Generative Adversarial Network Algorithm Research Articles

Hydroacoustic optimization with using Noise-GAN

In recent years, noise pollution has a significant impact on marine organisms, hence requiring some restrictions and safety protocols. The primary objective of these restrictions is to minimize the noise generated by human-driven vehicles in aquatic environments. As a result, hydroacoustical studies are becoming increasingly integrated into design studies. The objective of this study is to provide an innovative approach to the design of hydrofoils, are considered a crucial component in the field of hydroacoustic engineering. The objective of this approach is to create a cutting-edge optimization tool through the integration of machine learning and hydroacoustic performance calculations. This article presents the development of a novel method called Noise-GAN, combines Generative Adversarial Networks (GAN) algorithms with hydroacoustic optimization capabilities. The GAN algorithm is used as a dimensionality reduction method in the optimization process, allowing for quick exploration of the design space and obtaining unique profile geometries during optimization. This method is used to generate optimal hydrofoil geometry for various conditions. The hydroacoustic and hydrodynamic performances of the generated geometry are analyzed to determine the applicability and performance of the method. The results are compared to two existing dimensionality reduction method to enhance comprehension of the performance. In order to gain insight into the performance of generated geometries compared to traditional geometries, the results are also compared to the performance data of the profiles available in the literature. This article also includes comparing the performance results of the NACA0009 profile, which is typically employed in hydrofoil research, with the optimal geometries to evaluate of the method and the performance of the generated geometries. In order to determine the real-life applicability of the hydrofoil geometries generated by the method, optimization studies were performed at the five different Angle of Attack (AoA) conditions within the range of 0o - 15o. In this way, the feasibility of the method at different AoA values was also examined. The results of all these comparisons demonstrate that the Noise-GAN method, which was developed to generate hydroacoustically optimized hydrofoil geometry, is highly effective in a variety of respects. The optimization tool developed in this study generates hydrodynamically efficient and unique hydrofoil profiles while optimizing for hydroacoustical performance. The results of this study are presented in this paper.

Feature Separation and Fusion to Optimise the Migration Model of Mural Painting Style in Tombs

Tomb murals are different from cave temple murals and temple murals, as they are underground cultural relics, their painting style is unique, solemn, and austere, and the performance image is characterised by simple colours, low contrast, and fewer survivors. During the digital restoration process, it is important to have sufficient reference samples to ensure the accuracy of the restoration. In addition, the style of mural paintings in the tombs varies greatly from other styles of murals and types of word paintings. Therefore, learning the unique artistic style of tomb murals, providing stylistically consistent training samples for digital restoration, and overcoming the problems of dim lighting and complex surface granularity of tomb murals are all necessary for research. This paper proposes a generative adversarial network algorithm that separates and fuses style features to enhance the generative network’s ability to acquire image information. The algorithm extracts underlying and surface style feature details of the image to be tested and conducts fusion generation experiments. The generative network’s parsing layer modifies the input noise tensor and optimises the corresponding weights to prevent misalignment between drawing lines and fresco cracks. Finally, to optimise the fresco generation effect, we add the corresponding loss function in the discriminator. The tomb murals dataset was established for experiments and tests, and quantitatively and qualitatively analysed with other style migration models, and SSIM, FID, LPIPS and NIQE were used as evaluation indexes. The results were 0.97, 269.579, 0.425 and 3.250, respectively, and the effect of style migration of this paper’s method was significantly higher than that of the control group model.

Cotton Fusarium wilt diagnosis based on generative adversarial networks in small samples.

This study aimed to explore the feasibility of applying Generative Adversarial Networks (GANs) for the diagnosis of Verticillium wilt disease in cotton and compared it with traditional data augmentation methods and transfer learning. By designing a model based on small-sample learning, we proposed an innovative cotton Verticillium wilt disease diagnosis system. The system uses Convolutional Neural Networks (CNNs) as feature extractors and applies trained GAN models for sample augmentation to improve classification accuracy. This study collected and processed a dataset of cotton Verticillium wilt disease images, including samples from normal and infected plants. Data augmentation techniques were used to expand the dataset and train the CNNs. Transfer learning using InceptionV3 was applied to train the CNNs on the dataset. The dataset was augmented using GAN algorithms and used to train CNNs. The performances of the data augmentation, transfer learning, and GANs were compared and analyzed. The results have demonstrated that augmenting the cotton Verticillium wilt disease image dataset using GAN algorithms enhanced the diagnostic accuracy and recall rate of the CNNs. Compared to traditional data augmentation methods, GANs exhibit better performance and generated more representative and diverse samples. Unlike transfer learning, GANs ensured an adequate sample size. By visualizing the images generated, GANs were found to generate realistic cotton images of Verticillium wilt disease, highlighting their potential applications in agricultural disease diagnosis. This study has demonstrated the potential of GANs in the diagnosis of cotton Verticillium wilt disease diagnosis, offering an effective approach for agricultural disease detection and providing insights into disease detection in other crops.

Synthetic Tabular Data Based on Generative Adversarial Networks in Health Care: Generation and Validation Using the Divide-and-Conquer Strategy.

Synthetic data generation (SDG) based on generative adversarial networks (GANs) is used in health care, but research on preserving data with logical relationships with synthetic tabular data (STD) remains challenging. Filtering methods for SDG can lead to the loss of important information. This study proposed a divide-and-conquer (DC) method to generate STD based on the GAN algorithm, while preserving data with logical relationships. The proposed method was evaluated on data from the Korea Association for Lung Cancer Registry (KALC-R) and 2 benchmark data sets (breast cancer and diabetes). The DC-based SDG strategy comprises 3 steps: (1) We used 2 different partitioning methods (the class-specific criterion distinguished between survival and death groups, while the Cramer V criterion identified the highest correlation between columns in the original data); (2) the entire data set was divided into a number of subsets, which were then used as input for the conditional tabular generative adversarial network and the copula generative adversarial network to generate synthetic data; and (3) the generated synthetic data were consolidated into a single entity. For validation, we compared DC-based SDG and conditional sampling (CS)-based SDG through the performances of machine learning models. In addition, we generated imbalanced and balanced synthetic data for each of the 3 data sets and compared their performance using 4 classifiers: decision tree (DT), random forest (RF), Extreme Gradient Boosting (XGBoost), and light gradient-boosting machine (LGBM) models. The synthetic data of the 3 diseases (non-small cell lung cancer [NSCLC], breast cancer, and diabetes) generated by our proposed model outperformed the 4 classifiers (DT, RF, XGBoost, and LGBM). The CS- versus DC-based model performances were compared using the mean area under the curve (SD) values: 74.87 (SD 0.77) versus 63.87 (SD 2.02) for NSCLC, 73.31 (SD 1.11) versus 67.96 (SD 2.15) for breast cancer, and 61.57 (SD 0.09) versus 60.08 (SD 0.17) for diabetes (DT); 85.61 (SD 0.29) versus 79.01 (SD 1.20) for NSCLC, 78.05 (SD 1.59) versus 73.48 (SD 4.73) for breast cancer, and 59.98 (SD 0.24) versus 58.55 (SD 0.17) for diabetes (RF); 85.20 (SD 0.82) versus 76.42 (SD 0.93) for NSCLC, 77.86 (SD 2.27) versus 68.32 (SD 2.37) for breast cancer, and 60.18 (SD 0.20) versus 58.98 (SD 0.29) for diabetes (XGBoost); and 85.14 (SD 0.77) versus 77.62 (SD 1.85) for NSCLC, 78.16 (SD 1.52) versus 70.02 (SD 2.17) for breast cancer, and 61.75 (SD 0.13) versus 61.12 (SD 0.23) for diabetes (LGBM). In addition, we found that balanced synthetic data performed better. This study is the first attempt to generate and validate STD based on a DC approach and shows improved performance using STD. The necessity for balanced SDG was also demonstrated.

A novel occluded face detection approach using Enhanced ORB and optimized GAN

Objectives:This research presents an approach to detect occluded face images. In order to achieve this, the research presents a novel technique that involves feature extraction and occluded face recognition. Methods: Feature extraction is performed by the enhanced ORB algorithm, which is proposed by the modification of the Oriented Fast and Rotated Brief (ORB) algorithm, by adding a phase for contrast adjustment, together with CNN features. For occluded face recognition, a Generative Adversarial Network (GAN) optimized by the proposed SR-SSA is designed. SR-SSA is proposed by the integration of Search and Rescue Optimization (SAR) in the Sparrow Search Algorithm (SSA). Results: The experimental results demonstrate that the SR-SSA-based GAN algorithm outperforms existing methods in terms of accuracy of 0.956, FAR of 0.045 and FRR of 0.021.

The Pattern Design of A Camouflage Suit Based on the Cycle Generative Adversarial Network Algorithm

Camouflage refers to an essential means of protection for military reconnaissance. However, the traditional method of camouflage image generation does not allow for end-to-end generation. The algorithm of Cycle Generative Adversarial Network adopted in this article can not only keep the features of original pictures but also realize the end-to-end generation, which can better solve seasonal problems better. The generation model and the discrimination model are trained using the concept of the cyclic confrontation game of Cycle GAN. In the training process, the loss function served to stimulate the background image and camouflage images mapping to each other. The generated image is captured into the recognition model for recognition, so as to provide feedback on the findings. Finally, the camouflage image with background image characteristics is output to realize the generation of an end-to-end camouflage image. The camouflage evaluation index is used to detect the quality of color, texture, and edge of the experimental output image. The generated image shows a good camouflage effect in the color, texture, and comparison of edges, thus verifying the effectiveness of the practical scheme.

Real-time marine target recognition method of underwater inspection robot based on computer vision

In the complex marine environment, target recognition is difficult, and the real-time detection has a slow speed. In this article, a target recognition method combining underwater generative adversarial network and improved YOLOv4 is proposed, which is named M-YOLOv4. Firstly, the images collected by the underwater inspection robot are enhanced using the underwater generative adversarial network algorithm to obtain the training datasets. Secondly, the YOLOv4 target detection algorithm combines the feature extraction network of MoblieNetv3 for lightweight processing, which reduces the network model size, and reduces the number of algorithm calculations and parameters. Then, change the size of the spatial pyramid pooling module pooling kernel, which can enlarge receptive field and integrate characteristics of different receptive fields. Finally, the processed datasets are transferred to the improved M-YOLOv4 algorithm for training, and the trained model is transplanted to the Jetson Nano hardware device for real-time detection. The results of experiments show that the mean average precision value of the improved M-YOLOv4 recognition is 90.77%, which is 2.02% higher than that of the unimproved one. The frame per second value of the lightweight YOLOv4 algorithm with MobileNetv3 is 27, an increase of 12 compared with YOLOv4. The improved M-YOLOv4 algorithm can perform accurate detection of marine multi-targets on embedded devices.

Internet speech denoising method based on IGAN algorithm

At present, to settle the question of excessive noise in the speech signal during the call of mobile devices in China, the research proposes that the Wiener filter and the generative adversarial network are combined into the IGAN algorithm. Firstly, the Wiener filter regularization algorithm is introduced to construct the preprocessing model of the speech signal; then the preprocessing model is fused with the generative adversarial network algorithm to construct the denoising model. Finally, the performance analysis and simulation experiments of the application effect of the model are carried out. The results show that in the experiment comparing IGAN with five traditional algorithms, when the SNR ratio is increased to 17.5 dB, the MOS and PESQ scores under the IGAN method can reach 4.9 and 3.5 respectively, and the DNN effect is second only to IGAN. Other algorithms perform poorly. Then compare the number of iterations and the loss value between the two. When the network voice signal begins to converge, the loss value corresponding to DNN is 1.132; while the loss value of IGAN is about 0.573, it can be found that the loss value of IGAN has dropped by half, which shows that IGAN Build the model with a smaller loss value. And IGAN tends to converge when iteratively is performed for about 200 times, and the average peak SNR can reach up to 33.85 dB, an increase of nearly 1.02 dB, and the effect is remarkable. This all shows that the IGAN algorithm has the best denoising performance for network speech signals, improves the denoising efficiency, and is conducive to obtaining a denoising signal with a higher fit with the clean signal, so that mobile devices can better serve the people.

Use of Generative Adversarial Network Algorithm in Super-Resolution Images to Increase the Quality of Digital Elevation Models Based on ALOS PALSAR Data

Digital elevation models are responsible for providing altimetric information on a surface to be mapped. While global models of low and medium spatial resolution are available open source by several space agencies, the high- resolution ones, which are utilized in scales 1:25,000 and larger, are scarce and expensive. Here we address this limitation by the utilization of deep learning algorithms coupled with Single Image Super-Resolution techniques in digital elevation models to obtain better spatial quality versions from lower resolution inputs. The development of a GAN-based (Generative Adversarial Network-based) methodology enables the improvement of the initial spatial resolution of low-resolution images. In the geospatial data context, for example, these algorithms can be used with digital elevation models and satellite images. The methodological approach uses a dataset with digital elevation models SRTM (Shuttle Radar Topography Mission) (30 meters of spatial resolution) and ALOS PALSAR (12.5 meters of spatial resolution), created with the objective of allowing the study to be carried out, promoting the emergence of new research groups in the area as well as enabling the comparison between the results obtained. It has been found that by increasing the number of iterations the performance of the generated model was improved and the quality of the generated image increased. Furthermore, the visual analysis of the generated image against the high- and low-resolution ones showed a great similarity between the first two.

Improved SinGAN for Single-Sample Airport Runway Destruction Image Generation

Aims: To solve the problem of difficult acquisition of airport runway destruction image data. Objectives: This paper introduces SinGAN, a single-sample generative adversarial network algorithm. Methods: To address the shortcomings of SinGAN in image realism and diversity generation, an improved algorithm based on the combination of Gaussian error linear unit GELU and efficient channel attention mechanism ECANet is proposed Results: Experiments show that its generated image results are subjectively better than SinGAN and its lightweight algorithm ConSinGAN, and the model can obtain an effective balance in both quality and diversity of image generation. Conclusion: The algorithm effect is also verified using three objective evaluation metrics, and the results show that the method in this paper effectively improves the generation effect compared with SinGAN, in which the SIFID metric is reduced by 46.67%.

Implementation of Generative Adversarial Network (GAN) Method for Pneumonia Dataset Augmentation

As a communicable disease, the majority of pneumonia cases are brought on by bacteria or viruses, which cause the lungs' alveoli to swell with fluid or mucus. Pneumonia may arise from this and further making breathing challenging since the lungs' air sacs are unable to contain enough oxygen for the body. Pneumonia may generally be diagnosed clinically (by a physician based on physical symptoms) as well as through a photo chest radiograph, CT scan, and MRI. In this case, the lower cost of a chest radiograph examination making it as one of the most popular medical imaging tests. However, chest radiograph photo readings have a disadvantage, where it takes a long time for medical staff or physicians to identify the patient's illness since it is difficult to detect the condition. Therefore, an identification of chest radiograph imagery into various forms using machine learning becomes one way to address this issue. This research focuses on building a deep neural network model using techniques from the Generative Adversarial Network algorithm. GAN is a category of machine learning techniques using two models to be trained simultaneously, one is a generator model to generated fake data and the other is a discriminator model used to separate the raw data from the real data set images. The dataset used is Chest X-Ray images obtained from repo GitHub and repo Kaggle totaling 5,863 with normal data 1583 images and pneumonia data 4273 imagesThe results showed that the use of the Generative Adevrsarial Network method as augmentation data proved to be more effective in improving the generalization of neural networks, this can be seen from the results the result of the accuracy value obtained is 97%.

Network life time augmentation of WSN through efficient energy using GAN algorithm

The minimal energy sensor nodes are critical to the long-term viability of any wireless sensor network WSN). Clustering is used for this purpose. Choosing an efficient Cluster Head (CH) is critical in such cluster-based networks, as they are accountable for aggregating and transmitting data from their associate nodes to the base station (BS). A Generative Adversarial Networks (GAN) is proposed in this work to improve the selection of CH. As part of the fitness function, nodes’ residual energy, average energy, and inter-cluster distance are all considered. In an effort to further reduce energy consumption, a GAN routing method is proposed for use at the base station level for Efficient Energy. Simulations are used to evaluate the proposed ideal.The WSNs which require long life time with minimum cost sensors demand the proposed work. The research about the human unattainable places can be fit to necessitate this work. This method supports the maintenance of mines and petroleum refineries. In terms of energy consumption and network life expectancy, the results demonstrate a substantial improvement. And also, the proposed technique is analyzed and compared along with the existing approaches as Low-Energy Adaptive Clustering Hierarchy (Security based (S-LEACH), Cluster based (C-LEACH, More Energy Efficient-LEACH) (ME-LEACH) schemes. The proposed method detects the best location of storage-nodes for the sensor network. There is no need of agitation on battery drain up of storage-nodes (because of wireless recharge) which is a highly energy spending unit. The proposed method improves the network lifetime by a significant level. The proposed method is best fit to mines, petroleum refineries, forest department and military. The proposed method behaves as not only better storage scheme but also best fit to retrieval schemes.

Implementasi Steganografi Gambar Menggunakan Algoritma Generative Adversarial Network

Abstract
 In the era of information technology, it is very important to protect data and information so that irresponsible parties do not misuse it. One technique for securing data is steganography. Steganography is a technique of hiding messages in a medium. One of the media for hiding messages is pictures. However, steganography techniques can still be detected by steganalysis techniques. Steganalysis is a technique for analyzing hidden messages in steganography. Therefore this study applies image processing techniques with the Generative Adversarial Network algorithm model, which aims to manipulate images so that steganalysis techniques cannot detect hidden messages. Proof of the results of applying the Generative Adversarial Network algorithm using a web-based application containing message hiding and extraction functions. The results obtained are that the Generative Adversarial Network algorithm can be applied to create mock objects, and images can revive based on training data which is a model for how the algorithm works. In addition, the results of testing the Generative Adversarial Network algorithm were successfully applied to image steganography which functions to prevent steganalysis techniques from trying to detect messages in images. Future research is expected to be able to select steganographic images other than the results from the training data model according to the original size chosen randomly according to the selection of the user.

A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications

Generative adversarial networks (GANs) have recently become a hot research topic; however, they have been studied since 2014, and a large number of algorithms have been proposed. Nevertheless, few comprehensive studies explain the connections among different GAN variants and how they have evolved. In this paper, we attempt to provide a review of the various GAN methods from the perspectives of algorithms, theory, and applications. First, the motivations, mathematical representations, and structures of most GAN algorithms are introduced in detail, and we compare their commonalities and differences. Second, theoretical issues related to GANs are investigated. Finally, typical applications of GANs in image processing and computer vision, natural language processing, music, speech and audio, the medical field, and data science are discussed.

URBAN MAP GENERATION IN ARTIST’S STYLE USING GENERATIVE ADVERSARIAL NETWORKS (GAN)

Artificial Intelligence is a field that is able to learn from existing data to synthesize new ones using deep learning methods. Using Artificial Neural Networks that process big datasets, complex tasks and challenges become easily resolved. As the zeitgeist suggests, it is possible to produce novel outcomes for future projections by applying various machine learning algorithms on the generated data sets. In that context, the focus of this research is exploring the reinterpretation of 21st century urban plans with familiar artist styles using different subtypes of deep-learning-based generative adversarial networks (GAN) algorithms. In order to explore the capabilities of urban map transformation with machine learning approaches, two different GAN algorithms which are cycleGAN and styleGAN have been applied on the two main data sets. First data set, the urban data set, contains 50 cities urban plans in .jpeg format collected according to the diversity of the urban morphologies. Whereas the second data set is composed of four well-known artist’s paintings, that belong to various artistic movements. As a result of training the same data sets with different GAN algorithms and epoch values were compared and evaluated. In this respect, the study not only investigates the reinterpretation of stylistic urban maps and shows the discoverability of new representation techniques, but also offers a comparison of the use of different image to image translation GAN algorithms.

A decision-making method for reservoir operation schemes based on deep learning and whale optimization algorithm.

Reservoir operation is an important part of basin water resources management. The rational use of reservoir operation scheme can not only enhance the capacity of flood control and disaster reduction in the basin, but also improve the efficiency of water use and give full play to the comprehensive role the reservoir. The conventional decision-making method of reservoir operation scheme is computationally large, subjectivity and difficult to capture the nonlinear relationship. To solve these problems, this paper proposes a reservoir operation scheme decision-making model IWGAN-IWOA-CNN based on artificial intelligence and deep learning technology. In view of the lack of data in the original reservoir operation scheme and the limited improvement of data characteristics by the traditional data augmentation algorithm, an improved generative adversarial network algorithm (IWGAN) is proposed. IWGAN uses the loss function which integrates Wasserstein distance, gradient penalty and difference item, and dynamically adds random noise in the process of model training. The whale optimization algorithm is improved by introducing Logistic chaotic mapping to initialize population, non-linear convergence factor and adaptive weights, and Levy flight perturbation strategy. The improved whale optimization algorithm (IWOA) is used to optimize hyperparameters of convolutional neural networks (CNN), so as to obtain the best parameters for model prediction. The experimental results show that the data generated by IWGAN has certain representation ability and high quality; IWOA has faster convergence speed, higher convergence accuracy and better stability; IWGAN-IWOA-CNN model has higher prediction accuracy and reliability of scheme selection.

Single-Location and Multi-Locations Scenarios Generation for Wind Power Based On WGAN-GP

To address the randomness of renewable energy, scenario generation can simulate the random process of renewable energy. Still, most of the previous scenario generation algorithms are based on assumed probability distribution models, which are difficult to grasp the dynamic characteristics of renewable energy accurately. Based on an improved generative adversarial network algorithm, this paper generates single-site and multi-site scenarios for wind power generation data. The temporal and spatial correlations of the generated data were judged based on the maximum mean difference and the Pearson coefficient. Finally, multiple sets of wind power generation data are used to verify that the proposed method can reflect not only the volatility of renewable energy but also ensure the temporal and spatial correlation between the data.

Self-Supervised Metalearning Generative Adversarial Network for Few-Shot Fault Diagnosis of Hoisting System With Limited Data

Few-shot data collected from hoisting system suffer from inadequate information in the practical industries, which reduces the diagnostic accuracy of the data-driven-based fault diagnosis approaches. To overcome this problem, in this article, a self-supervised metalearning generative adversarial network algorithm is proposed. The purpose of the proposed algorithm is to determine the optimal initialization parameters of the model by training on various data generation tasks, thus accomplishing new data generation using only a small amount of training data. Specifically, a self-supervised strategy is proposed to improve the generalization performance of the proposed algorithm. Besides, the fault data of the hoisting system are collected for data generation, and the experimental results show that the proposed algorithm can determine the optimal initialization parameters under the condition of insufficient datasets. The effectiveness of the proposed algorithm for few-shot fault diagnosis is verified by using a mixture of real data and generated data.

An improved generative adversarial networks for remote sensing image super-resolution reconstruction via multi-scale residual block

Existing image super-resolution algorithms still suffer from the problems of not extracting rich image features and losing realistic high-frequency details. In order to solve these problems, this paper proposes an improved generative adversarial network algorithm for super-resolution reconstruction of remote sensing images by multi-scale residual blocks. The original generative adversarial network (GAN) structure is improved and multi-scale residual blocks are introduced in the generator to fuse features at different scales. After extracting the parallel information of multi-scale features, information is exchanged between multi-resolution information streams to obtain contextual information through spatial and channel attention mechanisms, and multi-scale features are fused according to the attention mechanism. In the discriminator, the concept of relative average GAN (RaGAN) is introduced, and the loss function of the network is redesigned so that the discriminator can predict relative probabilities instead of absolute probabilities thus enabling clear learning of edge and texture details. Experimental results show that the proposed method in this paper significantly outperforms state-of-the-art (SOTA) methods in terms of both subjective and objective metrics.In three test datasets, compared with SOTA methods, the Peak Signal to Noise Ratio(PSNR) is improved by a maximum of 1.18 dB, 0.84 dB and 1.29 dB respectively, and the Structural Similarity Index (SSIM) is improved by 0.0264, 0.0077 and 0.0109 respectively in scale of 2, 3 and 4 times images super-resolution.The model proposed in this paper effectively improved the super-resolution re-construction results of remote sensing images.

Comparative analysis of some selected generative adversarial network models for image augmentation: a case study of COVID-19 x-ray and CT images

One of the fastest-growing fields in today’s world is data analytics. Data analytics paved the way for a significant number of research and development in various fields including medicine and vaccine development, DNA analysis, artificial intelligence and many more. Data plays a very important role in providing the required results and helps in making critical decisions and predictions. However, ethical and legislative restrictions sometimes make it difficult for scientists to acquire data. For example, during the COVID-19 pandemic, data was very limited due to privacy and regulatory issues. To address data unavailability, data scientists usually leverage machine learning algorithms such as Generative Adversarial Networks (GAN) to augment data from existing samples. Today, there are over 450 algorithms that are designed to re-generate or augment data in case of unavailability of the data. With many algorithms in the market, it is practically impossible to predict which algorithm best fits the problem in question, unless many algorithms are tested. In this study, we select the most common types of GAN algorithms available for image augmentation to generate samples capable of representing a whole data distribution. To test the selected models, we used two unique datasets, namely COVID-19 CT images and COVID-19 X-Ray images. Five different GAN algorithms, namely CGAN, DCGAN, f-GAN, WGAN, and CycleGAN, were selected and applied to the samples to see how each algorithm reacts to the samples. To evaluate their performances, Visual Turing Test (VTT) and Fréchet Inception Distance (FID) were used. The VTT result shows that a human expert can accurately distinguish between different samples that were produced. Hence, CycleGAN scored 80% in CT image dataset and 77% in X-Ray image dataset. In contrast, the FID result revealed that CycleGAN had a high convergence and therefore generated high quality and clearer images on both datasets compared to CGAN, DCGAN, f-GAN, and WGAN. This study concluded that the CycleGAN model is the best when it comes to image augmentation due to its friendliness and high convergence.