Enhancement Generative Adversarial Network Research Articles

Text to image synthesis with multi-granularity feature aware enhancement Generative Adversarial Networks

Synthesizing complex images from text presents challenging. Compared to autoregressive and diffusion model-based methods, Generative Adversarial Network-based methods have significant advantages in terms of computational cost and generation efficiency yet remain two limitations: first, these methods often refine all features output from the previous stage indiscriminately, without considering these features are initialized gradually during the generation process; second, the sparse semantic constraints provided by the text description are typically ineffective for refining fine-grained features. These issues complicate the balance between generation quality, computational cost and inference speed. To address these issues, we propose a Multi-granularity Feature Aware Enhancement GAN (MFAE-GAN), which allows the refinement process to match the order of different granularity features being initialized. Specifically, MFAE-GAN (1) samples category-related coarse-grained features and instance-level detail-related fine-grained features at different generation stages based on different attention mechanisms in Coarse-grained Feature Enhancement (CFE) and Fine-grained Feature Enhancement (FFE) to guide the generation process spatially, (2) provides denser semantic constraints than textual semantic information through Multi-granularity Features Adaptive Batch Normalization (MFA-BN) in the process of refining fine-grained features, and (3) adopts a Global Semantics Preservation (GSP) to avoid the loss of global semantics when sampling features continuously. Extensive experimental results demonstrate that our MFAE-GAN is competitive in terms of both image generation quality and efficiency.

DAE-GAN: Underwater Image Super-Resolution Based on Symmetric Degradation Attention Enhanced Generative Adversarial Network

Underwater images often exhibit detail blurring and color distortion due to light scattering, impurities, and other influences, obscuring essential textures and details. This presents a challenge for existing super-resolution techniques in identifying and extracting effective features, making high-quality reconstruction difficult. This research aims to innovate underwater image super-resolution technology to tackle this challenge. Initially, an underwater image degradation model was created by integrating random subsampling, Gaussian blur, mixed noise, and suspended particle simulation to generate a highly realistic synthetic dataset, thereby training the network to adapt to various degradation factors. Subsequently, to enhance the network’s capability to extract key features, improvements were made based on the symmetrically structured blind super-resolution generative adversarial network (BSRGAN) model architecture. An attention mechanism based on energy functions was introduced within the generator to assess the importance of each pixel, and a weighted fusion strategy of adversarial loss, reconstruction loss, and perceptual loss was utilized to improve the quality of image reconstruction. Experimental results demonstrated that the proposed method achieved significant improvements in peak signal-to-noise ratio (PSNR) and underwater image quality measure (UIQM) by 0.85 dB and 0.19, respectively, significantly enhancing the visual perception quality and indicating its feasibility in super-resolution applications.

Automatic bioacoustics noise reduction method based on a deep feature loss network

Acoustic sensors that collect acoustic data over extended periods and broad ranges are widely used in bioacoustics monitoring. However, in open environments, acoustic data collected using acoustic sensors can be subject to interference from various real-world noises, thereby influencing the subsequent analysis and processing of bioacoustic data. Existing bioacoustic noise reduction methods are limited in their application because of their low efficiency, unsuitability for non-stationary noise, generally unimproved signal-to-noise ratio (SNR) efficacy, and considerable amounts of residual noise. These limitations hinder the effective processing of recorded signals for which extraneous noise overlaps with bird vocalizations. In this study, we propose a bioacoustic noise reduction method based on a deep feature loss network for bird sounds. The method has a rapid denoising speed and can more effectively remove background noise from field recording signals without distorting the bird acoustic spectrum. The denoising effects of the proposed method were compared with those of a speech enhancement generative adversarial network, web real-time communications denoising, and other noise reduction methods. The denoising ability of these methods for different noises was evaluated using spectrograms and objective evaluation measures such as the SNR and perceptual evaluation of speech quality (PESQ). The experimental results revealed that our proposed noise reduction method can obtain higher SNRs and PESQ scores than other noise reduction methods, with the SNR increasing by up to 35.83 dB following denoising.

Enhancing image style transfer for real-time indoor geometric data using GAN

<p>The need for two-dimensional (2D) simulated environments, such as those seen in VR/AR and the multiverse, has grown substantially in the rapidly emerging modern era. To reduce the need for human interaction, the present studies have focused on the automated transfer of image processing styles inside a 2D virtual world through the application of computer vision. However, there are several limits to the current research on 2D environment-style transfers that rely on modelling. One thing to keep in mind is that there is a significant amount of style image data required for training a style transfer network specifically for 2D simulations. All this information must be combined with perspectives that are fairly accurate representations of the internet. The second issue was that the 2D structures were inconsistent. Most of the research relies on 2D input image attributes and ignores 2D scene geometric data. Lastly, changing the way something looks does not change the fact that every object has its own distinct qualities. To address these issues, we propose an enhanced Generative Adversarial Networks (GAN) approach for image style transfer in which oversampling and fine tuning is used to improve the data loss. Image Style transfer is an approach to image-to-image translation that supports the transfer of the style of an image to a real-time image and is mainly used to enhance the resolution and quality of an image. The performance of the proposed approach is analyzed using the MIT dataset, which is retrieved from Kaggle. It is an open-source dataset that contains 67 indoor categories and has more than 15,000 images. The proposed approach is implemented using MATLAB simulation tool. The results of proposed approach show that, content loss and style loss are lower than other deep learning models such as VGG16 and Alex Net.</p>

Statistics Enhancement Generative Adversarial Networks for Diverse Conditional Image Synthesis

Statistics Enhancement Generative Adversarial Networks for Diverse Conditional Image Synthesis

LEGAN: A low-light image enhancement generative adversarial network for industrial internet of smart-cameras

The utilization of smart-cameras in the context of the Internet of Things (IoT) has become increasingly prevalent within smart workshops for performing in-situ quality inspection tasks. However, it is worth noting that these smart-cameras may encounter operational challenges when functioning under low-light conditions. The images acquired in such situation are severely degraded, resulting in the performance decline of the subsequent detection algorithms. Focusing on non-stationary noise compression and detail recovery, this paper constructs a novel enhancement model called LEGAN for the industrial internet of smart-cameras system. Firstly, the input undergoes a decomposition process into two branches using the Harr-wavelet technique. These branches are subsequently encoded independently by a series of compact residual blocks, facilitating effective noise suppression. Secondly, in order to enhance detail recovery, a feature selection module is meticulously designed to extract correlations between image foreground–background and low–high frequency signals, ultimately reconstructing a comprehensive feature map. This enables a multi-scale stepwise up-sampling approach that facilitates image recovery based on the reconstructed feature maps. Lastly, the training phase is supervised by an adversarial loss, comprising MSE loss, VGG loss, and discriminating loss, which ensures a harmonious balance between noise suppression and detail recovery. Comparative experiments clearly show the superiority of the LEGAN in terms of noise compression and detail recovery. Moreover, from an industrial practice perspective, the application of the proposed approach to yarn evenness inspection has proven to be highly effective, significantly enhancing detection accuracy in low-light environments.

LAE-GAN: a novel cloud-based Low-light Attention Enhancement Generative Adversarial Network for unpaired text images

With the widespread adoption of mobile multimedia devices, the deployment of compute-intensive inference tasks on edge and resource-constrained devices, particularly in the context of low-light text detection, remains a formidable challenge. Existing deep learning approaches have shown limited effectiveness in restoring images for extremely dark scenes. To address these limitations, this paper presents a novel cloud-based Low-light Attention Enhancement Generative Adversarial Network for unpaired text images (LAE-GAN) for the non-paired text image enhancement task in extremely low-light conditions. In the first stage, compressed low-light images are transmitted from edge devices to a cloud server for image enhancement. The LAE-GAN, an end-to-end network comprising a Zero-DCE and AGM-net generator, is designed with a global and local discriminator structure. The initial illumination restoration of extremely low-light images is accomplished using the Zero-DCE network. To enhance text details, we propose an Enhanced Text Attention Mechanism (ETAM) that transforms text information into a comprehensive text attention mechanism across the entire network. The Sobel operator is employed to extract text edge information, while attention is focused on text region details through constraints imposed on the attention map and edge map. Additionally, an AGM-Net module is integrated to reduce noise and fine-tune illumination. In the second stage, the cloud server makes decisions based on user requirements and processes requests in parallel, scaling with the quantity of requests. In the third stage, the enhanced results are transmitted back to edge devices for text detection. Experimental results on widely used LOL and SID low-light datasets demonstrate significant improvements in both quantitative and qualitative analysis, surpassing state-of-the-art enhancement methods in terms of image restoration and text detection.

An Enhancement Generative Adversarial Networks Based on Feature Moving for Solar Panel Defect Identification

An Enhancement Generative Adversarial Networks Based on Feature Moving for Solar Panel Defect Identification

Underwater Image Enhancement Based on Hybrid Enhanced Generative Adversarial Network

In recent years, underwater image processing has played an essential role in ocean exploration. The complexity of seawater leads to the phenomena of light absorption and scattering, which in turn cause serious image degradation problems, making it difficult to capture high-quality underwater images. A novel underwater image enhancement model based on Hybrid Enhanced Generative Adversarial Network (HEGAN) is proposed in this paper. By designing a Hybrid Underwater Image Synthesis Model (HUISM) based on a physical model and a deep learning method, many richly varied paired underwater images are acquired to compensate for the missing problem of underwater image enhancement dataset training. Meanwhile, the Detection Perception Enhancement Model (DPEM) with Perceptual Loss is designed to transfer the coding knowledge in the form of the gradient to the enhancement model through the perceptual loss, which leads to the generation of visually better and detection-friendly underwater images. Then, the synthesized and enhanced models are integrated into an adversarial network to generate high-quality underwater clear images through game learning. Experiments show that the proposed method significantly outperforms several state-of-the-art methods both qualitatively and quantitatively. Furthermore, it is also demonstrated that the method can improve target detection performance in underwater environments, which has specific application value for subsequent image processing.

SEGAN-BASED LESION SEGMENTATION AND OPTIMIZED RideNN FOR DIABETIC RETINOPATHY CLASSIFICATION

The most significant issue with diabetes is diabetic retinopathy (DR), which is the primary cause of blindness. DR typically develops no symptoms at the beginning of the disease, thus numerous physical examinations, including pupil dilation and a visual activity test, are necessary for DR identification. Due to the differences and challenges of DR, it is more challenging to identify it during the manual assessment. For DR patients, visual loss is prevented thanks to early detection and accurate therapy. Therefore, it is even more necessary to classify the severity levels of DR in order to provide a successful course of treatment. This study develops a deep learning method based on chronological rider sea lion optimization (CRSLO) for the classification of DR. The segmentation process divides the image into multiple subgroups, which is necessary for the appropriate detection and classification procedure. For the efficient identification of DR and classification of DR severity, the deep learning approach is used. Additionally, the CRSLO scheme is used to train the deep learning technique to achieve higher performance. With respect to testing accuracy, sensitivity, and specificity of 0.9218, 0.9304 and 0.9154, the newly introduced CRSLO-based deep learning approach outperformed other existing DR classification techniques like convolutional neural networks (CNNs), deep convolutional neural network (DCNN), synergic deep learning (SDL), HPTI-V4 and DR[Formula: see text]GRADUATE. The Speech Enhancement Generative Adversarial Network (SEGAN) model in use also produced increased segmentation accuracy of 0.90300.

Deep-learning visualization enhancement method for optical coherence tomography angiography in dermatology.

Optical coherence tomography angiography (OCTA) in dermatology usually suffers from low image quality due to the highly scattering property of the skin, the complexity of cutaneous vasculature, and limited acquisition time. Deep-learning methods have achieved great success in many applications. However, the deep learning approach to improve dermatological OCTA images has not been investigated due to the requirement of high-performance OCTA systems and difficulty of obtaining high-quality images as ground truth. This study aims to generate proper datasets and develop a robust deep learning method to enhance the skin OCTA images. A swept-source skin OCTA system was employed to create low-quality and high-quality OCTA images with different scanning protocols. We propose a model named vascular visualization enhancement generative adversarial network and adopt an optimized data augmentation strategy and perceptual content loss function to achieve better image enhancement effect with small amount of training data. We demonstrate the superiority of the proposed method in skin OCTA image enhancement by quantitative and qualitative comparisons.

A Novel Adversarial Learning Framework for Passive Bistatic Radar Signal Enhancement

Passive Bistatic Radar (PBR) has significant civilian and military applications due to its ability to detect low-altitude targets. However, the uncontrollable characteristics of the transmitter often lead to subpar target detection performance, primarily due to a low signal-to-noise ratio (SNR). Coherent accumulation typically has limited ability to improve SNR in the presence of strong noise and clutter. In this paper, we propose an adversarial learning-based radar signal enhancement method, called radar signal enhancement generative adversarial network (RSEGAN), to overcome this challenge. On one hand, an encoder-decoder structure is designed to map noisy signals to clean ones without intervention in the adversarial training stage. On the other hand, a hybrid loss constrained by L1 regularization, L2 regularization, and gradient penalty is proposed to ensure effective training of RSEGAN. Experimental results demonstrate that RSEGAN can reliably remove noise from target information, providing an SNR gain higher than 5 dB for the basic coherent integration method even under low SNR conditions.

An Enhanced Generative Adversarial Network Model for Fingerprint Presentation Attack Detection

An Enhanced Generative Adversarial Network Model for Fingerprint Presentation Attack Detection

K-NET+SEGAN-BASED SEGMENTATION WITH GANNET AQUILA OPTIMIZATION ALGORITHM-ENABLED DEEP MAXOUT NETWORK FOR BRAIN TUMOR CLASSIFICATION USING MRI

Segmentation and classification of brain tumor are time-consuming and challenging chore in clinical image processing. Magnetic Resonance Imaging (MRI) offers more information related to human soft tissues that assists in diagnosing brain tumor. Precise segmentation of the MRI images is vital to diagnose brain tumor by means of computer-aided medical tools. Afterwards suitable segmentation of MRI brain tumor images, tumor classification is performed that is a hard chore owing to complications. Therefore, Gannet Aquila Optimization Algorithm_deep maxout network (GAOA_DMN) and GAOA_K-Net+speech enhancement generative adversarial network (GAOA_K-Net+Segan) is presented for classification and segmentation of brain tumor utilizing MRI images. Here, pre-processing phase performs noise removal from input image utilizing the Laplacian filter and also the region of interest (ROI) extraction is also carried out. Then, segmentation of brain tumor is conducted by K-Net+Segan, which is combined by Motyka similarity. However, K-Net+Segan for segmentation is trained by GAOA that is an amalgamation of Gannet Optimization Algorithm (GOA) and Aquila Optimizer (AO). From segmented image, features are extracted for performing classification phase. At last, brain tumor classification is conducted by DMN, which is tuned by GAOA and thus, output is obtained. Furthermore, GAOA_K-Net+Segan obtained better outcomes in terms of segmentation accuracy whereas devised GAOA_DMN achieved maximum accuracy, true negative rate (TNR) and true positive rate (TPR) of 92.7%, 94.5% and 91.5%.

Automatic Kidney Segmentation Method Based on an Enhanced Generative Adversarial Network

When deciding on a kidney tumor's diagnosis and treatment, it is critical to take its morphometry into account. It is challenging to undertake a quantitative analysis of the association between kidney tumor morphology and clinical outcomes due to a paucity of data and the need for the time-consuming manual measurement of imaging variables. To address this issue, an autonomous kidney segmentation technique, namely SegTGAN, is proposed in this paper, which is based on a conventional generative adversarial network model. Its core framework includes a discriminator network with multi-scale feature extraction and a fully convolutional generator network made up of densely linked blocks. For qualitative and quantitative comparisons with the SegTGAN technique, the widely used and related medical image segmentation networks U-Net, FCN, and SegAN are used. The experimental results show that the Dice similarity coefficient (DSC), volumetric overlap error (VOE), accuracy (ACC), and average surface distance (ASD) of SegTGAN on the Kits19 dataset reach 92.28%, 16.17%, 97.28%, and 0.61 mm, respectively. SegTGAN outscores all the other neural networks, which indicates that our proposed model has the potential to improve the accuracy of CT-based kidney segmentation.

Adaptive and Efficient Hybrid In-loop Filter Based on Enhanced Generative Adversarial Networks with Sample Adaptive Offset Filter for HEVC/H-265

In this manuscript, an Adaptive and Efficient Hybrid In-loop Filter based on Enhanced Generative Adversarial Network Deblocking Filter (EGANDF) with Sample Adaptive Offset filter (EGANDF-SAO-HEVC) is proposed for High Efficiency Video Coding (HEVC)/H-265. In this, the proposed hybrid in-loop filter involves EGANDF and Sample Adaptive Offset (SAO) filter that lessens the blocking artifacts caused by block-wise processing for coding unit (CU), which is mainly used for improving the video quality. Initially, EGANDF is proposed for HEVC/H-265 for removing blocking artifacts along low computation. Here, the output of EGANDF is given to the SAO filter for reducing ringing artifacts by diminishing high-frequency components during quantization. Thus, the proposed method efficiently reduces artifacts for improving video quality performance. The proposed EGANDF-SAO-HEVC method is implemented in the working platform of HEVC reference software with MATLAB. Finally, the proposed EGANDF-SAO-HEVC model has attained 27.26%, 29.65%, 12.45% higher accuracy, 33.56%, 31.8%, 28.7% higher sensitivity, 34.7%, 33.5%, 32.6% higher specificity, 46.92%, 35.7%, 41.3% lower MSE, 25.7%, 29.7%, 35.6% higher PSNR, and 25.6%, 28.9%, 13.6% higher SSIM for using basketball video sequence when compared to the existing methods.

Sensor dynamic compensation method based on GAN and its application in shockwave measurement

Limited by the dynamic characteristics of the sensor, the high-frequency signal will be distorted by the dynamic error after passing through the sensor, which will affect the accuracy of the real value. To reduce the dynamic error, it is necessary to obtain a high-precision dynamic compensation model. This paper provides a solution of compensation model based on the deep learning method. First, the problem of limited sensor dynamic data is solved by data augmentation through Deep Convolutional Generative Adversarial Network. After that, the sensor compensation model is obtained by Speech Enhancement Generative Adversarial Network and applied to step signals and shockwave signals. This compensation method can compensate a variety of sensors used in the dynamic measurement. It is verified by the pressure sensor as an example in this paper, the results are better than that of traditional ones, the overshoot can be reduced from 119.2% to 2.5%, and the rising time is 5.5μs. The innovation of this paper is that we find a way to use deep learning methods to compensate sensor dynamic error based on a small dataset. At the same time, it is proved that this method has strong versatility, which is not available in traditional sensor compensation methods. It also provides a feasible scheme for the application of deep learning in dynamic compensation model calculation.

Advanced EGAN-IDS Framework for Resilience against Adversarial Attacks using Multi-headed Attention Module

A network's security depends heavily on its network intrusion detection system (NIDS). Monitoring network traffic continuously and spotting any unusual activity is its main duty. Even though several methods, such as machine learning-based network intrusion detection systems (ML-NIDSs), have been put forth and put into practice to improve the detection of malicious network traffic, many of the studies that have already been done do not adequately replicate real-world situations, where new attack types are continually emerging. Thus, more research is needed to determine how resistant intrusion detection systems are too adversarial and zero-day attacks. We provide and expand the Enhanced Generative Adversarial Network (EGAN-IDS) framework in this study. This framework creates hostile attack routes that are intended to avoid being discovered by five distinct Black Box ML-based intrusion detection systems. Artificial neural networks and self-awareness processes are used by EGAN-IDS to generate artificial adversarial attacks that are able to evade detection. According to our evaluation results, EGAN-IDS has produced adversarial patterns for a variety of attacks, which has reduced detection rates by an average of 15.93% for each of the five IDSs. These conclusions highlight the model's resilience and broad applicability.

Imbalanced medical disease dataset classification using enhanced generative adversarial network

In general, the imbalanced dataset is a major issue in health applications. The medical data classification faces the imbalanced count of data samples, here at least one class forms only a very small minority of the data, but it is a drawback of most of the machine learning algorithms. The medical datasets are mostly imbalanced in its class labels. When the dataset is imbalanced, the existing classification algorithms typically perform badly on minority class cases. To deal the class imbalance issue, an enhanced generative adversarial network (E-GAN) is proposed in this article. The proposed approach is the consolidation of deep convolutional generative adversarial network and modified convolutional neural network (DCG-MCNN). Initially, the imbalanced data is converted into balanced data in pre-processing process. Data preprocessing comprise of data cleaning, data normalization, data transformation and data reduction using Radius Synthetic minority oversampling technique (RSMOTE) method. The DCG is considered for balancing the dataset generating extra samples under training dataset. This training dataset based, the medical disease classification is enhanced by modified CNN diagnosis model. The proposed system performed is executed in MATLAB. The performance analysis is implemented under the Breast Cancer Wisconsin Dataset that provides the higher maximum geometry mean (MGM) of 8.686, 2.931 and 5.413%, and higher Matthews’s correlation coefficient (MCC) of 9.776, 1.841 and 5.413% compared to the existing methods.

Semi-Supervised DEGAN for Optical High-Resolution Remote Sensing Image Scene Classification

Semi-supervised methods have made remarkable achievements via utilizing unlabeled samples for optical high-resolution remote sensing scene classification. However, the labeled data cannot be effectively combined with unlabeled data in the existing semi-supervised methods during model training. To address this issue, we present a semi-supervised optical high-resolution remote sensing scene classification method based on Diversity Enhanced Generative Adversarial Network (DEGAN), in which the supervised and unsupervised stages are deeply combined in the DEGAN training. Based on the unsupervised characteristic of the Generative Adversarial Network (GAN), a large number of unlabeled and labeled images are jointly employed to guide the generator to obtain a complete and accurate probability density space of fake images. The Diversity Enhanced Network (DEN) is designed to increase the diversity of generated images based on massive unlabeled data. Therefore, the discriminator is promoted to provide discriminative features by enhancing the generator given the game relationship between two models in DEGAN. Moreover, the conditional entropy is adopted to make full use of the information of unlabeled data during the discriminator training. Finally, the features extracted from the discriminator and VGGNet-16 are employed for scene classification. Experimental results on three large datasets demonstrate that the proposed scene classification method yields a superior classification performance compared with other semi-supervised methods.