Search Results (138)

The SuperGlue algorithm, which integrates deep learning theory with the SuperPoint feature extraction operator and addresses the matching problem using the classical Sinkhorn method, has significantly enhanced matching efficiency and become a prominent research focus. However, existing feature extraction operators often struggle to extract high-quality features from extremely low-light or dark images, resulting in reduced matching accuracy. In this study, we propose a novel feature matching method that combines multi-scale retinex with color restoration (MSRCR) and SuperGlue to address this challenge, enabling effective feature extraction and matching from dark images, successfully addressing the challenges of feature point extraction difficulties, sparse matching points, and low matching accuracy in extreme environments such as nighttime autonomous navigation, mine exploration, and tunnel operations. Our approach first employs the retinex-based MSRCR algorithm to enhance features in original low-light images, followed by utilizing the enhanced image pairs as inputs for SuperGlue feature matching. Experimental results validate the effectiveness of our method, demonstrating that both the quantity of extracted feature points and correctly matched feature points approximately doubles compared to traditional methods, thereby significantly improving matching accuracy in dark images. Full article

This paper proposes an underwater image enhancement technology based on an artificial lateral inhibition network (ALIN) generated in the compound eye of a bionic horseshoe crab robot (BHCR). The concept of a horizontal suppression network is applied to underwater image processing with the aim of achieving low energy consumption, high efficiency processing, and adaptability to limited computing resources. The lateral inhibition network has the effect of “enhancing the center and suppressing the surroundings”. In this paper, a pattern recognition algorithm is used to compare and analyze the images obtained by an artificial lateral inhibition network and eight main underwater enhancement algorithms (white balance, histogram equalization, multi-scale Retinex, and dark channel). Therefore, we can evaluate the application of the artificial lateral inhibition network in underwater image enhancement and the deficiency of the algorithm. The experimental results show that the ALIN plays an obvious role in enhancing the important information in underwater image processing technology. Compared with other algorithms, this algorithm can effectively improve the contrast between the highlight area and the shadow area in underwater image processing, solve the problem that the information of the characteristic points of the collected image is not prominent, and achieve the unique effect of suppressing the intensity of other pixel points without information. Finally, we conduct target recognition verification experiments to assess the ALIN’s performance in identifying targets underwater with the BHCR in static water environments. The experiments confirm that the BHCR can maneuver underwater using multiple degrees of freedom (MDOF) and successfully acquire underwater targets. Full article

Wireless capsule endoscopy (WCE) offers a non-invasive diagnostic alternative for the gastrointestinal tract using a battery-powered capsule. Despite advantages, WCE encounters issues with video quality and diagnostic accuracy, often resulting in missing rates of 1–20%. These challenges stem from weak texture characteristics due to non-Lambertian tissue reflections, uneven illumination, and the necessity of color fidelity. Traditional Retinex-based methods used for image enhancement are suboptimal for endoscopy, as they frequently compromise anatomical detail while distorting color. To address these limitations, we introduce QRNet, a novel quaternion-based Retinex framework. QRNet performs image decomposition into reflectance and illumination components within hypercomplex space, maintaining inter-channel relationships that preserve color fidelity. A quaternion wavelet attention mechanism refines essential features while suppressing noise, balancing enhancement and fidelity through an innovative loss function. Experiments on Kvasir-Capsule and Red Lesion Endoscopy datasets demonstrate notable improvements in metrics such as PSNR (+2.3 dB), SSIM (+0.089), and LPIPS (−0.126). Moreover, lesion segmentation accuracy increases by up to 5%, indicating the framework’s potential for improving early-stage lesion detection. Ablation studies highlight the quaternion representation’s pivotal role in maintaining color consistency, confirming the promise of this advanced approach for clinical settings. Full article

Multispectral reconstruction is an important way to acquire spectral images with a high spatial resolution as snapshots. Current deep learning-based multispectral reconstruction models perform well under symmetric conditions, where the exposure of training and testing images is consistent. However, further research has shown that these models are sensitive to exposure changes. When the exposure symmetry is not maintained and testing images are input into the multispectral reconstruction model under different exposure conditions, the reconstructed multispectral images tend to deviate from the real ground truth to varying degrees. This limitation restricts the robustness and applicability of the model in practical scenarios. To address this challenge, we propose an exposure estimation multispectral reconstruction model of EFMST++ with data augmentation and optimized deep learning architecture, where Retinex decomposition and a wavelet transform are introduced into the proposed model. Based on the currently available dataset in this field, a comprehensive comparison is made between the proposed and existing models. The results show that after the current multispectral reconstruction models are retrained using the augmented datasets, the average MRAE and RMSE of the current most advanced model of MST++ are reduced from 0.570 and 0.064 to 0.236 and 0.040, respectively. The proposed method further reduces the average MRAE and RMSE to 0.229 and 0.037, with the average PSNR increasing from 27.94 to 31.43. The proposed model supports the use of multispectral reconstruction in open environments. Full article

In this paper, we describe the associative and commutative algebra or the (2,2)-model of quaternions with application in color image enhancement. The method of alpha-rooting, which is based on the 2D quaternion discrete Fourier transform (QDFT) is considered. In the (2,2)-model, the aperiodic convolution of quaternion signals can be calculated by the product of their QDFTs. The concept of linear convolution is simple, that is, it is unique, and the reduction of this operation to the multiplication in the frequency domain makes this model very attractive for processing color images. Note that in the traditional quaternion algebra, which is not commutative, the convolution can be chosen in many different ways, and the number of possible QDFTs is infinite. And most importantly, the main property of the traditional Fourier transform that states that the aperiodic convolution is the product of the transform in the frequency domain is not valid. We describe the main property of the (2,2)-model of quaternions, the quaternion exponential functions and convolution. Three methods of alpha-rooting based on the 2D QDFT are presented, and illustrative examples on color image enhancement are given. The image enhancement measures to estimate the quality of the color images are described. Examples of the alpha-rooting enhancement on different color images are given and analyzed with the known histogram equalization and Retinex algorithms. Our experimental results show that the alpha-rooting method in the quaternion space is one of the most effective methods of color image enhancement. Quaternions allow all colors in each pixel to be processed as a whole, rather than individually as is done in traditional processing methods. Full article

Two challenges in computer vision (CV) related to face detection are the difficulty of acquisition in the target domain and the degradation of image quality. Especially in low-light situations, the poor visibility of images is difficult to label, which results in detectors trained under well-lit conditions exhibiting reduced performance in low-light environments. Conventional works image enhancement and object detection techniques are unable to resolve the inherent difficulties in collecting and labeling low-light images. The Dark-Illuminated Network with Contrastive Language–Image Pretraining (CLIP) and Self-Supervised Vision Transformer (Dino), abbreviated as DAl-CLIP-Dino is proposed to address the degradation of object detection performance in low-light environments and achieve zero-shot day–night domain adaptation. Specifically, an advanced reflectance representation learning module (which leverages Retinex decomposition to extract reflectance and illumination features from both low-light and well-lit images) and an interchange–redecomposition coherence process (which performs a second decomposition on reconstructed images after the exchange to generate a second round of reflectance and illumination predictions while validating their consistency using redecomposition consistency loss) are employed to achieve illumination invariance and enhance model performance. CLIP (VIT-based image encoder part) and Dino have been integrated for feature extraction, improving performance under extreme lighting conditions and enhancing its generalization capability. Our model achieves a mean average precision (mAP) of $29.6\%$ for face detection on the DARK FACE dataset, outperforming other models in zero-shot domain adaptation for face detection. Full article

Images captured under low-light conditions often suffer from serious degradation due to insufficient light, which adversely impacts subsequent computer vision tasks. Retinex-based methods have demonstrated strong potential in low-light image enhancement. However, existing approaches often directly design prior regularization functions for either illumination or reflectance components, which may unintentionally introduce noise. To address these limitations, this paper presents an enhancement method by integrating a Plug-and-Play strategy into an extended decomposition model. The proposed model consists of three main components: an extended decomposition term, an iterative reweighting regularization function for the illumination component, and a Plug-and-Play refinement term applied to the reflectance component. The extended decomposition enables a more precise representation of image components, while the iterative reweighting mechanism allows for gentle smoothing near edges and brighter areas while applying more pronounced smoothing in darker regions. Additionally, the Plug-and-Play framework incorporates off-the-shelf image denoising filters to effectively suppress noise and preserve useful image details. Extensive experiments on several datasets confirm that the proposed method consistently outperforms existing techniques. Full article

Groundnut is a vital crop worldwide, but its production is significantly threatened by various leaf diseases. Early identification of such diseases is vital for maintaining agricultural productivity. Deep learning techniques have been employed to address this challenge and enhance the detection, recognition, and classification of groundnut leaf diseases, ensuring better management and protection of this important crop. This paper presents a new approach to the detection and classification of groundnut leaf diseases by the use of an advanced deep learning model, GNut, which integrates ResNet50 and DenseNet121 architectures for feature extraction and Few-Shot Learning (FSL) for classification. The proposed model overcomes groundnut crop diseases by addressing an efficient and highly accurate method of managing diseases in agriculture. Evaluated on a novel Pak-Nuts dataset collected from groundnut fields in Pakistan, the GNut model achieves promising accuracy rates of 99% with FSL and 95% without it. Advanced image preprocessing techniques, such as Multi-Scale Retinex with Color Restoration and Adaptive Histogram Equalization and Multimodal Image Enhancement for Vegetative Feature Isolation were employed to enhance the quality of input data, further improving classification accuracy. These results illustrate the robustness of the proposed model in real agricultural applications, establishing a new benchmark for groundnut leaf disease detection and highlighting the potential of AI-powered solutions to play a role in encouraging sustainable agricultural practices. Full article

Underwater images are important for underwater vision tasks, yet their quality often degrades during imaging, promoting the generation of Underwater Image Enhancement (UIE) algorithms. This paper proposes a Dual-Channel Convolutional Neural Network (DC-CNN)-based quality assessment method to evaluate the performance of different UIE algorithms. Specifically, inspired by the intrinsic image decomposition, the enhanced underwater image is decomposed into reflectance with color information and illumination with texture information based on the Retinex theory. Afterward, we design a DC-CNN with two branches to learn color and texture features from reflectance and illumination, respectively, reflecting the distortion characteristics of enhanced underwater images. To integrate the learned features, a feature fusion module and attention mechanism are conducted to align efficiently and reasonably with human visual perception characteristics. Finally, a quality regression module is used to establish the mapping relationship between the extracted features and quality scores. Experimental results on two public enhanced underwater image datasets (i.e., UIQE and SAUD) show that the proposed DC-CNN method outperforms a variety of the existing quality assessment methods. Full article

Line icings on the power transmission lines are dangerous risks that may lead to situations like structural damage or power outages. The current techniques used for identifying ice have certain drawbacks, particularly when used in complex environments. This paper aims to detect lines on the top and bottom in PTLI with low illumination and complex backgrounds. The proposed method integrates multistage image processing techniques, including image enhancement, filtering, thresholding, object isolation, edge detection, and line identification. A binocular camera is used to capture images of PTLI. The effectiveness of the method is evaluated through a series of metrics, including accuracy, sensitivity, specificity, and precision, and compared with existing methods. It is observed that the proposed method significantly outperforms the existing methods of ice detection and thickness measurement. This paper uses average accuracy of detection and isolation of ice formations under various conditions at a percentage of 98.35, sensitivity at 91.63%, specificity at 99.42%, and precision of 96.03%. Furthermore, the accuracy of the ice thickness based on the thickness measurements is shown with a much smaller RMSE of 1.20 mm, MAE of 1.10 mm, and R-squared of 0.95. The proposed scheme for ice detection provides a more accurate and reliable method for monitoring ice formation on power transmission lines. Full article

Power transmission line icing (PTLI) poses significant threats to the reliability and safety of electrical power systems, particularly in cold regions. Accumulation of ice on power lines can lead to severe consequences, such as line breaks, tower collapses, and widespread power outages, resulting in economic losses and infrastructure damage. This study proposes an enhanced image processing pipeline to accurately detect and match key points in PTLI images for 3D monitoring of ice thickness using binocular vision. The pipeline integrates established techniques such as multiscale retinex (MSR), oriented FAST and rotated BRIEF (ORB) and scale-invariant feature transform (SIFT) algorithms, further refined with m-estimator sample consensus (MAGSAC)-based random sampling consensus (RANSAC) optimization. The image processing steps include automatic cropping, image enhancement, feature detection, and robust key point matching, all designed to operate in challenging environments with poor lighting and noise. Experiments demonstrate that the proposed method significantly improves key point matching accuracy and computational efficiency, reducing processing time to make it suitable for real-time applications. The effectiveness of the pipeline is validated through 3D ice thickness measurements, with results showing high precision and low error rates, making it a valuable tool for monitoring power transmission lines in harsh conditions. Full article

Background/Objectives: Accurate detection and classification of nodules in medical images, particularly rheumatoid nodules, are critical due to the varying nature of these nodules, where their specific type is often unknown before analysis. This study addresses the challenges of multi-class prediction in nodule detection, with a specific focus on rheumatoid nodules, by employing a comprehensive approach to feature extraction and classification. We utilized a diverse dataset of nodules, including rheumatoid nodules sourced from the DermNet dataset and local rheumatologists. Method: This study integrates 62 features, combining traditional image characteristics with advanced graph-based features derived from a superpixel graph constructed through Delaunay triangulation. The key steps include image preprocessing with anisotropic diffusion and Retinex enhancement, superpixel segmentation using SLIC, and graph-based feature extraction. Texture analysis was performed using Gray-Level Co-occurrence Matrix (GLCM) metrics, while shape analysis was conducted with Fourier descriptors. Vascular pattern recognition, crucial for identifying rheumatoid nodules, was enhanced using the Frangi filter. A Hybrid CNN–Transformer model was employed for feature fusion, and feature selection and hyperparameter tuning were optimized using Gray Wolf Optimization (GWO) and Particle Swarm Optimization (PSO). Feature importance was assessed using SHAP values. Results: The proposed methodology achieved an accuracy of 85%, with a precision of 0.85, a recall of 0.89, and an F1 measure of 0.87, demonstrating the effectiveness of the approach in detecting and classifying rheumatoid nodules in both binary and multi-class classification scenarios. Conclusions: This study presents a robust tool for the detection and classification of nodules, particularly rheumatoid nodules, in medical imaging, offering significant potential for improving diagnostic accuracy and aiding in the early identification of rheumatoid conditions. Full article

The dynamic range of an image represents the difference between its darkest and brightest areas, a crucial concept in digital image processing and computer vision. Despite display technology advancements, replicating the broad dynamic range of the human visual system remains challenging, necessitating high dynamic range (HDR) synthesis, combining multiple low dynamic range images captured at contrasting exposure levels to generate a single HDR image that integrates the optimal exposure regions. Recent deep learning advancements have introduced innovative approaches to HDR generation, with the cycle-consistent generative adversarial network (CycleGAN) gaining attention due to its robustness against domain shifts and ability to preserve content style while enhancing image quality. However, traditional CycleGAN methods often rely on unpaired datasets, limiting their capacity for detail preservation. This study proposes an improved model by incorporating a switching map (SMap) as an additional channel in the CycleGAN generator using paired datasets. The SMap focuses on essential regions, guiding weighted learning to minimize the loss of detail during synthesis. Using translated images to estimate the middle exposure integrates these images into HDR synthesis, reducing unnatural transitions and halo artifacts that could occur at boundaries between various exposures. The multilayered application of the retinex algorithm captures exposure variations, achieving natural and detailed tone mapping. The proposed mutual image translation module extends CycleGAN, demonstrating superior performance in multiexposure fusion and image translation, significantly enhancing HDR image quality. The image quality evaluation indices used are CPBDM, JNBM, LPC-SI, S3, JPEG_2000, and SSEQ, and the proposed model exhibits superior performance compared to existing methods, recording average scores of 0.6196, 15.4142, 0.9642, 0.2838, 80.239, and 25.054, respectively. Therefore, based on qualitative and quantitative results, this study demonstrates the superiority of the proposed model. Full article

In recent years, pedestrian re-identification technology has made significant progress, with various neural network models performing well under normal conditions, such as good weather and adequate lighting. However, most research has overlooked extreme environments, such as rainy weather and nighttime. Additionally, the existing pedestrian re-identification datasets predominantly consist of well-lit images. Although some studies have started to address these issues by proposing methods for enhancing low-light images to restore their original features, the effectiveness of these approaches remains limited. We noted that a method based on Retinex theory designed a reflectance representation learning module aimed at restoring image features as much as possible. However, this method has so far only been applied in object detection networks. In response to this, we improved the method and applied it to pedestrian re-identification, proposing a transposed convolution reflectance decoder (TransConvRefDecoder) to better restore details in low-light images. Extensive experiments on the Market1501, CUHK03, and MSMT17 datasets demonstrated that our approach delivered superior performance. Full article

As crucial predecessor tasks for fault detection and transmission line inspection, insulators, anti-vibration hammers, and arc sag detection are critical jobs. Due to the complexity of the high-voltage transmission line environment and other factors, target detection work on transmission lines remains challenging. A method for high-voltage transmission line inspection based on DETR (TLI-DETR) is proposed to detect insulators, anti-vibration hammers, and arc sag. This model achieves a better balance in terms of speed and accuracy than previous methods. Due to environmental interference such as mountainous forests, rivers, and lakes, this paper uses the Improved Multi-Scale Retinex with Color Restoration (IMSRCR) algorithm to make edge extraction more robust with less noise interference. Based on the TLI-DETR’s feature extraction network, we introduce the edge and semantic information by Momentum Comparison (MoCo) to boost the model’s feature extraction ability for small targets. The different shooting angles and distances of drones result in the target images taking up small proportions and impeding each other. Consequently, the statistical profiling of the area and aspect ratio of transmission line targets captured by UAV generate target query vectors with prior information to enable the model to adapt to the detection needs of transmission line targets more accurately and effectively improve the detection accuracy of small targets. The experimental results show that this method has excellent performance in high-voltage transmission line detection, achieving up to 91.65% accuracy and a 55FPS detection speed, which provides a technical basis for the online detection of transmission line targets. Full article