Advanced search

Showing result 1 - 5 of 107 swedish dissertations matching the above criteria.

  2. 1. Synthetic data for visual machine learning : A data-centric approach

    Author : Apostolia Tsirikoglou; Jonas Unger; Gabriel Eilertsen; Anders Ynnerman; Philipp Slusallek; Linköpings universitet; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Training data; Synthetic images; Computer graphics; Generative modeling; Natural images; Histopathology; Digital pathology; Machine learning; Deep learning;

    Abstract : Deep learning allows computers to learn from observations, or else training data. Successful application development requires skills in neural network design, adequate computational resources, and a training data distribution that covers the application do-main. READ MORE

  4. 2. The synthetic chromosphere : Results and techniques with a numerical approach

    Author : Johan Pires Bjørgen; Jorrit Leenaarts; Oskar Steiner; Stockholms universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Sun; chromosphere; radiative transfer; numerical method; Astronomy; astronomi;

    Abstract : Realistic numerical simulations of the solar atmosphere can be used to interpret different phenomena observed on the solar surface. To gain insight into the atmospheric physical conditions, we compare the observations with 3D radiative magnetohydrodynamic models combined with forward modeling (radiative transfer). READ MORE

  5. 3. Statistical methods in medical image estimation and sparse signal recovery

    Author : Fekadu Lemessa Bayisa; Jun Yu; Ottmar Cronie; Henning Omre; Umeå universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; Computed tomography; magnetic resonance imaging; Gaussian mixture model; skew-Gaussian mixture model; hidden Markov random field; hidden Markov model; supervised statistical learning; synthetic CT images; pseudo-CT images; spike and slab prior; adaptive algorithm;

    Abstract : This thesis presents work on methods for the estimation of computed tomography (CT) images from magnetic resonance (MR) images for a number of diagnostic and therapeutic workflows. The study also demonstrates sparse signal recovery method, which is an intermediate method for magnetic resonance image reconstruction. READ MORE

  6. 4. Image Analysis in Support of Computer-Assisted Cervical Cancer Screening

    Author : Patrik Malm; Ewert Bengtsson; Calum MacAulay; Uppsala universitet; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Image analysis; cervical cancer; pap-smear; synthetic images; screening; image processing; cytometry; Computerized Image Processing; Datoriserad bildbehandling;

    Abstract : Cervical cancer is a disease that annually claims the lives of over a quarter of a million women. A substantial number of these deaths could be prevented if population wide cancer screening, based on the Papanicolaou test, were globally available. The Papanicolaou test involves a visual review of cellular material obtained from the uterine cervix. READ MORE

  7. 5. Model Based Reconstruction of Ultrasonic Images

    Author : Erik Wennerström; Uppsala universitet; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Signal processing; Signalbehandling;

    Abstract : This thesis is concerned with reconstruction methods for ultrasonic imaging, primarily applied to non-destructive material inspection. In ultrasonic inspection, a specimen is insonified with pulses of high frequency ultrasound, which enters the material and propagates through it. READ MORE