Generation Of Image Data Research Articles

Appearance-Based Gaze Estimation as a Benchmark for Eye Image Data Generation Methods

Data augmentation is commonly utilized to increase the size and diversity of training sets for deep learning tasks. In this study, we propose a novel application of an existing image generation approach in the domain of realistic eye images that leverages data collected from 40 subjects. This hybrid method combines the benefits of precise control over the image content provided by 3D rendering, while introducing the previously lacking photorealism and diversity into synthetic images through neural style transfer. We prove its general efficacy as a data augmentation tool for appearance-based gaze estimation when generated data are mixed with a sparse train set of real images. It improved the results for 39 out of 40 subjects, with an 11.22% mean and a 19.75% maximum decrease in gaze estimation error, achieving similar metrics for train and held-out subjects. We release our data repository of eye images with gaze labels used in this work for public access.

Synthetic Image Data Generation via Rendering Techniques for Training AI-Based Instance Segmentation

Synthetic image data generation has gained popularity in computer vision and machine learning in recent years. The work introduces a technique for creating artificial image data by utilizing 3D files and rendering methods in Python and Blender. The technique employs BlenderProc, a rendering tool for generating artificial images, to efficiently create a substantial amount of data. The output of the method is saved in JSON format, containing COCO annotations of objects in the images, facilitating seamless integration with current machine-learning pipelines. The paper shows that the created synthetic data can be used to enhance object data during simulation. The method can enhance the accuracy and robustness of machine-learning models by modifying simulation parameters like lighting, camera position, and object orientation to create a variety of images. This is especially beneficial for applications that require significant amounts of labelled real-world data, which can be time-consuming and labour-intensive to obtain. The study addresses the constraints and potential prejudices of creating synthetic data, emphasizing the significance of verifying and assessing the generated data prior to its utilization in machine learning models. Synthetic data generation can be a valuable tool for improving the efficiency and effectiveness of machine learning and computer vision applications. However, it is crucial to thoroughly assess the potential limitations and biases of the generated data. This paper emphasizes the potential of synthetic data generation to enhance the accuracy and resilience of machine learning models, especially in scenarios with limited access to labelled real-world data. This paper introduces a method that efficiently produces substantial amounts of synthetic image data with COCO annotations, serving as a valuable resource for professionals in computer vision and machine learning.

Synthetic image data generation via rendering techniques for training AI-based Instance Segmentation

Within the scope of the development of the project, the acceleration and gyro signal, VR implementation, and User Control for VR were realized. The starting point was a list of MPU9250 data, which are acceleration and gyro data. The goal is to do the signal processing of the signal that is got from MPU9250 and implement the data with a specific format so that the LINAK LA36 actuator can be controlled in such a way that it performs as desired position. For this purpose, a multi-axis acceleration and position sensor is mounted on a surfing board which then collects the acceleration and Gyro data. A MATLAB Program had been written to convert the desired position into a CAN message. Before that, the raw acceleration data and gyro must be converted and filtered into actual data. First, the acceleration data was collected from another group. A signal processing method has been implemented. This includes gravitational force filter, noise filter, integration, and complementary filter method was used in order to get the accurate actual data that is able to be implemented into the system. For those methods, it was necessary to deal extensively with the characteristics of signal processing. VR application was implemented in this project to give the user a sensational surfing experience in the virtual world. User control has been implemented as well to allow users to control the video. Unity with Arduino work together so that both Arduino and Unity can communicate with each other, and signal messages will be sent to the Arduino from Unity and vice versa to achieve the synchronization of the video signal and Unity VR application.

A Novel Adversarial Deep Learning Method for Substation Defect Image Generation.

The presence of defects in substation equipment is a major factor affecting the safety of power transmission. Therefore, timely and accurate detection of these defects is crucial. As intelligent inspection robots advance, using mainstream object detection models to diagnose surface defects in substation equipment has become a focal point of current research. However, the lack of defect image data is one of the main factors affecting the accuracy of supervised deep learning-based defect detection models. To address the issue of insufficient training data for defect images with complex backgrounds, such as rust and surface oil leakage in substation equipment, which leads to the poor performance of detection models, this paper proposes a novel adversarial deep learning model for substation defect image generation: the Abnormal Defect Detection Generative Adversarial Network (ADD-GAN). Unlike existing generative adversarial networks, this model generates defect images based on effectively segmented local areas of substation equipment images, avoiding image distortion caused by global style changes. Additionally, the model uses a joint discriminator for both overall images and defect images to address the issue of low attention to local defect areas, thereby reducing the loss of image features. This approach enhances the overall quality of generated images as well as locally generated defect images, ultimately improving image realism. Experimental results demonstrate that the YOLOV7 object detection model trained on the dataset generated using the ADD-GAN method achieves a mean average precision (mAP) of 81.5% on the test dataset, and outperforms other image data augmentation and generation methods. This confirms that the ADD-GAN method can generate a high-fidelity image dataset of substation equipment defects.

A generative benchmark for evaluating the performance of fluorescent cell image segmentation

Fluorescent cell imaging technology is fundamental in life science research, offering a rich source of image data crucial for understanding cell spatial positioning, differentiation, and decision-making mechanisms. As the volume of this data expands, precise image analysis becomes increasingly critical. Cell segmentation, a key analysis step, significantly influences quantitative analysis outcomes. However, selecting the most effective segmentation method is challenging, hindered by existing evaluation methods' inaccuracies, lack of graded evaluation, and narrow assessment scope. Addressing this, we developed a novel framework with two modules: StyleGAN2-based contour generation and Pix2PixHD-based image rendering, producing diverse, graded-density cell images. Using this dataset, we evaluated three leading cell segmentation methods: DeepCell, CellProfiler, and CellPose. Our comprehensive comparison revealed CellProfiler's superior accuracy in segmenting cytoplasm and nuclei. Our framework diversifies cell image data generation and systematically addresses evaluation challenges in cell segmentation technologies, establishing a solid foundation for advancing research and applications in cell image analysis.

Denoising diffusion probabilistic models for generation of realistic fully-annotated microscopy image datasets.

Recent advances in computer vision have led to significant progress in the generation of realistic image data, with denoising diffusion probabilistic models proving to be a particularly effective method. In this study, we demonstrate that diffusion models can effectively generate fully-annotated microscopy image data sets through an unsupervised and intuitive approach, using rough sketches of desired structures as the starting point. The proposed pipeline helps to reduce the reliance on manual annotations when training deep learning-based segmentation approaches and enables the segmentation of diverse datasets without the need for human annotations. We demonstrate that segmentation models trained with a small set of synthetic image data reach accuracy levels comparable to those of generalist models trained with a large and diverse collection of manually annotated image data, thereby offering a streamlined and specialized application of segmentation models.

A Defect Detection Method for Substation Equipment Based on Image Data Generation and Deep Learning

A Defect Detection Method for Substation Equipment Based on Image Data Generation and Deep Learning

A review on early diagnosis of glaucoma using machine learning techniques

Glaucoma refers to the accumulated loss of retinal cells within the optic nerve or the gradual visual loss caused by optic neuropathy. It is an illness that affects vision in the eye and is considered an irreversible condition that leads to degradation of eyesight. There are often no early warning signs of glaucoma, making it difficult to notice changes in vision due to subtle effects. To date, a large number of Deep Learning (DL) models have been developed for the accurate diagnosis of glaucoma. This work proposes an architecture for deep learning-based glaucoma detection using Convolutional Neural Networks (CNNs). CNNs can distinguish between patterns associated with glaucoma and non-glaucoma conditions, providing a hierarchical structure for classification. Using the proposed method, the disease is detected based on the optic cup-to-disc ratio. The diagnosis is further enhanced by integrating an image data generator for data augmentation. The results demonstrate that the proposed model achieved 98% accuracy, outperforming many existing algorithms.

Research and evaluation of the efficiency of handwritten character recognition methods using convulsional neural networks

The paper analyzes the possibilities of using deep learning neural networks for the implementation of text processing information systems, substantiates the prospects of this technology and the possibilities of its improvement. The possibility of using the MNIST database of handwritten digits on, as well as the EMNIST database of handwritten letters and numbers, namely the EMNIST Letters set, was considered. The research object was modelled in IDEF0 and IDEF3 notations for the «AS-IS» option. It was found that «Building a dataset for model training» and «Choosing a convolutional neural network architecture» are the most frequently asked questions. Reengineering measures are proposed, namely, the expediency of using, in addition to the well-known EMNIST and MNIST sets, a set of handwritten and italic fonts with Ukrainian glyphs, additionally created as part of the work, is shown. For this purpose, modern IT tools such as the Pillow library, Image Data Generator and the Scikit-Learn package were used to select training and test samples. Also, in addition to the initially proposed simplest CNN architectures of the Lenet type, the use of more complex architectures of the AlexNet and VGG-16 types is proposed. Taking into account the proposed reengineering measures, IDEF0 and IDEF3 diagrams were constructed for the «TO-BE» option. The paper analyzes in detail the results of recognizing handwritten Ukrainian letters and Arabic numerals using 6 different CNN architectures using a synthetic data set for training. The research presented in the work was carried out using a software application developed in the Python programming language using the Scikit Learn package, which provides the user with the ability to recognize handwritten text using a multilayer perceptron. carried out precisely using the developed program. It is justified that, in contrast to simple Lenet-type architectures, it is more appropriate to use more complex options, namely the VGG-16 type architecture. Experimental studies of the influence of the number of CNN parameters of different architectures on the recognition accuracy and training time of the neural network have been carried out. Also analyzed are the results of character recognition when recognizing images that do not belong to the training or test sample

Implementation of Convolutional Neural Network Method in Identifying Fashion Image

The fashion industry has changed a lot over the years, which makes it hard for people to compare different kinds of fashion. To make it easier, different styles of clothing are tried out to find the exact and precise look desired. So, we opted to employ the Convolutional Neural Network (CNN) method for fashion classification. This approach represents one of the methodologies employed to utilize computers for the purpose of recognizing and categorizing items. The goal of this research is to see how well the Convolutional Neural Network method classifies the Fashion-MNIST dataset compared to other methods, models, and classification processes used in previous research. The information in this dataset is about different types of clothes and accessories. These items are divided into 10 categories, which include ankle boots, bags, coats, dresses, pullovers, sandals, shirts, sneakers, t-shirts, and trousers. The new classification method worked better than before on the test dataset. It had an accuracy value of 95. 92%, which is higher than in previous research. This research also uses a method called image data generator to make the Fashion MNIST image better. This method helps prevent too much focus on certain details and makes the results more accurate.

Generative Artificial Intelligence and GPT using Deep Learning: A Comprehensive Vision, Applications Trends and Challenges

Generative Artificial intelligence is a prominent and recently emerging subdomain in the field of artificial intelligence. It deals with question-answering based on natural language processing. This paper discusses recent methodologies adopted by researchers in this field. It also discusses GAI and machine learning techniques for multimodal applications like image, text and audio-based data generation. This meta-analysis and survey was done from prominent research up to 2023 from the Scopus Database consisting of reputed and authenticated research papers.The research contribution is twofold 1. To analyze the recent research and applications at the industry level 2. To identify techniques and associated limitations. This would further aid practitioners to address future challenges.

Deep generative modeling-based data augmentation with demonstration using the BFBT benchmark void fraction datasets

Deep learning (DL) has achieved remarkable successes in many disciplines such as computer vision and natural language processing due to the availability of “big data”. However, such success cannot be easily replicated in many nuclear engineering problems because of the limited amount of training data, especially when the data comes from high-cost experiments. To overcome such a data scarcity issue, this paper explores the applications of deep generative models (DGMs) that have been widely used for image data generation to scientific data augmentation. DGMs, such as generative adversarial networks (GANs), normalizing flows (NFs), variational autoencoders (VAEs), and conditional VAEs (CVAEs), can be trained to learn the underlying probabilistic distribution of the training dataset. Once trained, they can be used to generate synthetic data that are similar to the training data and significantly expand the dataset size. By employing DGMs to augment TRACE simulated data of the steady-state void fractions based on the NUPEC Boiling Water Reactor Full-size Fine-mesh Bundle Test (BFBT) benchmark, this study demonstrates that VAEs, CVAEs, and GANs have comparable generative performance with similar errors in the synthetic data, with CVAEs achieving the smallest errors. The findings shows that DGMs have a great potential to augment scientific data in nuclear engineering, which proves effective for expanding the training dataset and enabling other DL models to be trained more accurately.

ANALISIS PENGARUH DIMENSI GAMBAR PADA KLASIFIKASI MOTIF BATIK DENGAN MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK

This study focuses on the classification of batik patterns using image data, specifically with three classes: kawung, parang, and pekalongan batik patterns. A total of 180 images were used for the research, divided equally among the three motifs. The dataset was collected through observations from Google. Data preprocessing involved two stages. In the first stage, the data was split into training and validation sets, with a 70% - 30% ratio, respectively. This separation allowed for evaluating the model's performance and generalization ability on unseen data. In the second stage, the Image Data Generator library was utilized to enhance data diversity and improve the model's ability to generalize patterns. Data augmentation techniques, such as rotation, shear, zoom, horizontal flip, and shift, were applied to the training data. The augmented data was then fed into a pre-defined Convolutional Neural Network (CNN) architecture. The CNN model processed the input data through convolutional layers with max pooling and ReLU activation functions. The outputs from the first convolutional layer were used as inputs for subsequent convolutional layers. The resulting feature maps were flattened and passed through fully connected layers for classification. The model's performance was assessed by evaluating accuracy measures. The CNN model achieved the highest accuracy of 98% on the training data and 100% on the validation data after 7 epochs.. The implementation was done using Python programming language and the Google Colab platform, along with required libraries. Model evaluation involved assessing the trained model's performance by inputting test data and computing evaluation metrics, including accuracy, precision, recall, and F1-score. Confusion matrix analysis provided insights into true positive, true negative, false positive, and false negative predictions. The classification report summarized the performance metrics of the model. In conclusion, the CNN method proved effective in classifying batik patterns. The size of the input images significantly influenced the accuracy of the model. A 148x148 pixel image size yielded 100% accuracy. As a suggestion, future research should consider using a larger dataset to maximize the accuracy of the classification model.

Synthetic image data generation using BIM and computer graphics for building scene understanding

Vision-based building scene understanding (BSU) is essential to many applications such as indoor navigation and 3D reconstruction. Deep learning excels in various BSU tasks but its training relies heavily on large-scale datasets, which are often burdensome and costly to obtain. This study proposes a universal and automated approach to generate synthetic building images with comprehensive annotations that support twelve BSU tasks, including camera pose estimation, scene recognition, depth estimation, 2D/3D object and object part detection, object and material semantic segmentation, object and object part instance segmentation, and panoptic segmentation. This approach captures and renders perspective views of indoor BIM model scenes to generate photorealistic images. Required annotations are computed by a ray tracing-based algorithm accelerated by two-tier axis-aligned bounding box tree indexing. The approach was validated by efficiently producing annotated synthetic images from various BIM models, and preliminary experiments demonstrated the promising efficacy of the synthetic images for deep learning model training.

SYNTHETIC DATA GENERATION AND TESTING FOR THE SEMANTIC SEGMENTATION OF HERITAGE BUILDINGS

Abstract. Over the past decade, the use of machine learning and deep learning algorithms to support 3D semantic segmentation of point clouds has significantly increased, and their impressive results has led to the application of such algorithms for the semantic modeling of heritage buildings. Nevertheless, such applications still face several significant challenges, caused in particular by the high number of training data required during training, by the lack of specific data in the heritage building scenarios, and by the time-consuming operations to data collection and annotation. This paper aims to address these challenges by proposing a workflow for synthetic image data generation in heritage building scenarios. Specifically, the procedure allows for the generation of multiple rendered images from various viewpoints based on a 3D model of a building. Additionally, it enables the generation of per-pixel segmentation maps associated with these images. In the first part, the procedure is tested by generating a synthetic simulation of a real-world scenario using the case study of Spedale del Ceppo. In the second part, several experiments are conducted to assess the impact of synthetic data during training. Specifically, three neural network architectures are trained using the generated synthetic images, and their performance in predicting the corresponding real scenarios is evaluated.

Transfer Learning based Image Classification of Diseased Tomato Leaves with Optimal Fine-Tuning combined with Heat Map Visualization

India is one of the leading countries in Tomato cultivation and production. Coimbatore, Dharmapuri, Salem,Krishnagiri are some of the foremost districts in tomato production. According to a survey, Tomato Leaf Curl virus is one of the most ravage class of disease and the maximum incidence of the disease is reported as 95.3% in Dharmapuri district of Tamil Nadu. The objective of the work is to identify the most recurrent tomato plant diseases using deep learning-based image classification techniques and to develop a plant disease classification web application. In this paper, Tomato based leaf disease images alone is used from Plant Village Dataset downloaded from Kaggle platform. Inception V3, a pre-trained transfer learning model is used to classify this multi-class tomato plant disease by using the leaf symptoms such as dark brown lesions, concentric rings etc. Data augmentation is performed while training the model on the images using Keras Image Data Generator on various layers and feature extraction is performed. The training accuracy and validation accuracy of the model before and after fine-tuning is 80.21%,76.29% and 81.72%,77.63% respectively. The highest precision, recall and F1 score is 95, 93 and 94 respectively is recorded for Tomato Yellow Leaf Curl Virus Disease for which the yield losses is severe. Further, activations are used to generate an attention map in the form of Heat Maps which is included as a post processing step before the classification of the output. Plant Leaf Disease Classification- A web application is deployed using Streamlit Python library and Ngrok services

Deep convolutional generative adversarial networks for traffic data imputation encoding time series as images

Sufficient high-quality traffic data are a crucial component of various Intelligent Transportation System (ITS) applications and research related to congestion prediction, speed prediction, incident detection, and other traffic operation tasks. Nonetheless, missing traffic data are a common issue in sensor data which is inevitable due to several reasons, such as malfunctioning, poor maintenance or calibration, and intermittent communications. Such missing data issues often make data analysis and decision-making complicated and challenging. In this study, we have developed a generative adversarial network (GAN) based traffic sensor data imputation framework (TSDIGAN) to efficiently reconstruct the missing data by generating realistic synthetic data. In recent years, GANs have shown impressive success in image data generation. However, generating traffic data by taking advantage of GAN based modeling is a challenging task, since traffic data have strong time dependency. To address this problem, we propose a novel time-dependent encoding method called the Gramian Angular Summation Field (GASF) that converts the problem of traffic time-series data generation into that of image generation. We have evaluated and tested our proposed model using the benchmark dataset provided by Caltrans Performance Management Systems (PeMS). This study shows that the proposed model can significantly improve the traffic data imputation accuracy in terms of Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) compared to state-of-the-art models on the benchmark dataset. Further, the model achieves reasonably high accuracy in imputation tasks even under a very high missing data rate (>50%), which shows the robustness and efficiency of the proposed model.

Herbal Leaves Classification Based on Leaf Image Using CNN Architecture Model VGG16

Herbal leaves are a type that is often used by people in the health sector. The problem faced is the lack of knowledge about the types of herbal leaves and the difficulty of distinguishing the types of herbal leaves for ordinary people who do not understand plants. If any type of plant is used, it will have a negative impact on health. Automatic classification with the help of technology will reduce the risk of misidentification of herbal leaf types. To make identification, a precise and accurate herbal leaf detection process is needed. This research aims to facilitate the classification model of herbal leaf images with a higher accuracy value than previous research. Therefore, the proposed method in this classification process is one of the Transfer Learning methods, namely Convolutional Neural Network (CNN) with a pretrained VGG16 model. This research uses a dataset of herbal leaves with a total of 10 classes: Belimbing Wuluh, Jambu Biji, Jeruk Nipis, Kemangi, Lidah Buaya, Nangka, Pandan, Pepaya, Seledri and Sirih. The performance of the results of the proposed classification method on the test dataset using Classification Report shows an increase in the results of the previous research accuracy value from 82% to 97%. This research also applies Image Data Generator in the augmentation process which aims to improve the image of herbal leaves, reduce overfitting, and improve accuracy.

Deep Learning-Enabled Brain Stroke Classification on Computed Tomography營mages

In the field of stroke imaging, deep learning (DL) has enormous untapped potential. When clinically significant symptoms of a cerebral stroke are detected, it is crucial to make an urgent diagnosis using available imaging techniques such as computed tomography (CT) scans. The purpose of this work is to classify brain CT images as normal, surviving ischemia or cerebral hemorrhage based on the convolutional neural network (CNN) model. In this study, we propose a computer-aided diagnostic system (CAD) for categorizing cerebral strokes using computed tomography images. Horizontal flip data magnification techniques were used to obtain more accurate categorization. Image Data Generator to magnify the image in real time and apply any random transformations to each training image. An early stopping method to avoid overtraining. As a result, the proposed methods improved several estimation parameters such as accuracy and recall, compared to other machine learning methods. A python web application was created to demonstrate the results of CNN model classification using cloud development techniques. In our case, the model correctly identified the drawing class as normal with 79% accuracy. Based on the collected results, it was determined that the presented automated diagnostic system could be used to assist medical professionals in detecting and classifying brain strokes.

Anomaly Detection in Solar Modules with Infrared Imagery

Image classification is a machine learning task that involves assigning a label or class to an input image. In the context of the Infrared Solar Modules dataset, image classification can be used to identify anomalies in solar panel imagery. To achieve this goal, A convolutional neural network (CNN) model trained from scratch and fine-tuned on the Infrared Solar Modules dataset from ai4earthscience. Model includes techniques such as dropout and image data generation to enhance its accuracy on this specific dataset. With these methods, Model can achieve high accuracy in identifying solar panel anomalies even with low-size images.