Different Types Of Degradation Research Articles

Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks

The efficient extraction of text information from the background in degraded color document images is an important challenge in the preservation of ancient manuscripts. The imperfect preservation of ancient manuscripts has led to different types of degradation over time, such as page yellowing, staining, and ink bleeding, seriously affecting the results of document image binarization. This work proposes an effective three-stage network method to image enhancement and binarization of degraded documents using generative adversarial networks (GANs). Specifically, in Stage-1, we first split the input images into multiple patches, and then split these patches into four single-channel patch images (gray, red, green, and blue). Then, three single-channel patch images (red, green, and blue) are processed by the discrete wavelet transform (DWT) with normalization. In Stage-2, we use four independent generators to separately train GAN models based on the four channels on the processed patch images to extract color foreground information. Finally, in Stage-3, we train two independent GAN models on the outputs of Stage-2 and the resized original input images (512 × 512) as the local and global predictions to obtain the final outputs. The experimental results show that the Avg-Score metrics of the proposed method are 77.64, 77.95, 79.05, 76.38, 75.34, and 77.00 on the (H)-DIBCO 2011, 2013, 2014, 2016, 2017, and 2018 datasets, which are at the state-of-the-art level. The implementation code for this work is available at https://github.com/abcpp12383/ThreeStageBinarization.

Neural Degradation Representation Learning for All-In-One Image Restoration.

Existing methods have demonstrated effective performance on a single degradation type. In practical applications, however, the degradation is often unknown, and the mismatch between the model and the degradation will result in a severe performance drop. In this paper, we propose an all-in-one image restoration network that tackles multiple degradations. Due to the heterogeneous nature of different types of degradations, it is difficult to process multiple degradations in a single network. To this end, we propose to learn a neural degradation representation (NDR) that captures the underlying characteristics of various degradations. The learned NDR adaptively decomposes different types of degradations, similar to a neural dictionary that represents basic degradation components. Subsequently, we develop a degradation query module and a degradation injection module to effectively approximate and utilize the specific degradation based on NDR, enabling the all-in-one restoration ability for multiple degradations. Moreover, we propose a bidirectional optimization strategy to effectively drive NDR to learn the degradation representation by optimizing the degradation and restoration processes alternately. Comprehensive experiments on representative types of degradations (including noise, haze, rain, and downsampling) demonstrate the effectiveness and generalizability of our method. Code is available at https://github.com/mdyao/NDR-Restore.

Kernel-guided injection deep network for blind fusion of multispectral and panchromatic images

Deep learning (DL)-based pansharpening methods show advantages in generating a high-resolution multispectral image (MS) by fusing low-resolution MS and high-resolution panchromatic (PAN) images. However, most current research only considers a single fixed kernel in the training process, thus they may fail to handle unknown degradations by using a single model for testing, i.e., blind pansharpening. Consequently, poor performance will occur when encountering the mismatched degradation problem. Therefore, building a single network that can tackle blind pansharpening is more realistic and challenging. To this end, we design an end-to-end blind pansharpening network composed of a kernel estimation sub-network and a fusion sub-network, named BPNet. In particular, different from existing DL-based methods, we control injected details by utilizing prior degradation information produced by kernel estimation sub-network, thus it can adapt to different types of degradation. Besides, we design an effective fusion sub-network with a strong interpretability, which injects details of PAN image into MS image by a learnable injection matrix. Especially, the estimated kernel that indicates the blur level of MS image is used to update the learnable injection matrix. To preserve important features well in the deep network, channel-Transformer is further utilized as a skip-connection in the fusion sub-network. With the combination of kernel estimation and fusion sub-networks, the proposed BPNet has great advantages in complex degradation situations, as the network’s adaptability to diverse unknown degradations is enhanced. Extensive experiments on simulated and real datasets demonstrate that BPNet outperforms other state-of-the-art methods in terms of visual results and objective quality analysis.

Multi-degradation-adaptation network for fundus image enhancement with degradation representation learning

Fundus image quality serves a crucial asset for medical diagnosis and applications. However, such images often suffer degradation during image acquisition where multiple types of degradation can occur in each image. Although recent deep learning based methods have shown promising results in image enhancement, they tend to focus on restoring one aspect of degradation and lack generalisability to multiple modes of degradation. We propose an adaptive image enhancement network that can simultaneously handle a mixture of different degradations. The main contribution of this work is to introduce our Multi-Degradation-Adaptive module which dynamically generates filters for different types of degradation. Moreover, we explore degradation representation learning and propose the degradation representation network and Multi-Degradation-Adaptive discriminator for our accompanying image enhancement network. Experimental results demonstrate that our method outperforms several existing state-of-the-art methods in fundus image enhancement. Code will be available at https://github.com/RuoyuGuo/MDA-Net.

Convolution-transformer blend pyramid network for underwater image enhancement

Underwater images suffer from different types of degradation, where color degradation occurs in the spatial domain and edge degradation in the frequency domain. The high-quality underwater image enhancement represents a crucial milestone in advancing computer vision systems tailored for marine environments. This foundational endeavor encompasses a wide array of applications in computer vision tasks, including underwater inspection, underwater archaeology, and environmental monitoring. However, current convolutional neural network (CNN)-based pyramid frameworks primarily focus on capturing local features, often overlooking the significance of global semantic features that play a crucial role in understanding underwater scenes. Moreover, these frameworks handle spatial and frequency features independently, failing to enhance images by exploring correlation among domain-specific attributes for enabling information consistency. Besides, optimizing the model using a loss function with the same domain attributes from the ground truth may not lead to a better generalization ability. To solve these problems, we propose a new Convolution-Transformer Blend Pyramid Network (CTPN), which consists of a spatial branch and several frequency branches. The CTPN has four key components: a Swin transformer encoder, a CNN-Transformer aggregated encoder–decoder (CTED) and a blend pyramid framework. The Swin transformer encoder is employed to capture global semantic features, benefiting from its ability to extract long-range and global dependencies among features. The CTED fuses local features captured by CNN layers and global semantic features captured by the Swin transformer encoder in the spatial branch, with the help of the Cross-Model Fusion Module (CFM) and Skip-Aggregation Module (SAM). Subsequently, a blend pyramid framework is designed which not only progressively expands the transformed information of the previous domain branch to the current domain branch via the CTED-based refining operation, but also utilizes the proposed Domain Affinity Block (DAB) to explore the connection between domain attributes, ensuring information consistency. The experimental results demonstrate that the proposed method outperforms existing underwater image enhancement methods quantitatively and qualitatively.

DocNLC: A Document Image Enhancement Framework with Normalized and Latent Contrastive Representation for Multiple Degradations

Document Image Enhancement (DIE) remains challenging due to the prevalence of multiple degradations in document images captured by cameras. In this paper, we respond an interesting question: can the performance of pre-trained models and downstream DIE models be improved if they are bootstrapped using different degradation types of the same semantic samples and their high-dimensional features with ambiguous inter-class distance? To this end, we propose an effective contrastive learning paradigm for DIE — a Document image enhancement framework with Normalization and Latent Contrast (DocNLC). While existing DIE methods focus on eliminating one type of degradation, DocNLC considers the relationship between different types of degradation while utilizing both direct and latent contrasts to constrain content consistency, thus achieving a unified treatment of multiple types of degradation. Specifically, we devise a latent contrastive learning module to enforce explicit decorrelation of the normalized representations of different degradation types and to minimize the redundancy between them. Comprehensive experiments show that our method outperforms state-of-the-art DIE models in both pre-training and fine-tuning stages on four publicly available independent datasets. In addition, we discuss the potential benefits of DocNLC for downstream tasks. Our code is released at https://github.com/RylonW/DocNLC

Molecular Design for Organic Redox Flow Batteries

Redox flow batteries have in recent years become an increasingly researched alternative to lithium-ion batteries for stationary energy storage, stabilizing fluctuations between demand and the intermittent electricity production from solar and wind. The most common vanadium redox flow battery technology suffers from high market volatility for vanadium metal. As a potentially more sustainable alternative to the electrolytes based on metal-ions used in e.g. the vanadium RFB, organic redox active species are being developed to store charge. The organic electrolytes used in aqueous organic redox flow batteries (AORFBs) are reaching closer to economic viability in terms of stability and electrochemical properties but is still inferior to its vanadium counterpart in long-term performance.[1]The degrees of freedom when designing organic electrolytes are endless. However, to improve strategies to designing new electrolytes more systematic studies on the working principles behind what makes organic compounds accept and store charge has to be made. Using less electronegative organo-metallic compounds, radical stabilization and multiple electron reactions, are some of these strategies that can be utilized. Figure 1 shows how examples of current parent molecules with functional groups modifications to tailor stability, solubility and electrochemical properties and in various pH regions.[Image]Molecular design can be divided into three important factors that will impact the performance of the electrolyte; electrochemical properties, solubility and stability. The electrochemical properties of the redox active species are essential for the application towards RFBs, regarding potential, electrochemical reversibility, coulombic- and voltaic efficiencies. The second criteria to maintain a reasonable operating energy density of the RFB is to optimise the water solubility, being proportional to capacity and energy density. The organic compounds solubility is highly pH dependent, thus pairings of posolyte and negolyte will need to operate within the same pH range. By substituting different functional groups to the parent molecule, the operating pH of the species can be tailored. Electrolyte conductivity is also an important factor when altering pH or co-electrolytes in terms of efficiency. Stability or capacity decay is the main focal point for AORFBs and limitation of the redox active species. These decay mechanisms can be further categorized into three different types of degradation, all which result in loss of active electrolyte. First, radical-induced reactions given rise to disproportionation or dimerization reactions, second, pH dependent chemical reactions such as hydrolysis, addition, substitution and elimination reactions and third, physical reactions dependent on molecular size and charge, that can supress or promote crossover through the membrane.As of designing structurally novel molecules, the electrochemical properties are the first property that must be assessed followed by solubility and stability. Since there are already some well explored compounds such as anthraquinones and viologens, much research has been put into increasing the solubility and stability for these.[2] The poster aims to highlight the interconnection between the parameters that make these compounds viable for use in AORFBs. Issues such as what has been explored in terms of posolytes, negolytes, alkaline, neutral and acidic electrolytes and what important components are missing for development of AORFB will be discussed.[1] J. Luo, A. P. Wang, M. Hu, and T. L. Liu, “Materials challenges of aqueous redox flow batteries,” MRS Energy and Sustainability, 9, 1–12, 2022, doi: 10.1557/s43581-022-00023-1.[2] Z. Li, T. Jiang, M. Ali, C. Wu, and W. Chen, “Recent Progress in Organic Species for Redox Flow Batteries,” Energy Storage Materials, 50, 105–138, 2022. doi: 10.1016/j.ensm.2022.04.038. Figure 1

Restoration of remote satellite sensing images using machine and deep learning: A survey

Remote sensing satellite images are affected by different types of degradation, which poses an obstacle for remote sensing researchers to ensure a continuous and trouble-free observation of our space. This degradation can reduce the quality of information and its effect on the reliability of remote sensing research. To overcome this phenomenon, the methods of detecting and eliminating this degradation are used, which are the subject of our study. The original aim of this paper is that it proposes a state of art of recent decade (2012-2022) on advances in remote sensing image restoration using machine and deep learning, identified by this survey, including the databases used, the different categories of degradation, as well as the corresponding methods. Machine learning and deep learning based strategies for remote sensing satellite image restoration are recommended to achieve satisfactory improvements.

Long-Term Tests and Advanced Post-Test Characterizations of the Oxygen Electrode in Solid Oxide Electrolysis Cells

Solid oxide electrolysis cells (SOEC) are a promising energy conversion technology for the production of green hydrogen via steam electrolysis. However, performance loss remains a bottleneck for large-scale commercialization. Here, we investigate the different types of degradation occurring in a state-of-the-art cell composed of La0.6Sr0.4Co0.2Fe0.8O3-Ce0.8Gd0.2O2 (LSCF-GDC) composite for the oxygen electrode, GDC for the barrier layer, Y0.16Zr0.84O1.92 (8YSZ) for the electrolyte and Ni-YSZ for the fuel electrode. Electrochemical impedance spectra measured before and after operation at 750 °C for 2000 hours at -1 A cm-2 in SOEC mode revealed no significant evolution for the oxygen electrode contribution. To investigate potential degradation of this electrode, we performed multi-modal chemical imaging based on synchrotron X-ray diffraction (µ-XRD) with a resolution at the micrometer-scale. In addition, we monitored the evolution of the chemical composition and chemical environment before and after ageing using laboratory X-ray photoelectron spectroscopy (XPS). All these analyses revealed a slight evolution of the crystal lattice parameter in the oxygen electrode and the inter-diffusion layer. It was also found that Sr segregation accelerates with ageing. However, more severe ageing conditions and/or longer ageing durations are required in order to observe an effect on the performance.

Blind Image Quality Assessment with Deep Learning: A Replicability Study and Its Reproducibility in Lifelogging

The wide availability and small size of different types of sensors have allowed for the acquisition of a huge amount of data about a person’s life in real time. With these data, usually denoted as lifelog data, we can analyze and understand personal experiences and behaviors. Most of the lifelog research has explored the use of visual data. However, a considerable amount of these images or videos are affected by different types of degradation or noise due to the non-controlled acquisition process. Image Quality Assessment can plays an essential role in lifelog research to deal with these data. We present in this paper a twofold study on the topic of blind image quality assessment. On the one hand, we explore the replication of the training process of a state-of-the-art deep learning model for blind image quality assessment in the wild. On the other hand, we present evidence that blind image quality assessment is an important pre-processing step to be further explored in the context of information retrieval in lifelogging applications. We consider that our efforts have been successful in the replication of the model training process, achieving similar results of inference when compared to the original version, while acknowledging a fair number of assumptions that we had to consider. Moreover, these assumptions motivated an extensive additional analysis that led to significant insights on the influence of both batch size and loss functions when training deep learning models in this context. We include preliminary results of the replicated model on a lifelogging dataset, as a potential reproducibility aspect to be considered.

Degradation (Portrayals of Sexuality in Pornography)

Degradation (Portrayals of Sexuality in Pornography)

Evaluation of Concrete by Non-destructive Ultrasonic Pulse Velocity Method

Concrete is a material whose properties depend on its initial formulation, its conditions of use, and its change over time depending on its environment and the different types of degradation that it is likely to undergo. Knowledge and monitoring of its various mechanical properties are therefore essential for the maintenance of civil engineering works. All of the concrete assessment methods, whether destructive or non-destructive, can then provide a valuable diagnosis to the operators of the structure. Depending on their precision, they can be used to easily detect an alteration in the characteristics of the materials, locate a damaged area, the extent of the damage, or even precisely quantify the evolution of this damage over time and predict future changes. This paper presents the Ultrasonic Pulse Velocity technique (UPV) which is used by many companies to assess the compressive strength of concrete in situ and which allows measuring the speed and attenuation of elastic waves. The influence of the reinforcements on the ultrasonic pulse velocity has been studied and this is in the case of reinforcement perpendicular and parallel to the direction of propagation. The influence of several factors affecting the UPV, whether related to the properties of concrete or otherwise, was mentioned. Indeed, the porosity, the water/Cement ratio, the micro-cracks, the state of saturation and the temperature of concrete are parameters which strongly influence the values of UPV.

Comprehensive Analysis of Ecological Restoration Technologies in Typical Ecologically Vulnerable Regions around the World

Ecosystem degradation is a key issue facing the world. Rapid economic development has been achieved at the cost of degradation and environmental pollution, which has affected human well-being, particularly in fragile ecosystems. To achieve the United Nations sustainable development goals, it is essential to develop technologies to control degradation and restore ecosystems. However, a comprehensive assessment of the different types of degradation, of the methods used in different regions, and of the differences between regions has not been carried out. In this study, we examined databases of international organizations, interviewed experts to evaluate existing methods based on five dimensions, identified restoration technologies (hereinafter referred to as RTs) suitable for different types of degradation, and summarized the restoration effectiveness in different regions. We found 101 RTs around the world and found that the same technology can be applied in different regions. The RTs were dominated by engineering and biological RTs, accounting for 19.2–26.7% and 33.4–34.7% of the total, respectively. 45, 30, and 26 RTs were suitable for controlling soil erosion, sandy desertification, and degraded ecosystem, respectively. The average evaluation index of RTs for controlling these degradation problems are 0.81, 0.78, and 0.73, respectively meaning RTs used to fight soil erosion are more effective. The potential to transfer a technology to other regions and the readiness of the technologies were low for degraded ecosystems, and the ease of use was high for sandy desertification RTs. Although a given technology could be applied to different regions or degradation types, results varied. Our study will help ecosystem managers to deal with specific degradation issues, phases, and severities, and will support the transfer of RTs among regions.

Towards common specifications for low- and high-expansion cement-based materials exposed to external sulphate attacks

External sulphate attack involves the penetration of sulphate ions in solution within a cementitious material. The equilibrium conditions are changed, and the ions released by hydration products can react with the sulphate ions and form new compounds. Depending on exposure conditions and cement compositions, expansive minerals, such as ettringite, can precipitate and cause cracking and, eventually, the collapsing of the material. Laboratory tests have been designed in order to qualify cements as sulphate resistant. The response to sulphate attack depending greatly on the cement composition, different types of degradation can be observed, with different severity and kinetics. Thus, it is difficult for a single test and indicator to reflect the wide range of degradation mechanisms. In this study, four CEM I Portland cements (including one sulphate resistant cement), one CEM III sulphate resistant slag cement and two CEM V slag-fly ash cements have been tested and the monitoring data have been analyzed with a new method coupling several indicators (based on length and mass variations and considering leaching) in order to represent as faithfully as possible, the degradation mechanism of the mortar samples. Two main degradation mechanisms have been spotted: one driven by expansion and the other by surface degradation. Three Portland cement-based mortar samples (CEM I cement with aluminate content >5%) went through massive expansion, thus being dismissed as sulphate resistant. On the other hand, the last CEM I cement and the CEM III samples went through slight to no expansion but were continuously affected by leaching. The two CEM V mortar samples had a particular degradation mechanism since they did not crack and mostly lost material through leaching, they showed low but significant expansion.

Restoration for blurred noisy images based on guided filtering and inverse filter

The development of complex life leads into a need using images in several fields, because these images degraded during capturing the image from mobiles, cameras and persons who do not have sufficient experience in capturing images. It was important using techniques differently to improve images and human perception as image enhancement and image restoration etc. In this paper, restoration noisy blurred images by guided filter and inverse filtering can be used for enhancing images from different types of degradation was proposed. In the color images denoising process, it was very significant for improving the edge and texture information. Eliminating noise can be enhanced by the image quality. In this article, at first, The color images were taken. Then, random noise and blur were added to the images. Then, the noisy blurred image passed to the guided filtering to get on denoised image. Finally, an inverse filter applied to the blurred image by convolution an image with a mask and getting on the enhanced image. The results of this research illustrated good outcomes compared with other methods for removing noise and blur based on PSNR measure. Also, it enhanced the image and retained the edge details in the denoising process. PSNR and SSIM measures were more sensitive to Gaussian noise than blur.

What Fate for Plastics in Artworks? An Overview of Their Identification and Degradative Behaviour.

This review is conceived as a guide for material science researchers and conservators aiming to face the problem of deterioration of contemporary artworks entirely or partially made of plastics. It initially illustrates the analytical approaches for identifying polymeric material components in 3D art objects, such as sculptures and installations, and provides a perspective of their limits and advantages. Subsequently, the methodologies used for studying the deterioration of contemporary art plastics are reviewed, emphasising the main effects of the different types of degradation (i.e., migration of additives, oxidation and hydrolysis) and suggesting the appropriate techniques for their detection. Finally, the application of artificial ageing tests is critically assessed. All the concepts are elaborated through case studies and examples.

A CNN-based approach to identification of degradations in speech signals

The presence of degradations in speech signals, which causes acoustic mismatch between training and operating conditions, deteriorates the performance of many speech-based systems. A variety of enhancement techniques have been developed to compensate the acoustic mismatch in speech-based applications. To apply these signal enhancement techniques, however, it is necessary to know prior information about the presence and the type of degradations in speech signals. In this paper, we propose a new convolutional neural network (CNN)-based approach to automatically identify the major types of degradations commonly encountered in speech-based applications, namely additive noise, nonlinear distortion, and reverberation. In this approach, a set of parallel CNNs, each detecting a certain degradation type, is applied to the log-mel spectrogram of audio signals. Experimental results using two different speech types, namely pathological voice and normal running speech, show the effectiveness of the proposed method in detecting the presence and the type of degradations in speech signals which outperforms the state-of-the-art method. Using the score weighted class activation mapping, we provide a visual analysis of how the network makes decision for identifying different types of degradation in speech signals by highlighting the regions of the log-mel spectrogram which are more influential to the target degradation.

A Dual Branch Attention Network for Multiple Degraded Image Restoration

In this paper, we propose a novel dual branch attention network (DBA-Net), which can efficiently restore multiple degradation images. Most methods of image restoration focus on a single degradation factor, such as blur, noise, raindrop, etc. However, these methods frequently fail to real degraded images, because the real images usually contain different types of degradation. Our network backbone consists of two branches, the residual branch and the information distillation branch, which have different receptive fields. We design a gate module to choose useful feature maps from the two branches. Then, an improved multi-channel attention selection module is proposed to allow the network to learn more features of real results. On DIV2K datasets, which contains different degradation types (noise, blur, and compression loss) and diverse degradation levels (mild, moderate and severe), our results on PSNR and SSIM outperform other advanced algorithms. In visual performance, the texture of objects in DBA-Net images is more similar to the original image.

Variations in the diversity of the soil microbial community and structure under various categories of degraded wetland in Sanjiang Plain, northeastern China

AbstractUnderstanding the changes in microbial community composition in wetlands affected by different types of degradation can help enrich theoretical knowledge about wetland degradation. However, studies of the relative role of microorganisms under different types of degradation of wetlands are rare in wetland ecology. Because of agricultural development, a large volume of groundwater has been extracted from the Sanjiang Plain over the last few decades, which has caused wetland degradation. To provide information for the development and protection of this wetland ecosystem, investigations into the processes of wetland degradation are important. The aim of the present work was to assess the impacts of wetland degradation on soil microbial communities under four different types of wetlands degradation in the Sanjiang Plain: swamp meadow (SW), meadow wetland (MW), paddy farmland (PF), and cropland (CL). Both 16S and ITS rRNA gene amplicon sequencing were used to evaluate the diversity and composition of bacteria and fungi. A total of 638,758 effective 16S rRNA and 916,211 valid internal transcribed spacer rRNA gene sequences were obtained, which were classified into 11 fungal and 40 bacterial phyla. The dominant fungal and bacterial phyla were Ascomycota and Proteobacteria, respectively. In addition, wetland degradation increased the relative abundances of Chloroflexi and Gemmatimonadetes, but the relative abundances of Proteobacteria and Verrucomicrobia significantly decreased. The bacterial Shannon index of SW was lower than those of the other investigated sites. Fungal diversity showed no significant differences for different types of degraded wetlands. In addition to wetland degradation, different reactions of the dominant microbial phyla and their diversity were clearly coorelated with total phosphorus (TP), total potassium (TK), available potassium (AK), and soil organic matter (SOM), which formed essential criteria that influenced the soil microbial communities. Wetland degradation resulted in the decrease of soil nutrient and the decline of the abundance of dominant phylum in soil bacterial and fungal communities. These changes can be used as an early warning signal for the degrading wetland of the Sanjiang Plain.

CNN-Based Classification of Degraded Images Without Sacrificing Clean Images

Image classification needs to consider image degradations in practice because an image classification network trained with clean images works poorly for degraded images while digital images usually include some degradations such as JPEG compression. To tackle this problem, a common approach is training classification networks on degraded images with various levels of degradation, e.g. various quality factors for JPEG compression. However, the classification networks do not usually have enough accuracy for clean images because the classification networks have been averagely trained for various levels of degradation. This paper aims to construct a classification network of degraded images without sacrificing the performance of clean images. This paper proposes a network to learn the classification of degraded images and degradation levels of degraded images as multi-task learning. Learning the classification of degraded images is the main task of multi-task learning. On the other hand, learning degradation levels is a sub-task of multi-task learning and reinforces the classification ability. In the proposed network, a feature extractor of the classification is trained with image features acquired from a classification network of clean images by using consistency regularization with the cosine similarity loss. The experimental results using different types of degradations, including JPEG compression, Gaussian blur, Gaussian noise, and salt-and-pepper noise, show that our proposed network has enough ability to classify degraded images without sacrificing the performance for clean images.