A Comprehensive Review of Deep Learning-Based Real-World Image Restoration

Zhai, Lujun; Wang, Yonghui; Cui, Suxia; Zhou, Yu

doi:10.1109/access.2023.3250616

Cited by 17 publications

(10 citation statements)

References 168 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning, a subset of machine learning, involves neural networks with multiple layers which tries to copy human brain function through algorithms [20]. Ideal for tasks requiring complex pattern recognition, such as image and speech processing [11], it holds promise for enhancing security in smart homes through advanced threat detection. In the Machine Learning section (Figure 3), a visual representation (cat and dog) undergoes 'processing,' 'feature extraction,' and 'feature selection' stages, culminating in the classification of two images differently.…”

Section: Deep Learningmentioning

confidence: 99%

“…This visual framework emphasizes the intricate layers and capabilities of deep learning, showcasing its potential for advanced threat detection in smart homes. Understanding these machine learning models serves as a crucial foundation for tailoring security solutions to address the specific challenges inherent in IoT-based home automation systems [11].…”

Section: Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

Securing the Dynamic Realm: A Comprehensive Review of ML Algorithms in IoT-Based Home Automation Systems and Beyond

2024

IJETER

View full text Add to dashboard Cite

This paper comprehensively reviews the imperative for secure IoT systems, emphasizing the challenges posed by their dynamic nature. Exploring various ML algorithms for IoT security, it highlights their advantages while addressing common limitations, including computational overhead and privacy risks. The focus narrows to federated learning (FL) and deep learning (DL) algorithms, showcasing their potential to overcome conventional ML drawbacks by preserving data privacy. The study provides an in-depth analysis of FL and DL-based techniques, emphasizing their efficiency in enhancing security in IoT-based home automation systems. The paper further examines ML's pivotal role in smart homes, presenting a case study that utilizes the support vector machine algorithm to distinguish between regular occupants and intruders. Extending the discussion to face recognition for home automation, the review underscores the utilization of IoT and smart techniques. Beyond home automation, the paper delves into the broader landscape of ML applications in the Fourth Industrial Revolution, offering insights into cybersecurity, smart cities, healthcare, and more. The review briefly introduces the utilization of Convolutional Neural Networks (CNNs) within the broader context of deep learning algorithms. While the main emphasis remains on FL and DL, the paper acknowledges CNNs as a powerful tool for image-based tasks, especially relevant in the context of visual data analysis for security in IoT-based home automation systems. In summary, this concise review encapsulates the transformative impact of ML on IoT-based home automation security, providing valuable perspectives on current trends, challenges, and future research directions. The inclusion of CNNs within the abstract recognizes their relevance, especially in image-based security applications.

show abstract

Section: Deep Learningmentioning

confidence: 99%

Section: Deep Learningmentioning

confidence: 99%

Securing the Dynamic Realm: A Comprehensive Review of ML Algorithms in IoT-Based Home Automation Systems and Beyond

2024

IJETER

View full text Add to dashboard Cite

show abstract

“…They can acquire knowledge about the intricate arrangement and qualities of the image, resulting in the successful elimination of noisy disturbances and the preservation of a greater amount of detailed data. However, in order to achieve the optimal denoising effect for some forms of noise or complex image structures, it is necessary to employ specific designs and make adjustments [16,17].…”

Section: Introductionmentioning

confidence: 99%

EDUNet++: An Enhanced Denoising Unet++ for Ice-Covered Transmission Line Images

Zhang,

Dou,

Zhao

et al. 2024

Electronics

View full text Add to dashboard Cite

New technology has made it possible to monitor and analyze the condition of ice-covered transmission lines based on images. However, the collected images are frequently accompanied by noise, which results in inaccurate monitoring. Therefore, this paper proposes an enhanced denoising Unet++ for ice-covered transmission line images (EDUNet++). This algorithm mainly comprises three modules: a feature encoding and decoding module (FEADM), a shared source feature fusion module (SSFFM), and an error correction module (ECM). In the FEADM, a residual attention module (RAM) and a multilevel feature attention module (MFAM) are proposed. The RAM incorporates the cascaded residual structure and hybrid attention mechanism, that effectively preserve the mapping of feature information. The MFAM uses dilated convolution to obtain features at different levels, and then uses feature attention for weighting. This module effectively combines local and global features, which can better capture the details and texture information in the image. In the SSFFM, the source features are fused to preserve low-frequency information like texture and edges in the image, hence enhancing the realism and clarity of the image. The ECM utilizes the discrepancy between the generated image and the original image to effectively capture all the potential information in the image, hence enhancing the realism of the generated image. We employ a novel piecewise joint loss. On the dataset of ice-covered transmission lines, PSNR (peak signal to noise ratio) and SSIM (structural similarity) achieved values of 29.765 dB and 0.968, respectively. Additionally, the visual effects exhibited more distinct detailed features. The proposed method exhibits superior noise suppression capabilities and robustness compared to alternative approaches.

show abstract

“…From surveillance to autonomous navigation, RGB pictures have emerged as the default option for perception systems. Numerous computer vision techniques, particularly those that use deep learning, were developed as a result of the pictures' richness in semantic information [1] [2] [3]. Lightning circumstances, however, limit our capacity to provide information.…”

Section: Introductionmentioning

confidence: 99%

Image Translation and Reconstruction Using a Single Dual Mode Lightweight Encoder

Amendola,

Cenkeramaddi,

Jha

2024

IEEE Access

View full text Add to dashboard Cite

The richness of textures and semantic information from RGB images can be supplemented in computer vision by the robustness of thermal images to light variations and weather artifacts. While many models rely on inputs from one sensor modality, image translation among modalities can be a solution. The existing works use large models that only work in one translation direction. This cause problems in limited computation applications, as well as a lack of flexibility to work interchangeably for different modalities. Three channel cameras extract visually rich features, but processing them on embedded platforms becomes a bottleneck. Furthermore, edge computing systems impose the burden of compressing data to be sent elsewhere. To address these issues, we propose a novel architecture with a single lightweight encoder capable of working in dual mode, encoding inputs from both grayscale an thermal images into very compact latent vectors. The encoding is then used for cross-modal image translation, grayscale image colorization and thermal image reconstruction, thus allowing (a) different downstream tasks on different modalities, (b) visually rich features from grayscale images and (c) data compression. Four different generators are employed and the training occurs in adversarial fashion with two discriminators. The loss function proposed contains not only adversarial terms but also reconstruction error terms. They induce consistency and contrast preservation across translation and reconstruction. The results backed by evaluation over multiple metrics demonstrate that the model performs the tasks with competitive quality of translation/reconstruction of images with different lighting conditions. Finally, we perform ablation studies to demonstrate the effectiveness of loss terms combined. INDEX TERMS Generative Adversarial Networks (GAN), Image reconstruction, Image-to-image (I2I) translation

show abstract

A Comprehensive Review of Deep Learning-Based Real-World Image Restoration

Cited by 17 publications

References 168 publications

Securing the Dynamic Realm: A Comprehensive Review of ML Algorithms in IoT-Based Home Automation Systems and Beyond

Securing the Dynamic Realm: A Comprehensive Review of ML Algorithms in IoT-Based Home Automation Systems and Beyond

EDUNet++: An Enhanced Denoising Unet++ for Ice-Covered Transmission Line Images

Image Translation and Reconstruction Using a Single Dual Mode Lightweight Encoder

Contact Info

Product

Resources

About