Sökning: "image vision"

Visar resultat 1 - 5 av 430 avhandlingar innehållade orden image vision.

1. 1. Representation Learning and Information Fusion : Applications in Biomedical Image Processing

   Författare :Elisabeth Wetzer; Nataša Sladoje; Fred Hamprecht; Uppsala universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Representation Learning; Texture Descriptors; Equivariant Neural Networks; Contrastive Learning; Image Classification; Image Registration; Image Retrieval; Digital Pathology; Computerized Image Processing; Datoriserad bildbehandling;

   Sammanfattning : In recent years Machine Learning and in particular Deep Learning have excelled in object recognition and classification tasks in computer vision. As these methods extract features from the data itself by learning features that are relevant for a particular task, a key aspect of this remarkable success is the amount of data on which these methods train. LÄS MER

3. 2. Methods for Reliable Image Registration : Algorithms, Distance Measures, and Representations

   Författare :Johan Öfverstedt; Natasa Sladoje; Mattias Heinrich; Uppsala universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Image registration; alignment; local optimization; global optimization; mutual information; normalized gradient fields; representation learning; Computerized Image Processing; Datoriserad bildbehandling;

   Sammanfattning : Much biomedical and medical research relies on the collection of ever-larger amounts of image data (both 2D images and 3D volumes, as well as time-series) and increasingly from multiple sources. Image registration, the process of finding correspondences between images based on the affinity of features of interest, is often required as a vital step towards the final analysis, which may consist of a comparison of images, measurement of movement, or fusion of complementary information. LÄS MER

4. 3. Adapting Deep Learning for Microscopy: Interaction, Application, and Validation

   Författare :Ankit Gupta; Carolina Wählby; Ida-Maria Sintorn; Ola Spjuth; Andreas Hellander; Philip Kollmannsberger; Uppsala universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Deep Learning; Microscopy; Human-in-the-Loop; Semi-Supervised Learning; Application-Specific Analysis; Image Classification; Image-to-Image Translation; Template Matching; Computerized Image Processing; Datoriserad bildbehandling;

   Sammanfattning : Microscopy is an integral technique in biology to study the fundamental components of life visually. Digital microscopy and automation have enabled biologists to conduct faster and larger-scale experiments with a sharp increase in the data generated. LÄS MER

5. 4. Galna kameror och barns virtuella bildseende, bildtänkande och filmgörande i förskolan

   Författare :Maria Olsson; Anne-Li Lindgren; Anna Palmer; Simon Ceder; Stockholms universitet; []
   Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; children; preschool; children’s filmmaking; image vision; digital videography; Deleuze’s film philosophy; transcendental empiricism; the crystal-image; barn; förskola; barns filmgörande; bildseende; digital videografi; Deleuzes filmfilosofi; transcendental empirism; kristallbild; Early Childhood Education; förskoledidaktik;

   Sammanfattning : The aim of this thesis is to contribute knowledge about children’s image-vision, image-thinking and image- and filmmaking in preschool, through a collaboration with children and digital film technology, and about Gilles Deleuze’s film philosophy (1989) as well as digital videography and the methodology created in the research process. The empirical production was carried out as a digital decentralized videography, according to Pink et al. LÄS MER

7. 5. Graph-based Methods for Interactive Image Segmentation

   Författare :Filip Malmberg; Ingela Nyström; Ewert Bengtsson; Jayaram K. Udupa; Uppsala universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Digital image analysis; Interactive image segmentation; Fuzzy image segmentation; Image foresting transform; Graph labeling; Graph cuts; Computerized Image Processing; Datoriserad bildbehandling;

   Sammanfattning : The subject of digital image analysis deals with extracting relevant information from image data, stored in digital form in a computer. A fundamental problem in image analysis is image segmentation, i.e., the identification and separation of relevant objects and structures in an image. LÄS MER