Sökning: "SSIM"

Visar resultat 26 - 30 av 57 uppsatser innehållade ordet SSIM.

  1. 26. JPEG-deblocking of Blood Cell Images using Deep Learning

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Justin Ma; Julia Hafsbrandt Fovaeus; [2020]
    Nyckelord :Image Analysis; Image Reconstruction; Image Restoration; Image Compression; Machine Learning; Deep Learning; JPEG; JPEG-deblocking; CellaVision; Neural Networks; Convolutional Neural Networks; Blood Cells; White Blood Cells; Microscopy; Microscope; Mathematics and Statistics;

    Sammanfattning : This thesis investigates the use of convolutional neural networks as a reconstruction or JPEG- deblocking model for JPEG-compressed blood cell images, needed due to the well known block artifacts caused by JPEG-compression. CellaVision develops automated microscopy for blood analysis that detects and classifies blood cells from images. LÄS MER

  3. 27. Analysering av Variable Rate Shading's bildbaserad skuggning i uppskjuten sammansättning av ljussättning : En jämförelse mellan bildbaserad skuggning och enhetlig skuggning för spel

    Uppsats för yrkesexamina på avancerad nivå, Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Författare :Filip Lundbeck; [2020]
    Nyckelord :Rendering; Adaptive Shading; Uniform Shading; Variable Rate Shading; Dynamic Resolution Rendering; Rendering; Adaptiv ljussättning; enhetlig ljussättning; Variable Rate Shading; Dynamic Resolution Rendering;

    Sammanfattning : Bakgrund. Kostnaden att ljussätta en pixel blir dyrare med realistiska spel. Upplösningen av spel är ökas i samma tak för att visa upp detaljerna. Att rendera en blidruta för användare blir därför allt dyrare. LÄS MER

  4. 28. Developing an emulator for 360° video : intended for algorithm development

    Master-uppsats, Linköpings universitet/Databas och informationsteknik

    Författare :Eric Lindskog; [2020]
    Nyckelord :VR; emulation; simulation; tools; 360°; video; streaming; DASH; HAS; QoE; MS-SSIM; SSIM; virtual; reality; fetching; VoD; bandwidth; MOS;

    Sammanfattning : Streaming 360° video has become more commonplace with content delivery services such as YouTube having support for it. By its nature, 360° video requires more bandwidth as only a fraction of the image is actually in view, while the user is expecting the same "in view" quality as with a regular video. LÄS MER

  5. 29. A Novel Perceptual Metric in Deep Learning

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Johanna Engman; Hanna Nilsson; [2020]
    Nyckelord :Loss function; Metric; Deep learning; Denoising; MRI reconstruction; U-net; Machine learning; Image Analysis; Mathematics and Statistics;

    Sammanfattning : Loss functions are a crucial part of image processing when using modern neural networks, trained with stochastic gradient descent. There exist multiple loss functions today, some claiming to be perceptual. Researchers at NVIDIA recently published a proposal of such a metric called FLIP. LÄS MER

  7. 30. Depth of Field Rendering from Sparsely Sampled Pinhole Images

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

    Författare :Natalie Axelsson; [2020]
    Nyckelord :;

    Sammanfattning : Optical lenses cause foreground and background objects to appear blurred, causing an effect called depth of field. Each point in the scene is projected onto the imaging plane as a semitransparent circle of confusion (CoC) with diameter depending on the distance between the point and the lens. LÄS MER