Sos С. Agaian

Chunyu Yuan, Dongfang Zhao, Sos S. Agaian

Skin cancer poses a significant public health challenge, necessitating efficient diagnostic tools. We introduce UCM-Net, a novel skin lesion segmentation model combining Multi-Layer Perceptrons (MLP) and Convolutional Neural Networks (CNN). This lightweight, efficient architecture, deviating from traditional UNet designs, dramatically reduces computational demands, making it ideal for mobile health applications. Evaluated on PH2, ISIC 2017, and ISIC 2018 datasets, UCM-Net demonstrates robust performance with fewer than 50KB parameters and requires less than 0.05 Giga Operations Per Second (GLOPs). Moreover, its minimal memory requirement is just 1.19MB in CPU environment positions. It is a potential benchmark for efficiency in skin lesion segmentation, suitable for deployment in resource-constrained settings. In order to facilitate accessibility and further research in the field, the UCM-Net source code is https://github.com/chunyuyuan/UCM-Net.

Vladimir Frants, Sos Agaian, Karen Panetta

Images captured in real-world applications in remote sensing, image or video retrieval, and outdoor surveillance suffer degraded quality introduced by poor weather conditions. Conditions such as rain and mist, introduce artifacts that make visual analysis challenging and limit the performance of high-level computer vision methods. For time-critical applications where a rapid response is necessary, it becomes crucial to develop algorithms that automatically remove rain, without diminishing the quality of the image contents. This article aims to develop a novel quaternion multi-stage multiscale neural network with a self-attention module called QSAM-Net to remove rain streaks. The novelty of this algorithm is that it requires significantly fewer parameters by a factor of 3.98, over prior methods, while improving visual quality. This is demonstrated by the extensive evaluation and benchmarking on synthetic and real-world rainy images. This feature of QSAM-Net makes the network suitable for implementation on edge devices and applications requiring near real-time performance. The experiments demonstrate that by improving the visual quality of images. In addition, object detection accuracy and training speed are also improved.

Adel Oulefki, Yassine Himeur, Thaweesak Trongtiraku et al.

Solar Photovoltaic (PV) is increasingly being used to address the global concern of energy security. However, hot spot and snail trails in PV modules caused mostly by crakes reduce their efficiency and power capacity. This article presents a groundbreaking methodology for automatically identifying and analyzing anomalies like hot spots and snail trails in Solar Photovoltaic (PV) modules, leveraging unsupervised sensing algorithms and 3D Augmented Reality (AR) visualization. By transforming the traditional methods of diagnosis and repair, our approach not only enhances efficiency but also substantially cuts down the cost of PV system maintenance. Validated through computer simulations and real-world image datasets, the proposed framework accurately identifies dirty regions, emphasizing the critical role of regular maintenance in optimizing the power capacity of solar PV modules. Our immediate objective is to leverage drone technology for real-time, automatic solar panel detection, significantly boosting the efficacy of PV maintenance. The proposed methodology could revolutionize solar PV maintenance, enabling swift, precise anomaly detection without human intervention. This could result in significant cost savings, heightened energy production, and improved overall performance of solar PV systems. Moreover, the novel combination of unsupervised sensing algorithms with 3D AR visualization heralds new opportunities for further research and development in solar PV maintenance.

Artyom M. Grigoryan, Sos S. Agaian, Karen Panetta

As the availability of imagery data continues to swell, so do the demands on transmission, storage and processing power. Processing requirements to handle this plethora of data is quickly outpacing the utility of conventional processing techniques. Transitioning to quantum processing and algorithms that offer promising efficiencies over conventional methods can address some of these issues. However, to make this transformation possible, fundamental issues of implementing real time Quantum algorithms must be overcome for crucial processes needed for intelligent analysis applications. For example, consider edge detection tasks which require time-consuming acquisition processes and are further hindered by the complexity of the devices used thus limiting feasibility for implementation in real-time applications. Convolution is another example of an operation that is essential for signal and image processing applications, where the mathematical operations consist of an intelligent mixture of multiplication and addition that require considerable computational resources. This paper studies a new paired transform-based quantum representation and computation of one-dimensional and 2-D signals convolutions and gradients. A new visual data representation is defined to simplify convolution calculations making it feasible to parallelize convolution and gradient operations for more efficient performance. The new data representation is demonstrated on multiple illustrative examples for quantum edge detection, gradients, and convolution. Furthermore, the efficiency of the proposed approach is shown on real-world images.

Vladimir Frants, Sos Agaian, Karen Panetta

Deploying deep neural networks on edge devices is often limited by the memory traffic and compute cost of dense linear operators. While quaternion neural networks improve parameter efficiency by coupling multiple channels through Hamilton products, they typically retain unstructured dense weights; conversely, structured matrices enable fast computation but are usually applied in the real domain. This paper introduces EdgeLDR, a practical framework for quaternion block-circulant linear and convolutional layers that combines quaternion channel mixing with block-circulant parameter structure and enables FFT-based evaluation through the complex adjoint representation. We present reference implementations of EdgeLDR layers and compare FFT-based computation against a naive spatial-domain realization of quaternion circulant products. FFT evaluation yields large empirical speedups over the naive implementation and keeps latency stable as block size increases, making larger compression factors computationally viable. We further integrate EdgeLDR layers into compact CNN and Transformer backbones and evaluate accuracy-compression trade-offs on 32x32 RGB classification (CIFAR-10/100, SVHN) and hyperspectral image classification (Houston 2013, Pavia University), reporting parameter counts and CPU/GPU latency. The results show that EdgeLDR layers provide significant compression with competitive accuracy.

Artyom M. Grigoryan, Sos S. Agaian

Over the past century, a correlation has been an essential mathematical technique utilized in engineering sciences, including practically every signal/image processing field. This paper describes an effective method of calculating the correlation function of signals and color images in quaternion algebra. We propose using the quaternions with a commutative multiplication operation and defining the corresponding correlation function in this arithmetic. The correlation between quaternion signals and images can be calculated by multiplying two quaternion DFTs of signals and images. The complexity of the correlation of color images is three times higher than in complex algebra.

Jitesh Joshi, Sos S. Agaian, Youngjun Cho

Remote photoplethysmography (rPPG) enables non-invasive extraction of blood volume pulse signals through imaging, transforming spatial-temporal data into time series signals. Advances in end-to-end rPPG approaches have focused on this transformation where attention mechanisms are crucial for feature extraction. However, existing methods compute attention disjointly across spatial, temporal, and channel dimensions. Here, we propose the Factorized Self-Attention Module (FSAM), which jointly computes multidimensional attention from voxel embeddings using nonnegative matrix factorization. To demonstrate FSAM's effectiveness, we developed FactorizePhys, an end-to-end 3D-CNN architecture for estimating blood volume pulse signals from raw video frames. Our approach adeptly factorizes voxel embeddings to achieve comprehensive spatial, temporal, and channel attention, enhancing performance of generic signal extraction tasks. Furthermore, we deploy FSAM within an existing 2D-CNN-based rPPG architecture to illustrate its versatility. FSAM and FactorizePhys are thoroughly evaluated against state-of-the-art rPPG methods, each representing different types of architecture and attention mechanism. We perform ablation studies to investigate the architectural decisions and hyperparameters of FSAM. Experiments on four publicly available datasets and intuitive visualization of learned spatial-temporal features substantiate the effectiveness of FSAM and enhanced cross-dataset generalization in estimating rPPG signals, suggesting its broader potential as a multidimensional attention mechanism. The code is accessible at https://github.com/PhysiologicAILab/FactorizePhys.

Chunyu Yuan, Sos S. Agaian

Deep learning (DL) has recently changed the development of intelligent systems and is widely adopted in many real-life applications. Despite their various benefits and potentials, there is a high demand for DL processing in different computationally limited and energy-constrained devices. It is natural to study game-changing technologies such as Binary Neural Networks (BNN) to increase deep learning capabilities. Recently remarkable progress has been made in BNN since they can be implemented and embedded on tiny restricted devices and save a significant amount of storage, computation cost, and energy consumption. However, nearly all BNN acts trade with extra memory, computation cost, and higher performance. This article provides a complete overview of recent developments in BNN. This article focuses exclusively on 1-bit activations and weights 1-bit convolution networks, contrary to previous surveys in which low-bit works are mixed in. It conducted a complete investigation of BNN's development -from their predecessors to the latest BNN algorithms/techniques, presenting a broad design pipeline and discussing each module's variants. Along the way, it examines BNN (a) purpose: their early successes and challenges; (b) BNN optimization: selected representative works that contain essential optimization techniques; (c) deployment: open-source frameworks for BNN modeling and development; (d) terminal: efficient computing architectures and devices for BNN and (e) applications: diverse applications with BNN. Moreover, this paper discusses potential directions and future research opportunities in each section.

Yue Wu, Yicong Zhou, Joseph P. Noonan et al.

In this paper, we introduce a symmetric-key Latin square image cipher (LSIC) for grayscale and color images. Our contributions to the image encryption community include 1) we develop new Latin square image encryption primitives including Latin Square Whitening, Latin Square S-box and Latin Square P-box ; 2) we provide a new way of integrating probabilistic encryption in image encryption by embedding random noise in the least significant image bit-plane; and 3) we construct LSIC with these Latin square image encryption primitives all on one keyed Latin square in a new loom-like substitution-permutation network. Consequently, the proposed LSIC achieve many desired properties of a secure cipher including a large key space, high key sensitivities, uniformly distributed ciphertext, excellent confusion and diffusion properties, semantically secure, and robustness against channel noise. Theoretical analysis show that the LSIC has good resistance to many attack models including brute-force attacks, ciphertext-only attacks, known-plaintext attacks and chosen-plaintext attacks. Experimental analysis under extensive simulation results using the complete USC-SIPI Miscellaneous image dataset demonstrate that LSIC outperforms or reach state of the art suggested by many peer algorithms. All these analysis and results demonstrate that the LSIC is very suitable for digital image encryption. Finally, we open source the LSIC MATLAB code under webpage https://sites.google.com/site/tuftsyuewu/source-code.

Silvano A. Bernabel, Sos S. Agaian

This paper tackles the intricate challenge of improving the quality of nighttime images under hazy and low-light conditions. Overcoming issues including nonuniform illumination glows, texture blurring, glow effects, color distortion, noise disturbance, and overall, low light have proven daunting. Despite the inherent difficulties, this paper introduces a pioneering solution named Nighttime Dehazing, Low-Light Enhancement, and Light Suppression (NDELS). NDELS utilizes a unique network that combines three essential processes to enhance visibility, brighten low-light regions, and effectively suppress glare from bright light sources. In contrast to limited progress in nighttime dehazing, unlike its daytime counterpart, NDELS presents a comprehensive and innovative approach. The efficacy of NDELS is rigorously validated through extensive comparisons with eight state-of-the-art algorithms across four diverse datasets. Experimental results showcase the superior performance of our method, demonstrating its outperformance in terms of overall image quality, including color and edge enhancement. Quantitative (PSNR, SSIM) and qualitative metrics (CLIPIQA, MANIQA, TRES), measure these results.

Vladimir Frants, Sos Agaian, Karen Panetta et al.

Images used in real-world applications such as image or video retrieval, outdoor surveillance, and autonomous driving suffer from poor weather conditions. When designing robust computer vision systems, removing adverse weather such as haze, rain, and snow is a significant problem. Recently, deep-learning methods offered a solution for a single type of degradation. Current state-of-the-art universal methods struggle with combinations of degradations, such as haze and rain-streak. Few algorithms have been developed that perform well when presented with images containing multiple adverse weather conditions. This work focuses on developing an efficient solution for multiple adverse weather removal using a unified quaternion neural architecture called CMAWRNet. It is based on a novel texture-structure decomposition block, a novel lightweight encoder-decoder quaternion transformer architecture, and an attentive fusion block with low-light correction. We also introduce a quaternion similarity loss function to preserve color information better. The quantitative and qualitative evaluation of the current state-of-the-art benchmarking datasets and real-world images shows the performance advantages of the proposed CMAWRNet compared to other state-of-the-art weather removal approaches dealing with multiple weather artifacts. Extensive computer simulations validate that CMAWRNet improves the performance of downstream applications such as object detection. This is the first time the decomposition approach has been applied to the universal weather removal task.

Sos Agaian, Vladimir Frants

Images taken in low light often show color shift, low contrast, noise, and other artifacts that hurt computer-vision accuracy. Retinex theory addresses this by viewing an image S as the pixel-wise product of reflectance R and illumination I, mirroring the way people perceive stable object colors under changing light. The decomposition is ill-posed, and classic Retinex models have four key flaws: (i) they treat the red, green, and blue channels independently; (ii) they lack a neuroscientific model of color vision; (iii) they cannot perfectly rebuild the input image; and (iv) they do not explain human color constancy. We introduce the first Quaternion Retinex formulation, in which the scene is written as the Hamilton product of quaternion-valued reflectance and illumination. To gauge how well reflectance stays invariant, we propose the Reflectance Consistency Index. Tests on low-light crack inspection, face detection under varied lighting, and infrared-visible fusion show gains of 2-11 percent over leading methods, with better color fidelity, lower noise, and higher reflectance stability.

Vladimir Frants, Sos Agaian

This paper addresses the vulnerability of deep-learning models designed for rain, snow, and haze removal. Despite enhancing image quality in adverse weather, these models are susceptible to adversarial attacks that compromise their effectiveness. Traditional defenses such as adversarial training and model distillation often require extensive retraining, making them costly and impractical for real-world deployment. While denoising and super-resolution techniques can aid image classification models, they impose high computational demands and introduce visual artifacts that hinder image processing tasks. We propose a model-agnostic defense against first-order white-box adversarial attacks using the Quaternion-Hadamard Network (QHNet) to tackle these challenges. White-box attacks are particularly difficult to defend against since attackers have full access to the model's architecture, weights, and training procedures. Our defense introduces the Quaternion Hadamard Denoising Convolutional Block (QHDCB) and the Quaternion Denoising Residual Block (QDRB), leveraging polynomial thresholding. QHNet incorporates these blocks within an encoder-decoder architecture, enhanced by feature refinement, to effectively neutralize adversarial noise. Additionally, we introduce the Adversarial Weather Conditions Vision Dataset (AWCVD), created by applying first-order gradient attacks on state-of-the-art weather removal techniques in scenarios involving haze, rain streaks, and snow. Using PSNR and SSIM metrics, we demonstrate that QHNet significantly enhances the robustness of low-level computer vision models against adversarial attacks compared with state-of-the-art denoising and super-resolution techniques. The source code and dataset will be released alongside the final version of this paper.

Artyom M. Grigoryan, Sos S. Agaian

In this paper, we discuss possible color palletes, prediction and analysis of originality of the colors that Artists used on the Renaissance oil paintings. This framework goal is to help to use the color symbology and image enhancement tools, to predict the historical color palletes of the Renaissance oil artworks. This work is only the start of a development to explore the possibilities of prediction of color palletes of the Renaissance oil artworks. We believe that framework might be very useful in the prediction of color palletes of the Renaissance oil artworks and other artworks. The images in number 105 have been taken from the paintings of three well-known artists, Rafael, Leonardo Da Vinci, and Rembrandt that are available in the Olga's Gallery. Images are processed in the frequency domain to enhance a quality of images and ratios of primary colors are calculated and analyzed by using new measurements of color-ratios.

Artyom M Grigoryan, Aparna John, Sos S Agaian

A novel method of color image enhancement is proposed, in which three or four color channels of the image are transformed to one channel 2-D grayscale image. This paper describes different models of such transformations in the RGB and other color models. Color image enhancement is achieved by enhancing first the transformed grayscale image and, then, transforming back the grayscale image into the colors. The color image enhancement is done on the transformed 2-D grayscale image rather than on the color image. New algorithms of color image enhancement are described in both frequency and time domains. The enhancement by this novel method shows good results. The enhancement of the image is measured with respect to the metric referred to as the Color Enhancement Measure Estimation (CEME).

Artyom M. Grigoryan, Aparna John, Sos S. Agaian

In this paper a quaternion approach of enhancement method is proposed in which color in the image is considered as a single entity. This new method is referred as the alpha-rooting method of color image enhancement by the two-dimensional quaternion discrete Fourier transform (2-D QDFT) followed by a spatial transformation. The results of the proposed color image enhancement method are compared with its counterpart channel-by-channel enhancement algorithm by the 2-D DFT. The image enhancements are quantified to the enhancement measure that is based on visual perception referred as the color enhancement measure estimation (CEME). The preliminary experiment results show that the quaternion approach of image enhancement is an effective color image enhancement technique.

Artyom M. Grigoryan, Aparna John, Sos S. Agaian

Color in an image is resolved into 3 or 4 color components and 2-Dimages of these components are stored in separate channels. Most of the color image enhancement algorithms are applied channel-by-channel on each image. But such a system of color image processing is not processing the original color. When a color image is represented as a quaternion image, processing is done in original colors. This paper proposes an implementation of the quaternion approach of enhancement algorithm for enhancing color images and is referred as the modified alpha-rooting by the two-dimensional quaternion discrete Fourier transform (2-D QDFT). Enhancement results of this proposed method are compared with the channel-by-channel image enhancement by the 2-D DFT. Enhancements in color images are quantitatively measured by the color enhancement measure estimation (CEME), which allows for selecting optimum parameters for processing by the genetic algorithm. Enhancement of color images by the quaternion based method allows for obtaining images which are closer to the genuine representation of the real original color.

James Collins, Sos Agaian

LSB steganography is a one of the most widely used methods for implementing covert data channels in image file exchanges [1][2]. The low computational complexity and implementation simplicity of the algorithm are significant factors for its popularity with the primary reason being low image distortion. Many attempts have been made to increase the embedding capacity of LSB algorithms by expanding into the second or third binary layers of the image while maintaining a low probability of detection with minimal distortive effects [2][3][4]. In this paper, we introduce an advanced technique for covertly embedding data within images using redundant number system decomposition over non-standard digital bit planes. Both grayscale and bit-mapped images are equally effective as cover files. It will be shown that this unique steganography method has minimal visual distortive affects while also preserving the cover file statistics, making it less susceptible to most general steganography detection algorithms.

James Collins, Sos Agaian

Network steganography has been a well-known covert data channeling method for over three decades. The basic set of techniques and implementation tools have not changed significantly since their introduction in the early 1980's. In this paper, we review the predominant methods of classical network steganography, describing the detailed operations and resultant challenges involved in embedding data in the network transport domain. We also consider the various cyber threat vectors of network steganography and point out the major differences between classical network steganography and the widely known end-point multimedia embedding techniques, which focus exclusively on static data modification for data hiding. We then challenge the security community by introducing an entirely new network dat hiding methodology, which we refer to as real-time network data steganography. Finally we provide the groundwork for this fundamental change of covert network data embedding by forming a basic framework for real-time network data operations that will open the path for even further advances in computer network security.

Yue Wu, Sos S. Agaian, Joseph P. Noonan

Sudoku puzzles are now popular among people in many countries across the world with simple constraints that no repeated digits in each row, each column, or each block. In this paper, we demonstrate that the Sudoku configuration provides us a new alternative way of matrix element representation by using block-grid pair besides the conventional row-column pair. Moreover, we discover six more matrix element representations by using row-digit pair, digit-row pair, column-digit pair, digit-column pair, block-digit pair, and digit-block pair associated with a Sudoku matrix. These parametric Sudoku associated matrix element representations not only allow us to denote matrix elements in secret ways, but also provide us new parametric two-dimensional bijective mappings. We study these two-dimensional bijections in the problem of image scrambling and propose a simple but effective Sudoku Associated Image Scrambler only using Sudoku associated two dimensional bijections for image scrambling without bandwidth expansion. Our simulation results over a wide collection of image types and contents demonstrate the effectiveness and robustness of the proposed method. Scrambler performance analysis with comparisons to peer algorithms under various investigation methods, including human visual inspections, gray degree of scrambling, autocorrelation coefficient of adjacent pixels, and key space and key sensitivities, suggest that the proposed method outperforms or at least reaches state-of-the-art. Similar scrambling ideas are also applicable to other digital data forms such as audio and video.

Yue Wu, Sos Agaian, Joseph P. Noonan

Since the 1990s chaotic cat maps are widely used in data encryption, for their very complicated dynamics within a simple model and desired characteristics related to requirements of cryptography. The number of cat map parameters and the map period length after discretization are two major concerns in many applications for security reasons. In this paper, we propose a new family of 36 distinctive 3D cat maps with different spatial configurations taking existing 3D cat maps [1]-[4] as special cases. Our analysis and comparisons show that this new 3D cat maps family has more independent map parameters and much longer averaged period lengths than existing 3D cat maps. The presented cat map family can be extended to higher dimensional cases.