Sökning: "Image generation"

Visar resultat 1 - 5 av 304 uppsatser innehållade orden Image generation.

  1. 1. Robustness Analysis of Perfusion Parameter Calculations

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Alicia Palmér; [2024]
    Nyckelord :Perfusion; Medical image analysis; Dynamic Contrast Enhanced Magnetic Resonance Imaging; Tofts model; Functional imaging; Optimization; T1 map; Perfusion; Medicinsk bildanalys; Dynamisk kontrastförstärkt magnetisk resonanstomografibildtagning; Tofts-modell; Funktionell bildbehandling; Optimering; T1 karta;

    Sammanfattning : Cancer is one of the most common causes of death worldwide. When given optimal treatment, however, the risk of severe illness may greatly be reduced. Determining optimal treatment in turn requires evaluation of disease progression and response to potential, previous treatment. LÄS MER

  3. 2. Visualization and analysis of object states using diffusion models and PyTorch

    Kandidat-uppsats, Mälardalens universitet/Akademin för innovation, design och teknik

    Författare :Christopher Nyberg; [2024]
    Nyckelord :;

    Sammanfattning : Artificial Intelligence (AI) is an extremely rapidly growing field in modern technology. As the applications of AI expand, the ability to accurately analyze and predict the condition of various objects through various models has profound implications across numerous industries. LÄS MER

  4. 3. Designers Krav på Midjourney : En Studie om Integrationen av Bildgenererande AI i Grafiska Formgivares Arbetsprocess

    Kandidat-uppsats, Uppsala universitet/Informationssystem

    Författare :Lukas Bruhn; Max Algelin; [2024]
    Nyckelord :Generative Artificial Intelligence; Graphic Design; Midjourney; Requirement Design; Idea Generation; Generativ Artificiell Intelligens; Grafisk Formgivning; Midjourney; Kravutformning; Idégenerering;

    Sammanfattning : Text-to-image generation is one of the most significant technological advancements in artificial intelligence (AI) during recent years, with the software Midjourney being amongst the most popular tools for this purpose. There is however some uncertainty about how tools like Midjourney will impact and integrate with creative professions, such as graphic design. LÄS MER

  5. 4. AI-based image generation: The impact of fine-tuning on fake image detection

    Kandidat-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskap

    Författare :Nick Hagström; Anders Rydberg; [2024]
    Nyckelord :Fake image detection; LoRA; DreamBooth; Stable Diffusion; Image generation;

    Sammanfattning : Machine learning-based image generation models such as Stable Diffusion are now capable of generating synthetic images that are difficult to distinguish from real images, which gives rise to a number of legal and ethical concerns. As a potential measure of mitigation, it is possible to train neural networks to detect the digital artifacts present in the images synthesized by many generative models. LÄS MER

  7. 5. Image Quality Assessment Pipeline and Semi-Automated Annotation method for Synthetic Data

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Liam Le Tran; Edina Dedovic; [2023-10-24]
    Nyckelord :Facial Expression Recognition; FACS; Action Units; styleGAN2-ada; synthetic data; Image Quality Assessment; Multi-stage Pre-training; Pipeline Processing; Semi-automated Human Annotation;

    Sammanfattning : Predicting human emotions through facial expression, particularly in relation to medication field such as clinical trial settings, has garnered scientific interest in recent years due to significant understanding of the impact of treatment on emotions and social functioning. This thesis aims to improve performance of a FER model using large scale of synthetic data. LÄS MER