• Hypothesis selection for scene interpretation using grammatical models of scene evolution 

      Autor: Young, R.; Kittler, J.; Matas, J.
      (IEEE, 1998-08)
      A major bottleneck in dynamic scene interpretation is the search that is required through a database to find a model that best matches the observed data. We show that the problem can be alleviated if the object model ...
    • Image Matching and Retrieval by Repetitive Patterns 

      Autor: 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. ...
    • Improving Descriptors for Fast Tree Matching by Optimal Linear Projection 

      Autor: Mikolajczyk, Krystian; Matas, Jiří
      (IEEE, 2007-10)
      In this paper we propose to transform an image descriptor so that nearest neighbor (NN) search for correspondences becomes the optimal matching strategy under the assumption that inter-image deviations of corresponding ...
    • Inter-stage Feature Propagation in Cascade Building with AdaBoost 

      Autor: Šochman, Jan; Matas, Jiří
      (IEEE, 2004-08)
      A modification of the cascaded detector with the Ada-Boost trained stage classifiers is proposed and brought to bear on the face detection problem. The cascaded detector is a sequential classifier with the ability of early ...
    • ITAREPS: Information Technology Aided Relapse Prevention Programme in Schizophrenia 

      Autor: Novák, Daniel
      (2008)
      ITAREPS presents a mobile phone-based telemedicine solution for weekly remote patient monitoring and disease management in schizophrenia and psychotic disorders in general. The programme provides health professionals with ...
    • Joint Orientation of Epipoles 

      Autor: Chum, Ondřej; Werner, Tomáš; Pajdla, Tomáš
      (British Machine Vision Association, 2003-09)
      It is known that epipolar constraint can be augmented with orientation by formulating it in the oriented projective geometry. This oriented epipolar constraint requires knowing the orientations (signs of overall scales) ...
    • jSLIC : superpixels in ImageJ 

      Autor: Borovec, Jiří; Kybic, Jan
      (Czech Society for Cybernetics and Informatics, 2014)
      This paper presents the implementation and particular improvements on the superpixel clustering algorithm - SLIC (Simple Linear Iterative Clustering). The main contribution of the jSLIC is a significant speed-up of the ...
    • Large-Scale Discovery of Spatially Related Images 

      Autor: 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 ...
    • Learning Support Vectors for Face Verification and Recognition 

      Autor: Jonsson, K.; Matas, J.; Kittler, J.; Li, Y. P.
      (IEEE, 2000)
      The paper studies support vector machines (SVM) in the context of face verification and recognition. Our study supports the hypothesis that the SVM approach is able to extract the relevant discriminatory information from ...
    • Line filtering for detection of microtools in 3D ultrasound data 

      Autor: Uherčík, Marián; Kybic, Jan; Cachard, Christian; Liebgott, Hervé
      (IEEE, 2009-09)
      We propose a robust method for localization of elongated surgical tools in 3D ultrasound data based on shape analysis. The tubular structures in input data are enhanced by a line filter in the pre-processing phase. A new ...
    • Line Filtering for Surgical Tool Localization in 3D Ultrasound Images 

      Autor: Uherčík, Marián; Kybic, Jan; Zhao, Yue; Cachard, Christian; Liebgott, Hervé
      (Elsevier, 2013)
      We present a method for automatic surgical tool localization in 3D ultrasound images based on line ltering, voxel classi cation and model tting. A possible application is to provide assistance for biopsy needle or ...
    • Linear Predictors for Fast Simultaneous Modeling and Tracking 

      Autor: Ellis, Liam; Dowson, Nicholas; Matas, Jiří; Bowden, Richard
      (IEEE, 2007-10)
      An approach for fast tracking of arbitrary image features with no prior model and no offline learning stage is presented. Fast tracking is achieved using banks of linear displacement predictors learnt online. A multi-modal ...
    • Linear Programming Relaxation Approach to Weighted CSP 

      Autor: Werner, Tomáš
      (2008)
    • Local Affine Frames for Wide-Baseline Stereo 

      Autor: Matas, Jiří; Obdržálek, Štěpán; Chum, Ondřej
      (IEEE, 2002)
      A novel procedure for establishing wide-baseline correspondence is introduced. Tentative correspondences are established by matching photometrically normalised colour measurements represented in a local affine frame. The ...
    • Marginal Consistency: Unifying Constraint Propagation on Commutative Semirings 

      Autor: Werner, Tomáš
      (Institute National de la Recherche Agronomique, 2008-09)
      We generalise the linear programming relaxation approach to Weighted CSP by Schlesinger and the max-sum diffusion algorithm by Koval and Kovalevsky twice: from Weighted CSP to Semiring CSP, and from binary networks to ...
    • Matching with PROSAC – Progressive Sample Consensus 

      Autor: Chum, Ondřej; Matas, Jiří
      (IEEE, 2005-06)
      A new robust matching method is proposed. The progressive sample consensus (PROSAC) algorithm exploits the linear ordering defined on the set of correspondences by a similarity function used in establishing tentative ...
    • Model Fitting Using RANSAC for Surgical Tool Localization in 3-D Ultrasound Images 

      Autor: Uherčík, Marián; Kybic, Jan; Liebgott, Hervé; Cachard, Christian
      (IEEE, 2010-08)
      Ultrasound guidance is used for many surgical interventions such as biopsy and electrode insertion. We present a method to localize a thin surgical tool such as a biopsy needle or a microelectrode in a 3-D ultrasound image. ...
    • Model Selection for Automated Architectural Reconstruction from Multiple Views 

      Autor: Werner, Tomáš; Zisserman, Andrew
      (British Machine Vision Conference (BMVC), 2002-09)
      We describe progress in automatically fitting a plane plus modelled perturbation surface model to represent architectural scenes. There are two areas of novelty. The first is a method of fitting parametrized models in which ...
    • Multi Modal Verification for Teleservices and Security Applications (M2VTS) 

      Autor: Richard, G.; Menguy, Y.; Guis, I.; Suaudeau, N.; Boudy, J.; Lockwood, P.; Fernandez, C.; Fernández, F.; Kotropoulos, C.; Tefas, A.; Pitas; Heimgartner, R.; Ryser, P.; Beumier, C.; Verlinde, P.; Pigeon, S.; Matas, J.; Kittler, J.; Bigün, J.; Abdeljaoued, Y.; Meurville, E.; Besacier, L.; Ansorge, M.; Maitre, G.; Luettin, J.; Ben-Yacoub, S.; Ruiz, B.; Aldama, K.; Cortes, J.
      (IEEE, 1999-07)
      The paper presents the European ACTS project “M2VTS” which stands for Multi Modal Verification for Teleservices and Security Applications. The primary goal of this project is to address the issue of secured access to local ...
    • A Multi-Frequency Approach to Increase the Native Resolution of Ultrasound Images 

      Autor: Varray, François; Cachard, Christian; Kybic, Jan; Novell, Anthony; Bouakaz, Ayache; Basset, Olivier
      (IEEE, 2012)
      In ultrasound (US), a natural competition exists between the resolution of the image and the depth-of-field (DOF) into the medium, competition which is difficult to overcome with current US probe. Using large bandwidth ...