Loss Of Detail Research Articles

Enhancement of Mine Images through Reflectance Estimation of V Channel Using Retinex Theory

The dim lighting and excessive dust in underground mines often result in uneven illumination, blurriness, and loss of detail in surveillance images, which hinders subsequent intelligent image recognition. To address the limitations of the existing image enhancement algorithms in terms of generalization and accuracy, this paper proposes an unsupervised method for enhancing mine images in the hue–saturation–value (HSV) color space. Inspired by the HSV color space, the method first converts RGB images to the HSV space and integrates Retinex theory into the brightness (V channel). Additionally, a random perturbation technique is designed for the brightness. Within the same scene, a U-Net-based reflectance estimation network is constructed by enforcing consistency between the original reflectance and the perturbed reflectance, incorporating ResNeSt blocks and a multi-scale channel pixel attention module to improve accuracy. Finally, an enhanced image is obtained by recombining the original hue (H channel), brightness, and saturation (S channel), and converting back to the RGB space. Importantly, this image enhancement algorithm does not require any normally illuminated images during training. Extensive experiments demonstrated that the proposed method outperformed most existing unsupervised low-light image enhancement methods, qualitatively and quantitatively, achieving a competitive performance comparable to many supervised methods. Specifically, our method achieved the highest PSNR value of 22.18, indicating significant improvements compared to the other methods, and surpassing the second-best WCDM method by 10.3%. In terms of SSIM, our method also performed exceptionally well, achieving a value of 0.807, surpassing all other methods, and improving upon the second-place WCDM method by 19.5%. These results demonstrate that our proposed method significantly enhanced image quality and similarity, far exceeding the performance of the other algorithms.

Image fusion-based low-dose CBCT enhancement method for visualizing miniscrew insertion in the infrazygomatic crest

Digital dental technology covers oral cone-beam computed tomography (CBCT) image processing and low-dose CBCT dental applications. A low-dose CBCT image enhancement method based on image fusion is proposed to address the need for subzygomatic small screw insertion. Specifically, firstly, a sharpening correction module is proposed, where the CBCT image is sharpened to compensate for the loss of details in the underexposed/over-exposed region. Secondly, a visibility restoration module based on type II fuzzy sets is designed, and a contrast enhancement module using curve transformation is designed. In addition to this, we propose a perceptual fusion module that fuses visibility and contrast of oral CBCT images. As a result, the problems of overexposure/underexposure, low visibility, and low contrast that occur in oral CBCT images can be effectively addressed with consistent interpretability. The proposed algorithm was analyzed in comparison experiments with a variety of algorithms, as well as ablation experiments. After analysis, compared with advanced enhancement algorithms, this algorithm achieved excellent results in low-dose CBCT enhancement and effective observation of subzygomatic small screw implantation. Compared with the best performing method, the evaluation metric is 0.07–2 higher on both datasets. The project can be found at: https://github.com/sunpeipei2024/low-dose-CBCT.

Retinex Jointed Multiscale CLAHE Model for HDR Image Tone Compression

Tone-mapping algorithms aim to compress a wide dynamic range image into a narrower dynamic range image suitable for display on imaging devices. A representative tone-mapping algorithm, Retinex theory, reflects color constancy based on the human visual system and performs dynamic range compression. However, it may induce halo artifacts in some areas or degrade chroma and detail. Thus, this paper proposes a Retinex jointed multiscale contrast limited adaptive histogram equalization method. The proposed algorithm reduces localized halo artifacts and detail loss while maintaining the tone-compression effect via high-scale Retinex processing. A performance comparison of the experimental results between the proposed and existing methods confirms that the proposed method effectively reduces the existing problems and displays better image quality.

Lane detection using hough transformation and Yolov8

Autonomous vehicles necessitate the integration of advanced technologies such as computer vision and deep learning to comprehend and navigate their surroundings. A crucial yet challenging component of this integration is the accurate detection of lanes, which can be influenced by a multitude of varying lane characteristics and conditions. This research undertakes a comparative analysis of lane detection methodologies, explicitly focusing on traditional image processing techniques and Convolutional Neural Networks (CNNs). The evaluation utilized a sample of 500 images from the CULane dataset, which encompasses a diverse range of traffic scenarios. Initially, a method incorporating Gaussian blurring, Canny edge detection, and Hough line transformation was examined. Despite its efficiency, operating at 30 frames per second, this approach exhibited a high error rate (average Mean Squared Error (MSE) of 0.537), which is attributable to the loss of critical image details during the preprocessing stage. Subsequently, the performance of a fine-tuned YOLOv8 model, trained on a reformatted version of the CULane dataset was assessed. The combination of object detection and subsequent Hough transformation yielded high accuracy, demonstrating the model’s ability to learn and identify relevant lane features. The deep CNNs demonstrated superior performance over classical image processing techniques in terms of lane detection accuracy, thereby underscoring their potential applicability within the realm of autonomous vehicle technology

Vison Transformer-Based Automatic Crack Detection on Dam Surface

Dam is an essential structure in hydraulic engineering, and its surface cracks pose significant threats to its integrity, impermeability, and durability. Automated crack detection methods based on computer vision offer substantial advantages over manual approaches with regard to efficiency, objectivity and precision. However, current methods face challenges such as misidentification, discontinuity, and loss of details when analyzing real-world dam crack images. These images often exhibit characteristics such as low contrast, complex backgrounds, and diverse crack morphologies. To address the above challenges, this paper presents a pure Vision Transformer (ViT)-based dam crack segmentation network (DCST-net). The DCST-net utilizes an improved Swin Transformer (SwinT) block as the fundamental block for enhancing the long-range dependencies within a SegNet-like encoder–decoder structure. Additionally, we employ a weighted attention block to facilitate side fusion between the symmetric pair of encoder and decoder in each stage to sharpen the edge of crack. To demonstrate the superior performance of our proposed method, six semantic segmentation models have been trained and tested on both a self-built dam crack dataset and two publicly available datasets. Comparison results indicate that our proposed model outperforms the mainstream methods in terms of visualization and most evaluation metrics, highlighting its potential for practical application in dam safety inspection and maintenance.

Conditional generative model with skip-connection structure for low-light image enhancement

Vision-guided coal mine robots often encounter challenges in low-light environments, capturing images marked by poor visibility and significant loss of detail, which complicates the advancement of smart mine safety production. Despite various advancements, achieving high visibility and detailed images through robotic vision sensors remains a formidable task. This paper introduces a conditional generative model incorporating a skip-connection structure to address these issues. We present a novel approach utilizing conditional Generative Adversarial Networks (GNAs) aimed at improving the visibility of image content. This involves an encoder-decoder framework with skip-connections functioning as the generator, and the discriminator, both tailored to enhance image detail. In addition, we implement loss functions integrated with boundary equilibrium constraints to counter the issue of model collapse in conditional GANs, thereby enhancing training stability and image fidelity. Our experimental findings demonstrate that our model delivers competitive results against other state-of-the-art low-light image enhancement models, alongside a standardized training regimen that ensures rapid and consistent convergence.

Ultrasound image denoising autoencoder model based on lightweight attention mechanism.

The presence of noise in medical ultrasound images significantly degrades image quality and affects the accuracy of disease diagnosis. The convolutional neural network-denoising autoencoder (CNN-DAE) model extracts feature information by stacking regularly sized kernels. This results in the loss of texture detail, the over-smoothing of the image, and a lack of generalizability for speckle noise. A lightweight attention denoise-convolutional neural network (LAD-CNN) is proposed in the present study. Two different lightweight attention blocks (i.e., the lightweight channel attention (LCA) block and the lightweight large-kernel attention (LLA) block are concatenated into the downsampling stage and the upsampling stage, respectively. A skip connection is included before the upsampling layer to alleviate the problem of gradient vanishing during backpropagation. The effectiveness of our model was evaluated using both subjective visual effects and objective evaluation metrics. With the highest peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) values at all noise levels, the proposed model outperformed the other models. In the test of brachial plexus ultrasound images, the average PSNR of our model was 0.15 higher at low noise levels and 0.33 higher at high noise levels than the suboptimal model. In the test of fetal ultrasound images, the average PSNR of our model was 0.23 higher at low noise levels and 0.20 higher at high noise levels than the suboptimal model. The statistical analysis showed that the p values were less than 0.05, which indicated a statistically significant difference between our model and the other models. The results of this study suggest that the proposed LAD-CNN model is more efficient in denoising and preserving image details than both conventional denoising algorithms and existing deep-learning algorithms.

Take a prior from other tasks for severe blur removal

Recovering clear structures from severely blurry inputs is a huge challenge due to the detail loss and ambiguous semantics. Although segmentation maps can help deblur facial images, their effectiveness is limited in complex natural scenes because they ignore the detailed structures necessary for deblurring. Furthermore, direct segmentation of blurry images may introduce error propagation. To alleviate the semantic confusion and avoid error propagation, we propose utilizing high-level vision tasks, such as classification, to learn a comprehensive prior for severe blur removal. We propose a feature learning strategy based on knowledge distillation, which aims to learn the priors with global contexts and sharp local structures. To integrate the priors effectively, we propose a semantic prior embedding layer with multi-level aggregation and semantic attention. We validate our method on natural image deblurring benchmarks by introducing the priors to various models, including UNet and mainstream deblurring baselines, to demonstrate its effectiveness and generalization ability. The results show that our approach outperforms existing methods on severe blur removal with our plug-and-play semantic priors.

Research on Image Classification And Semantic Segmentation Model Based on Convolutional Neural Network

This paper investigates convolutional neural network (CNN)-based approaches for image classification and semantic segmentation, with a focus on addressing spatial detail loss and multi-scale feature integration issues prevalent in semantic segmentation. The introduced EDNET model tackles these challenges through the incorporation of spatial information branches and the design of efficient feature fusion mechanisms. It further enhances performance via the use of global pooling and boundary refinement modules. Evaluations on the PASCAL VOC 2012 dataset reveal an 11.67% increase in mean intersection-over-union (IoU) compared to standard fully convolutional networks, demonstrating substantial improvement over comparable techniques. These results confirm the efficacy and practicality of the EDNET framework.

Hierarchical prior-guided quality assessment method for underwater images

Many underwater image enhancement (UIE) algorithms have been proposed to improve the quality of the underwater image. However, the lack of effective objective image quality assessment (IQA) methods has hindered the further development of UIE algorithms. Unlike traditional distorted images, underwater images usually contain natural distortions such as color cast and fog effects induced by light absorption and scattering. In addition, due to the complexity of underwater scenes, the enhanced results generated using existing UIE algorithms may have artificial distortions such as under-enhancement, over-enhancement, and detail loss. Thus, it is difficult for traditional IQA methods to comprehensively capture quality-related features in complicated underwater conditions. Based on this, this paper proposes a new hierarchical prior-guided quality assessment method for underwater images with the aid of deep learning technology, which first decomposes the underwater image into the base layer and detail layer. Then, the two layers are taken as input of feature extraction network for extracting the luminance information and texture information of the image, respectively. Meanwhile, two pseudo-reference images are used to guide model training so as to obtain luminance and texture features more accurately and efficiently. Finally, the two types of features are fused to obtain the quality score of the underwater image. Extensive experiments have been conducted on two publicly available underwater image datasets, and the experimental results show that the proposed method outperforms other underwater image quality assessment methods.

Unsupervised face image deblurring via disentangled representation learning

Unsupervised face image deblurring aims to restore latent clear face images with explicit structure and facial details without relying on labels. Despite the recent progress, most existing approaches ignore the domain shift issue between clear and blur domains, leading to color distortion and loss of detail in deblurred images. To tackle this issue, we propose a symmetrical unsupervised framework including a decoupling stage and a reconstruction stage. In the decoupling stage, we employ disentangled representation and adversarial domain translation to establish discriminative boundaries between content-invariant domains and feature-shift domains. Besides, a clear feature encoder for clear images is introduced to obtain a latent feature space containing more detailed clarity, providing reliable input for subsequent reconstruction. In the reconstruction stage, similar modules are adopted to ensure the integrity of the mutual mapping between clear and blurred images, while domain latent supervision loss is introduced to ensure that the decoupled features and content information from both stages belong to the same domain. Extensive experimental results on popular benchmarks validate the effectiveness of our method by surpassing existing works.

Optimized multi-scale framework for image enhancement using spatial information-based histogram equalization

ABSTRACT The histogram equalization method, used to improve images, minimizes the amount of pixel intensities, which results in the loss of detail and an unnatural appearance. This study presents an approach for enhancing low contrast images based on their inherent characteristics. The statistical parameter skewness is derived from the photographs to facilitate the classification process into dark and bright images. Based on the classification, appropriate dark and bright pass filters are applied on the multi-level decomposed images to extract the significant edge details. The level of decomposition is optimized using particle swarm optimization. The extracted edge details are utilized by the two-dimensional histogram equalization technique. It leverages the combined presence of edge information and pixel intensities in the low contrast image. The algorithm's efficacy is assessed on three databases, namely CCID, LOL, and DRESDEN, through the utilization of standard deviation (SD), contrast improvement index (CII), discrete entropy (DE), the natural image quality evaluator (NIQE), and Kullback–Leibler distance (KL). Based on the empirical findings, it can be observed that the suggested methodology exhibits better performance compared to alternative methods, including deep learning architectures, in terms of high CII, SD, DE, and low NIQE, KL values.

Lightweight two-stage transformer for low-light image enhancement and object detection

In low-light conditions, due to the loss of image details the visual tasks are challenging. To achieve real-time image enhancement and improve the accuracy of object detection task, we propose a lightweight two-stage Transformer. First, we use dynamic convolution to improve the adaptability of the network to different samples and preliminarily enhance the image through predicting the multiplicative and additive maps of the least squares method. In the second stage, we propose a FFT-Guidance Block (FGB) to obtain frequency components for explicit modeling, guiding the recovery of image potential information. In addition, joint our model with YOLOv3 to build a dark object detection framework, and we only use normal detection loss to simplify the training process. On the LOLv2 dataset, our model achieves advanced results. The enhanced model maintains good performance while the parameters are only 0.050M, and increase the accuracy of the downstream object detection task. The detection framework reaches 77.9% and 60.2 in mAP and FPS respectively on ExDark dataset, which can be better robust in dark conditions.

Medical Image Fusion Based on Local Saliency Energy and Multi-scale Fractal Dimension.

At present, there are some problems in multimodal medical image fusion, such as texture detail loss, leading to edge contour blurring and image energy loss, leading to contrast reduction. To solve these problems and obtain higher-quality fusion images, this study proposes an image fusion method based on local saliency energy and multi-scale fractal dimension. First, by using a non-subsampled contourlet transform, the medical image was divided into 4 layers of high-pass subbands and 1 layer of low-pass subband. Second, in order to fuse the high-pass subbands of layers 2 to 4, the fusion rules based on a multi-scale morphological gradient and an activity measure were used as external stimuli in pulse coupled neural network. Third, a fusion rule based on the improved multi-scale fractal dimension and new local saliency energy was proposed, respectively, for the low-pass subband and the 1st closest to the low-pass subband. Layerhigh pass sub-bands were fused. Lastly, the fused image was created by performing the inverse non-subsampled contourlet transform on the fused sub-bands. On three multimodal medical image datasets, the proposed method was compared with 7 other fusion methods using 5 common objective evaluation metrics. Experiments showed that this method can protect the contrast and edge of fusion image well and has strong competitiveness in both subjective and objective evaluation.

Unsupervised Bidirectional Contrastive Reconstruction and Adaptive Fine-Grained Channel Attention Networks for image dehazing

Recently, Unsupervised algorithms has achieved remarkable performance in image dehazing. However, the CycleGAN framework can lead to confusion in generator learning due to inconsistent data distributions, and the DisentGAN framework lacks effective constraints on generated images, resulting in the loss of image content details and color distortion. Moreover, Squeeze and Excitation channel attention employs only fully connected layers to capture global information, lacking interaction with local information, resulting in inaccurate feature weight allocation for image dehazing. To solve the above problems, in this paper, we propose an Unsupervised Bidirectional Contrastive Reconstruction and Adaptive Fine-Grained Channel Attention Networks (UBRFC-Net). Specifically, an Unsupervised Bidirectional Contrastive Reconstruction Framework (BCRF) is proposed, aiming to establish bidirectional contrastive reconstruction constraints, not only to avoid the generator learning confusion in CycleGAN but also to enhance the constraint capability for clear images and the reconstruction ability of the unsupervised dehazing network. Furthermore, an Adaptive Fine-Grained Channel Attention (FCA) is developed to utilize the correlation matrix to capture the correlation between global and local information at various granularities promotes interaction between them, achieving more efficient feature weight assignment. Experimental results on challenging benchmark datasets demonstrate the superiority of our UBRFC-Net over state-of-the-art unsupervised image dehazing methods. This study successfully introduces an enhanced unsupervised image dehazing approach, addressing limitations of existing methods and achieving superior dehazing results. The source code is available at https://github.com/Lose-Code/UBRFC-Net.

WaveletFormerNet: A Transformer-based wavelet network for real-world non-homogeneous and dense fog removal

Although deep convolutional neural networks have achieved remarkable success in removing synthetic fog, it is essential to be able to process images taken in complex foggy conditions, such as dense or non-homogeneous fog, in the real world. However, the haze distribution in the real world is complex, and downsampling can lead to color distortion or loss of detail in the output results as the resolution of a feature map or image resolution decreases. Moreover, the over-stacking of convolutional blocks might increase the model complexity. In addition to the challenges of obtaining sufficient training data, overfitting can also arise in deep learning techniques for foggy image processing, which can limit the generalization abilities of the model, posing challenges for its practical applications in real-world scenarios. Considering these issues, this paper proposes a Transformer-based wavelet network (WaveletFormerNet) for real-world foggy image recovery. We embed the discrete wavelet transform into the Vision Transformer by proposing the WaveletFormer and IWaveletFormer blocks, aiming to alleviate texture detail loss and color distortion in the image due to downsampling. We introduce parallel convolution in the Transformer block, which allows for the capture of multi-frequency information in a lightweight mechanism. Such a structure reduces computational expenses and improves the effectiveness of the network. Additionally, we have implemented a feature aggregation module (FAM) to maintain image resolution and enhance the feature extraction capacity of our model, further contributing to its impressive performance in real-world foggy image recovery tasks. Through extensive experiments on real-world fog datasets, we have demonstrated that our WaveletFormerNet achieves superior performance compared to state-of-the-art methods, as shown through quantitative and qualitative evaluations of minor model complexity. Additionally, our satisfactory results on real-world dust removal and application tests showcase the superior generalization ability and improved performance of WaveletFormerNet in computer vision-related applications compared to existing state-of-the-art methods, further confirming our proposed approach's effectiveness and robustness. Our code is available at https://github.com/shengli666666/WaveletFormerNet.

AoSRNet: All-in-One Scene Recovery Networks via multi-knowledge integration

Scattering and attenuation of light in no-homogeneous imaging media or inconsistent light intensity will cause insufficient contrast and color distortion in the collected images, which limits the developments such as vision-driven smart urban, autonomous vehicles, and intelligent robots. In this paper, we propose an all-in-one scene recovery network via multi-knowledge integration (termed AoSRNet) to improve the visibility of imaging devices in typical low-visibility imaging scenes (e.g., haze, sand dust, underwater, and low light). It combines gamma correction (GC) and optimized linear stretching (OLS) to create the detail enhancement module (DEM) and color restoration module (CRM). Additionally, we suggest a multi-receptive field extraction module (MEM) to attenuate the loss of image texture details caused by GC nonlinear and OLS linear transformations. Finally, we refine the coarse features generated by DEM, CRM, and MEM through Encoder-Decoder to generate the final restored image. Comprehensive experimental results demonstrate the effectiveness and stability of AoSRNet compared to other state-of-the-art methods. The source code is available at https://github.com/LouisYuxuLu/AoSRNet.

Generation model meets swin transformer for unsupervised low-dose CT reconstruction

Computed tomography (CT) has evolved into an indispensable tool for clinical diagnosis. Reducing radiation dose crucially minimizes adverse effects but may introduce noise and artifacts in reconstructed images, affecting diagnostic processes for physicians. Scholars have tackled deep learning training instability by exploring diffusion models. Given the scarcity of clinical data, we propose the unsupervised image domain score generation model (UISG) for low-dose CT reconstruction. During training, normal-dose CT images are utilized as network inputs to train a score-based generative model that captures the prior distribution of CT images. In the iterative reconstruction, the initial CT image is obtained using a filtered back-projection algorithm. Subsequently, diffusion-based prior, high-frequency convolutional sparse coding prior, and data-consistency steps are employed to obtain the high-quality reconstructed image. Given the global characteristics of noise, the score network of the diffusion model utilizes a swin transformer structure to enhance the model’s ability to capture long-range dependencies. Furthermore, convolutional sparse coding is applied exclusively to the high-frequency components of the image, to prevent over-smoothing or the loss of crucial anatomical details during the denoising process. Quantitative and qualitative results indicate that UISG outperforms competing methods in terms of denoising and generalization performance.

A medical image segmentation method for rectal tumors based on multi-scale feature retention and multiple attention mechanisms.

With the continuous development of deep learning algorithms in the field of medical images, models for medical image processing based on convolutional neural networks have made great progress. Since medical images of rectal tumors are characterized by specific morphological features and complex edges that differ from natural images, achieving good segmentation results often requires a higher level of enrichment through the utilization of semantic features. The efficiency of feature extraction and utilization has been improved to some extent through enhanced hardware arithmetic and deeper networks in most models. However, problems still exist with detail loss and difficulty in feature extraction, arising from the extraction of high-level semantic features in deep networks. In this work, a novel medical image segmentation model has been proposed for Magnetic Resonance Imaging (MRI) image segmentation of rectal tumors. The model constructs a backbone architecture based on the idea of jump-connected feature fusion and solves the problems of detail feature loss and low segmentation accuracy using three novel modules: Multi-scale Feature Retention (MFR), Multi-branch Cross-channel Attention (MCA), and Coordinate Attention (CA). Compared with existing methods, our proposed model is able to segment the tumor region more effectively, achieving 97.4% and 94.9% in Dice and mIoU metrics, respectively, exhibiting excellent segmentation performance and computational speed. Our proposed model has improved the accuracy of both lesion region and tumor edge segmentation. In particular, the determination of the lesion region can help doctors identify the tumor location in clinical diagnosis, and the accurate segmentation of the tumor edge can assist doctors in judging the necessity and feasibility of surgery.

Adipose-derived stem cells can alleviate RHDV2 induced acute liver injury in rabbits

Rabbit hemorrhagic disease virus (RHDV) can cause fatal fulminant hepatitis, which is very similar to human acute liver failure. The aim of this study was to investigate whether adipose-derived stem cells (ADSCs) could alleviate RHDV2-induced liver injury in rabbits. Twenty 50-day-old rabbits were divided randomly into two groups (RHDV2 group, ADSCs + RHDV2 group). Starting from the 1st day, two groups of rabbits were given 0.5 ml of viral suspensions by subcutaneous injection in the neck. Meanwhile, the ADSCs + RHDV2 group was injected with ADSCs cell suspension (1.5 × 107 cells/ml) via a marginal ear vein, and the RHDV2 group was injected with an equal amount of saline via a marginal ear vein. At the end of the 48 h experiment, the animals were euthanized and gross hepatic changes were observed before liver specimens were collected. Histopathological analysis was performed using hematoxylin-eosin (HE), periodic acid schiff (PAS) and Masson's trichrome staining. For RHDV2 affected rabbits, HE staining demonstrated disorganized hepatic cords, loss of cellular detail, and severe cytoplasmic vacuolation within hepatocytes. Glycogen was not observed with PAS staining, and Masson's Trichrome staining showed increased hepatic collagen deposition. For rabbits treated with ADSCs at the time of inoculation, hepatic pathological changes were significantly less severe, liver glycogen synthesis was increased, and collagen fiber deposition was decreased. For RHDV2 affected rabbits, Tunel and immunofluorescence staining showed that the number of apoptotic cells, TGF-β, and MMP-9 protein expression increased. And that in the ADSC treated group there was less hepatocyte apoptosis. In addition, RHDV2 induces liver inflammation and promotes the expression of IL-1β, IL-6, and TNF-α. In rabbits administered ADSCs at time of inoculation, the expression of inflammatory factors in liver tissue decreased significantly. Our experiments show that ADSCs can protect rabbits from liver injury by RHDV2 and reduce the pathological and inflammatory response of liver. However, the specific protective mechanism needs further study.