Sökning: "bildsegmentering"
Visar resultat 11 - 15 av 34 uppsatser innehållade ordet bildsegmentering.
11. Screw Hole Detection in Industrial Products using Neural Network based Object Detection and Image Segmentation : A Study Providing Ideas for Future Industrial Applications
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : This project is about screw hole detection using neural networks for automated assembly and disassembly. In a lot of industrial companies, such as Ericsson AB, there are products such as radio units or filters that have a lot of screw holes. LÄS MER
12. Road Damage Segmentation for Mobile Hardware
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The detection and early repair of road damage are paramount for the quality and safety of roads. Current detection efforts typically rely on Deep Learning methods for object detection with bounding boxes, with calculations performed on high-performance hardware. LÄS MER
13. Localization of fractures in drill cores using Deep Learning
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Investigating and assessing rock structures requires extensive manual work, where geologists measure the fractures in drill cores to get a better understanding of the condition of the underlying rock. This study investigates the possibility to use Deep Learning for localizing fractures in images of drill cores, automating and facilitating the work of geologists. LÄS MER
14. Data Augmentation to Improve Cross-Domain Generalization in Deep Learning MRI Segmentation
Master-uppsats, Lunds universitet/Matematik LTHSammanfattning : Semantic segmentation of medical images is an important task with many applications. However, manually delineating 3D images is time-consuming and the demand for automation is high. For many image segmentation tasks, deep learning has provided state-of-the-art results. LÄS MER
15. Road Segmentation and Optimal Route Prediction using Deep Neural Networks and Graphs
Master-uppsats, KTH/Matematik (Avd.)Sammanfattning : Observing the earth from above is a great way of understanding our world better. From space, many complex patterns and relationships on the ground can be identified through high-quality satellite data. LÄS MER