Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 146 for “"UNET"”.
-
DEBLURRING OF OPTICALLY ABERRATED SATELLITE IMAGERY WITH DEEP LEARNING (UNET)
… applying deep learning algorithms based on the UNET Convolutional Neural Network, which is widely used in the bio-medical imaging field, to deblur optically aberrated satellite imagery. The XVIEW dataset, which is composed of images taken by the Worldview-3 satellite, is used. The XVIEW images …
-
A UNet MobileNetV2 palpebral fissure segmentation model in the context of blink analysis
… models. This work investigates the use of a UNet with a pretrained MobileNetV2 encoder to measure the palpebral fissure in pixels in situations where the eyes cover a small region of the images, such as images from a computer webcam. The semantic segmentation of the palpebral fissure is the …
-
Comparing UNet and HRNet for Geomorphic Feature Extraction from Digital Terrain Model-Derived Land Surface Parameters
… two convolutional neural network architectures, UNet and High-Resolution Network (HRNet), for semantic segmentation of mine benches and sinkholes from lidar-derived digital terrain models and land surface parameters. Mine benches represent anthropogenic, elongated, stepped landforms associated …
-
An Advanced Machine Learning Framework and Multi-Label Heart Disease Classification with UNet-Based Nucleus Segmentation
… in microscopy images, the study introduces mA-UNet—an advanced model engineered to detect fine-grained foreground elements in imbalanced datasets. This model outperforms existing approaches, attaining a mean Intersection over Union score of 95.50%, and exhibits hardware efficiency when deployed …
-
Mapeamento de milho de segunda safra em mato Grosso com mosaicos LANDSAT 8-9 : comparação entre Random Forest e UNET
Produtos de mapeamento agrícola por sensoriamento remoto voltados ao milho de segunda safra ainda são limitados no Brasil, onde grande parte das bases disponíveis representa a agricultura de forma mais geral ou por recortes anuais. No estado do Mato Grosso, principal área produtora dessa cultura no …
-
Medical Image Segmentation For Embryo Image Analysis
… techniques. In this work, we implemented a UNet variant model named Residual Dilated UNet (RD-UNet) to segment ICM and TE in ZP-intact embryonic images. We added residual convolution to the encoding and decoding units and replaced conventional convolutional layer with multiple dilated …
-
Metody segmentace obrazu s malými trénovacími množinami
… množstvom trénovacích dát. Navrhnutá sieť ODE-UNet vznikla kombináciou architektúry UNet a siete ODE, pričom využíva výhod oboch sietí. Na ISBI dátovej sade bolo dosiahnutých presností Rand: 0,950272 a Info: 0,978061 na testovacích snímkoch, čím bola prekonaná presnosť siete UNet, ktorá bola …
-
Statistical Analysis and Deep Learning Techniques for Enhancing Low Quality Magnetic Resonance Imaging
… of deep learning (DL) methods, such as UNet convolutional networks and generative adversarial networks (GANs), to enhance the quality of low-resolution and low SNR MRI images. This dissertation focuses on the statistical analysis of different UNet variants and their performance to …
-
CLASSIFICATION OF THORAX DISEASES FROM CHEST X-RAY IMAGES
… input data for this project. This approach uses UNet architecture as its classification layer. UNet architecture is well-known for its efficiency in image segmentation. Adding residual blocks enhances this approach's ability to classify images. The goal of this project is to create a robust and …
-
Mikroplastiko dalelių segmentacija mikroskopiniuose vaizduose /
… several deep learning segmentation approaches, a UNet based convolutional network was developed and trained on an FTMC image set. Data augmentation and hyperparameter tuning enabled the model to identify most particles accurately. Although background artefacts and limited training data still …
-
Revealing The Three-Dimensional Magnetic Texture with Machine Learning Models
… a simple convolutional neural network (CNN) or Unet architecture, is built and used to reconstruct the 3D magnetic texture. We demonstrate that the magnetic vector potential and magnetic induction field can be successfully reconstructed with an end-to-end Unet-based ML model. Also, …
-
Estimation of Lidar Point Clouds Based on Ultrasonic Sensors Using Deep Learning
… in five different models: DAE(bin), DAE(mse), UNET(bin), UNET(ce) and an I2I cGAN. We train these models on three datasets, each containing paired ultrasonic and Lidar representations of a two-dimensional environment around the car. In order to measure the performance of these models, we …
-
Physics-Informed Deep Learning for Quasi-Static Elasticity Imaging: Mechanical Characterization of Heterogeneous Domains in Two and Three Dimensions
… introduces a new neural network backbone, El-UNet, based on encoder-decoder convolutional neural networks with skip connections (UNet). El-UNet outperformed fully-connected physics-informed neural networks in accurately estimating two-dimensional (2D) unknown parameters and stress …
-
An Investigation of Advanced Deep Learning-Based Automated Models for Tumor Segmentation in Whole-body PET/CT Images
… Anything Model (SAM) (Hybrid), and (c) Swin-Unet (U-Net-like pure transformer) in a publicly available dataset of PET/CT images including normal patients and patients with lung cancer, lymphoma, and melanoma. Our study includes a holistic performance analysis for three cancer types and normal …
-
Deep Learning Climate Model Emulation with PEAR - Adapting a Transformer-Based Weather Forecasting Model onthe HEALPix Grid to the Climate Domain
… Earth system models, and benchmarked against UNet and ClimaX baselines from the ClimateSet benchmarks. Across 15 climate models and 5 random seeds, PEAR achieves competitive performance despite its small size, with 4.3M trainable parameters compared with 18.3M for UNet and 106.6M for ClimaX. …
-
A Unified Deep Learning Framework For Simultaneous Segmentation And Multiclass Classification Of Chronic Wounds *
… For segmentation, we proposed Attention-Dense-UNet (Att-d-UNet), and for classification, we introduced a feature concatenation-based method. Our framework segments wound images using Att-d-UNet, followed by classification into one of the wound types using our proposed method. We evaluated our …
-
Neuroninių tinklų taikymas mikroskopinių vaizdų segmentavimui /
… To achieve this goal, a program using the UNet model was developed, which was trained with a dataset of microscopic images of microplastics collected by the physical and technology science center (FTMC), data augmentation was performed, and hyperparameters were optimized. The study results …
-
Potlačení šumu ve videu pomocí hlubokých neuronových sítí
… šumu ve videu, který je založen na architektuře UNet inspirované těmito referenčními modely. V průběhu práce jsou vysvětleny, implementovány a vyhodnoceny navrhované modely UNet Baseline, ResUNet a ResUNet Temporal, aby byla prokázána jejich účinnost v odstraňování šumu ve videu.
-
Detekce a lokalizace mikrobiálních kolonií pomocí algoritmů hlubokého učení
… neuronových sítí na bázi architektur UNet, UNet++ a ENet. Na základě množství experimentů zkoumajících různé konfigurace sítí a předzpracování trénovacího datasetu byl pro použití v produkčním prostředí vybrán model ENet s čtyřnásobným množstvím filtrů a přidaným konvolučním blokem …
-
Deep Learning-Based Microscopy
… microscopy modalities. To do so, we present UNet-RCAN, a two-step deep learning network architecture based on a residual U-Net and residual channel attention network (RCAN) for image restoration. We demonstrate that UNet-RCAN achieves higher prediction accuracy compared to other …
Page 1 of 8