gated recurrent unit (DGRU) neural network to improve the accuracy of existing DL-based fall detection methods. DGRU has the advantage of dealing with time-series IoMT data, and it can reduce the number of parameters and avoid the vanishing gradient problem. The experimental results on two public datasets show that the DGRU model of the proposed framework achieves higher accuracy rates compared to the current related works on the same datasets.

Ahmed Alghamdi, Mohamed Hammad, Hassan Ugail et al.

. In this paper, an effective computer-aided diagnosis (CAD) system is presented to detect MI signals using the convolution neural network (CNN) for urban healthcare in smart cities. Two types of transfer learning techniques are employed to retrain the pre-trained VGG-Net (Fine-tuning and VGG-Net as fixed feature extractor) and obtained two new networks VGG-MI1 and VGG-MI2. In the VGG-MI1 model, the last layer of the VGG-Net model is replaced with a specific layer according to our requirements and various functions are optimized to reduce overfitting. In the VGG-MI2 model, one layer of the VGG-Net model is selected as a feature descriptor of the ECG images to describe it with informative features. Considering the limited availability of dataset, ECG data is augmented which has increased the classification performance. Physikalisch-technische bundesanstalt (PTB) Diagnostic ECG database is used for experimentation, which has been widely employed in MI detection studies. In case of using VGG-MI1, we achieved an accuracy, sensitivity, and specificity of 99.02%, 98.76%, and 99.17%, respectively and we achieved an accuracy of 99.22%, a sensitivity of 99.15%, and a specificity of 99.49% with VGG-MI2 model. Experimental results validate the efficiency of the proposed system in terms of accuracy sensitivity, and specificity.

Khan Muhammad, Jamil Ahmad, Haleem Farman et al.

Image Steganography is a growing research area of information security where secret information is embedded in innocent-looking public communication. This paper proposes a novel crystographic technique for grayscale images in spatial domain. The secret data is encrypted and shuffled using pattern based bits shuffling algorithm (PBSA) and a secret key. The encrypted data is then embedded in the cover image using magic least significant bit (M-LSB) method. Experimentally, the proposed method is evaluated by qualitative and quantitative analysis which validates the effectiveness of the proposed method in contrast to several state-of-the-art methods.

Khan Muhammad

Addressing the security concerns in wireless sensor networks (WSN) is a challenging task, which has attracted the attention of many researchers from the last few decades. Researchers have presented various schemes in WSN, addressing the problems of processing, bandwidth, load balancing, and efficient routing. However, little work has been done on security aspects of WSN. In a typical WSN network, the tiny nodes installed on different locations sense the surrounding environment, send the collected data to their neighbors, which in turn is forwarded to a sink node. The sink node aggregate the data received from different sensors and send it to the base station for further processing and necessary actions. In highly critical sensor networks such as military and law enforcement agencies networks, the transmission of such aggregated data via the public network Internet is very sensitive and vulnerable to various attacks and risks. Therefore, this paper provides a solution for addressing these security issues based on steganography, where the aggregated data can be embedded as a secret message inside an innocent-looking cover image. The stego image containing the embedded data can be then sent to fusion center using Internet. At the fusion center, the hidden data is extracted from the image, the required processing is performed and decision is taken accordingly. Experimentally, the proposed method is evaluated by objective analysis using peak signal-to-noise ratio (PSNR), mean square error (MSE), normalized cross correlation (NCC), and structural similarity index metric (SSIM), providing promising results in terms of security and image quality, thus validating its superiority.

Khan Muhammad, Jamil Ahmad, Muhammad Sajjad et al.

Information security is one of the most challenging problems in today's technological world. In order to secure the transmission of secret data over the public network (Internet), various schemes have been presented over the last decade. Steganography combined with cryptography, can be one of the best choices for solving this problem. This paper proposes a new steganographic method based on gray-level modification for true colour images using image transposition, secret key and cryptography. Both the secret key and secret information are initially encrypted using multiple encryption algorithms (bitxor operation, bits shuffling, and stego key-based encryption); these are, subsequently, hidden in the host image pixels. In addition, the input image is transposed before data hiding. Image transposition, bits shuffling, bitxoring, stego key-based encryption, and gray-level modification introduce five different security levels to the proposed scheme, making the data recovery extremely difficult for attackers. The proposed technique is evaluated by objective analysis using various image quality assessment metrics, producing promising results in terms of imperceptibility and security. Moreover, the high quality stego images and its minimal histogram changeability, also validate the effectiveness of the proposed approach.

Khan Muhammad, Irfan Mehmood, Mi Young Lee et al.

Image classification is an enthusiastic research field where large amount of image data is classified into various classes based on their visual contents. Researchers have presented various low-level features-based techniques for classifying images into different categories. However, efficient and effective classification and retrieval is still a challenging problem due to complex nature of visual contents. In addition, the traditional information retrieval techniques are vulnerable to security risks, making it easy for attackers to retrieve personal visual contents such as patients records and law enforcement agencies databases. Therefore, we propose a novel ontology-based framework using image steganography for secure image classification and information retrieval. The proposed framework uses domain-specific ontology for mapping the low-level image features to high-level concepts of ontologies which consequently results in efficient classification. Furthermore, the proposed method utilizes image steganography for hiding the image semantics as a secret message inside them, making the information retrieval process secure from third parties. The proposed framework minimizes the computational complexity of traditional techniques, increasing its suitability for secure and real-time visual contents retrieval from personalized image databases. Experimental results confirm the efficiency, effectiveness, and security of the proposed framework as compared with other state-of-the-art systems.

Khan Muhammad, Zahoor Jan, Jamil Ahmad et al.

Wireless Sensor Networks (WSNs) are memory and bandwidth limited networks whose main goals are to maximize the network lifetime and minimize the energy consumption and transmission cost. To achieve these goals, dif ferent techniques of compression and clustering have been used. However, security is an open and major issue in WSNs for which different approaches are used, both in centralized and distributed WSNs' environments. This paper presents an adaptive cryptographic scheme for secure transmission of various sensitive parameters, sensed by wireless sensors to the fusion center for further processing in WSNs such as military networks. The proposed method encrypts the sensitive captured data of sensor nodes using various encryption procedures (bitxor operation, bits shuffling, and secret key based encryption) and then sends it to the fusion center. At the fusion center, the received encrypted data is decrypted for taking further necessary actions. The experimental results with complexity analysis, validate the effectiveness and feasibility of the proposed method in terms of security in WSNs.

Khan Muhammad, Muhammad Sajjad, Irfan Mehmood et al.

Image Steganography is a thriving research area of information security where secret data is embedded in images to hide its existence while getting the minimum possible statistical detectability. This paper proposes a novel magic least significant bit substitution method (M-LSB-SM) for RGB images. The proposed method is based on the achromatic component (I-plane) of the hue-saturation-intensity (HSI) color model and multi-level encryption (MLE) in the spatial domain. The input image is transposed and converted into an HSI color space. The I-plane is divided into four sub-images of equal size, rotating each sub-image with a different angle using a secret key. The secret information is divided into four blocks, which are then encrypted using an MLE algorithm (MLEA). Each sub-block of the message is embedded into one of the rotated sub-images based on a specific pattern using magic LSB substitution. Experimental results validate that the proposed method not only enhances the visual quality of stego images but also provides good imperceptibility and multiple security levels as compared to several existing prominent methods.

Khan Muhammad, Jamil Ahmad, Haleem Farman et al.

Image Steganography is the process of embedding text in images such that its existence cannot be detected by Human Visual System (HVS) and is known only to sender and receiver. This paper presents a novel approach for image steganography using Hue-Saturation-Intensity (HSI) color space based on Least Significant Bit (LSB). The proposed method transforms the image from RGB color space to Hue-Saturation-Intensity (HSI) color space and then embeds secret data inside the Intensity Plane (I-Plane) and transforms it back to RGB color model after embedding. The said technique is evaluated by both subjective and Objective Analysis. Experimentally it is found that the proposed method have larger Peak Signal-to Noise Ratio (PSNR) values, good imperceptibility and multiple security levels which shows its superiority as compared to several existing methods

Khan Muhammad, Jamil Ahmad, Naeem Ur Rehman et al.

Information Security is a major concern in today's modern era. Almost all the communicating bodies want the security, confidentiality and integrity of their personal data. But this security goal cannot be achieved easily when we are using an open network like Internet. Steganography provides one of the best solutions to this problem. This paper represents a new Cyclic Steganographic T echnique (CST) based on Least Significant Bit (LSB) for true color (RGB) images. The proposed method hides the secret data in the LSBs of cover image pixels in a randomized cyclic manner. The proposed technique is evaluated using both subjective and objective analysis using histograms changeability, Peak Signal-to-Noise Ratio (PSNR) and Mean Square Error (MSE). Experimentally it is found that the proposed method gives promising results in terms of security, imperceptibility and robustness as compared to some existent methods and vindicates this new algorithm.