Now showing items 1-4 of 4

    • Efficient Sequential Correspondence Selection by Cosegmentation 

      Author: Čech, Jan; Matas, Jiří; Perd’och, Michal
      (IEEE, 2010-09)
      In many retrieval, object recognition, and wide-baseline stereo methods, correspondences of interest points (distinguished regions) are commonly established by matching compact descriptors such as SIFTs. We show that a ...
    • Image Matching and Retrieval by Repetitive Patterns 

      Author: Doubek, Petr; Matas, Jiří; Perd’och, Michal; Chum, Ondřej
      (IEEE, 2010-08)
      Detection of repetitive patterns in images has been studied for a long time in computer vision. This paper discusses a method for representing a lattice or line pattern by shift-invariant descriptor of the repeating element. ...
    • Large-Scale Discovery of Spatially Related Images 

      Author: Chum, Ondřej; Matas, Jiří
      (IEEE, 2010-02)
      We propose a randomized data mining method that finds clusters of spatially overlapping images. The core of the method relies on the min-Hash algorithm for fast detection of pairs of images with spatial overlap, the so-called ...
    • Výběr reprezentativních obrazových prototypů 

      Author: Pavel Gramovich; Supervisor: Matas Jiří; Opponent: Šroubek Filip
      (České vysoké učení technické v Praze. Vypočetní a informační centrum.Czech Technical University in Prague. Computing and Information Centre., 2020-09-02)
      The diversity of image retrieval results is an important feature that allows users to explore different aspects of the queried object. However, most of the works in this area are focused more on relevance rather than ...