Browsing by Author "Dahyot, Rozenn"

Now showing items 1-11 of 11

    • 3D object reconstruction using multiple views 

      Kim, Donghoon (Trinity College (Dublin, Ireland). School of Computer Science & Statistics, 2011)
      3D object modelling from multiple view images has recently been of increasing interest in computer vision. Two techniques, Visual Hull and Photo Hull, have been extensively studied in the hope of developing 3D shape ...

    • Automatic Discovery and Geotagging of Objects from Street View Imagery 

      Kenny, Eamonn; Krylov, Vladimir; Dahyot, Rozenn (2018)
      Many applications, such as autonomous navigation, urban planning, and asset monitoring, rely on the availability of accurate information about objects and their geolocations. In this paper, we propose the automatic detection ...

    • Colour transfer and shape registration using functional data representations 

      Grogan, Mairéad (Trinity College (Dublin, Ireland). School of Computer Science & Statistics, 2017)
      In this thesis we propose new colour transfer and shape registration methods based on the robust L2 distance. For colour transfer, we present an approach inspired by techniques recently proposed in shape registration. We ...

    • Convolutional Neural Networks based on Discrete Cosine Transform with Applications in Computer Vision 

      Ulicny, Matej (Trinity College Dublin. School of Computer Science & Statistics. Discipline of Computer Science, 2021)
      Convolutional neural networks (CNNs) have become a paradigm for designing vision based intelligent systems. These models are controlled by a vast amount of parameters, which are learned thanks to the availability of annotated ...

    • Image Restoration Using Deep Learning 

      ALBLUWI, FATMA HAMED (Trinity College Dublin. School of Computer Science & Statistics. Discipline of Statistics, 2020)
      In this thesis, we propose several convolutional neural network (CNN) architectures with fewer parameters compared to state-of-the-art deep structures to restore original images from degraded versions. Employing fewer ...

    • IRISH MACHINE VISION & IMAGE PROCESSING Conference proceedings 2015 

      Dahyot, Rozenn; Lacey, Gerard; Dawson-Howe, Kenneth; Pitie, Francois (Irish Pattern Recognition & Classification Society (ISBN 978-0-9934207-0-2), 2015)

    • Irish Machine Vision and Image Processing Conference Proceedings 2018 

      Dahyot, Rozenn (Irish Pattern Recognition and Classification Society, 2018)
      With IMVIP 2018 the series of Irish Machine Vision and Image Processing conferences reaches a landmark occasion: IMVIP 2018 is the 20th edition in a series of which the inaugural meeting was held at the Magee campus of ...

    • L_ Inference for shape parameter estimation 

      Arellano Vidal, Claudia L. (Trinity College (Dublin, Ireland). School of Computer Science & Statistics, 2014)
      In this thesis, we propose a method to robustly estimate the parameters that controls the mapping of a shape (model shape) onto another (target shape). The shapes of interest are contours in the 2D space, surfaces in the ...

    • Probability Density Function Transfer in High Dimensional Spaces and its Application to Colour Transfer 

      Alghamdi, Hana (Trinity College Dublin. School of Computer Science & Statistics. Discipline of Computer Science, 2021)
      This thesis addresses the topic of example-based colour transfer from the domain of image processing. Colour transfer is often recast as a distribution transfer problem in which the actual probability density function of ...

    • Semantic image segmentation based on spatial relationships and inexact graph matching 

      Dahyot, Rozenn (2020)
      We propose a method for semantic image segmentation, combining a deep neural network and spatial relationships between image regions, encoded in a graph representation of the scene. Our proposal is based on inexact graph ...

    • Visual attention using 2D & 3D displays 

      Zdziarski, Zbigniew (Trinity College (Dublin, Ireland). School of Computer Science & Statistics, 2015)
      In the past three decades, robotists and computer vision scientists, inspired by psychological and neurophysiological studies, have developed many computational models of attentions (CMAs) that mimic the behaviour of the ...