Sökning: "Image segmentation"
Visar resultat 11 - 15 av 431 uppsatser innehållade orden Image segmentation.
11. Automatisk detektering av kretskorts position inom in-circuit testning
Uppsats för yrkesexamina på grundnivå, Högskolan i Gävle/DatavetenskapSammanfattning : Detta arbete har försökt att skapa ett program som kan användas för att hitta position och vinklar av kretskort för ett automatiserat Bed-of-Nails test. Programmet har haft som krav att kunna räkna ut vilken position i en bricka kretskort ligger i, vilken vinkel kretskortet ligger i gentemot brickan samt hur många kretskort som finns i brickan. LÄS MER
12. Improved U-Net architecture for Crack Detection in Sand Moulds
Kandidat-uppsats, Högskolan i Gävle/DatavetenskapSammanfattning : The detection of cracks in sand moulds has long been a challenge for both safety and maintenance purposes. Traditional image processing techniques have been employed to identify and quantify these defects but have often proven to be inefficient, labour-intensive, and time-consuming. LÄS MER
13. Development of a Complete Minuscule Microscope: Embedding Data Pipeline and Machine Learning Segmentation
Master-uppsats, KTH/Tillämpad fysikSammanfattning : Cell culture is a fundamental procedure in many laboratories and precedes much research performed under the microscope. Despite the significance of this procedural stage, the monitoring of cells throughout growth is impossible due to the absence of equipment and methodological approaches. LÄS MER
14. Developing a Neural Network Model for Semantic Segmentation
M1-uppsats, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)Sammanfattning : This study details the development of a neural network model designed for real-time semantic segmentation, specifically to distinguish sky pixels from other elements within an image. The model is incorporated into a feature for an Augmented Reality application in Unity, leveraging Unity Barracuda—a versatile neural network inference library. LÄS MER
15. Self-learning for 3D segmentation of medical images from single and few-slice annotation
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Training deep-learning networks to segment a particular region of interest (ROI) in 3D medical acquisitions (also called volumes) usually requires annotating a lot of data upstream because of the predominant fully supervised nature of the existing stateof-the-art models. To alleviate this annotation burden for medical experts and the associated cost, leveraging self-learning models, whose strength lies in their ability to be trained with unlabeled data, is a natural and straightforward approach. LÄS MER