• Efficient Representation of Local Geometry for Large Scale Object Retrieval 

      Autor: Perd’och, Michal; Chum, Ondřej; Matas, Jiří
      (IEEE, 2009-06)
      State of the art methods for image and object retrieval exploit both appearance (via visual words) and local geometry (spatial extent, relative pose). In large scale problems, memory becomes a limiting factor - local ...
    • Efficient Sequential Correspondence Selection by Cosegmentation 

      Autor: Čech, Jan; Matas, Jiří; Perd’och, Michal
      (IEEE, 2008-06)
      In many retrieval, object recognition and wide baseline stereo methods, correspondences of interest points are established possibly sublinearly by matching a compact descriptor such as SIFT. We show that a subsequent ...
    • Efficient Sequential Correspondence Selection by Cosegmentation 

      Autor: 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 ...
    • Epipolar Geometry Estimation via RANSAC Benefits from the Oriented Epipolar Constraint 

      Autor: Chum, Ondřej; Werner, Tomáš; Matas, Jiří
      (IEEE, 2004-08)
      The efficiency of epipolar geometry estimation by RANSAC is improved by exploiting the oriented epipolar constraint. Performance evaluation shows that the enhancement brings up to a two-fold speed-up. The orientation test ...
    • Epipolar Geometry from Two Correspondences 

      Autor: Perd’och, Michal; Matas, Jiří; Chum, Ondřej
      (IEEE, 2006)
      A novel algorithm for robust RANSAC-like estimation of epipolar geometry (of uncalibrated camera pair) from two correspondences of local affine frames (LAFs) is presented. Each LAF is constructed from three points independently ...
    • Face Verification Using Error Correcting Output Codes 

      Autor: Kittler, J.; Ghaderi, R.; Windeatt, T.; Matas, J.
      (IEEE, 2001)
      The error correcting output coding (ECOC) approach to classifier design decomposes a multi-class problem into a set of complementary two-class problems. We show how to apply the ECOC concept to automatic face verification, ...
    • Face-TLD: Tracking-Learning-Detection applied to faces 

      Autor: Kalal, Zdenek; Mikolajczyk, Krystian; Matas, Jiří
      (IEEE, 2010-09)
      A novel system for long-term tracking of a human face in unconstrained videos is built on Tracking-Learning-Detection (TLD) approach. The system extends TLD with the concept of a generic detector and a validator which is ...
    • Fast Detection of Multiple Textureless 3-D Objects 

      Autor: Cai, Hongping; Werner, Tomáš; Matas, Jiří
      (Springer, 2013)
      We propose a fast edge-based approach for detection and approximate pose estimation of multiple textureless objects in a single image. The objects are trained from a set of edge maps, each showing one object in one pose. ...
    • Fast no ground truth image registration accuracy evaluation: Comparison of bootstrap and Hessian approaches 

      Autor: Kybic, Jan
      (IEEE, 2008-05)
      Image registration algorithms provide a displacement field between two images. We consider the problem of estimating accuracy of the calculated displacement field from the input images only and without assuming any specific ...
    • Fast Parametric Elastic Image Registration 

      Autor: Kybic, Jan; Unser, Michael
      (IEEE, 2003-11)
      We present an algorithm for fast elastic multidimensional intensity-based image registration with a parametric model of the deformation. It is fully automatic in its default mode of operation. In the case of hard real-world ...
    • Fixed Points of Loopy Belief Propagation as Zero Gradients of a Function of Reparameterizations 

      Autor: Werner, Tomáš
      (Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, 2010-02)
      The existing view on loopy belief propagation sees it as an algorithm to nd a common zero of a system of non-linear functions, not explicitly related to each other. We show that these functions are in fact related { they ...
    • Forward-Backward Error: Automatic Detection of Tracking Failures 

      Autor: Kalal, Zdenek; Mikolajczyk, Krystian; Matas, Jiří
      (IEEE, 2010-08)
      This paper proposes a novel method for tracking failure detection. The detection is based on the Forward-Backward error, i.e. the tracking is performed forward and backward in time and the discrepancies between these two ...
    • Generalized Sampling: A Variational Approach. Part I: Theory 

      Autor: Kybic, Jan; Blu, Thierry; Unser, Michael
      (IEEE, 2002-08)
      We consider the problem of reconstructing a multidimensional vector function fin: Rm→Rn from a finite set of linear measures. These can be irregularly sampled responses of several linear filters. Traditional approaches ...
    • Generalized Sampling: A Variational Approach. Part II: Applications 

      Autor: Kybic, Jan; Blu, Thierry; Unser, Michael
      (IEEE, 2002-08)
      The variational reconstruction theory from a companion paper finds a solution consistent with some linear constraints and minimizing a quadratic plausibility criterion. It is suitable for treating vector and multidimensional ...
    • Geometric Hashing with Local Af ne Frames 

      Autor: Chum, Ondřej; Matas, Jiří
      (IEEE, 2006-06)
      We propose a novel representation of local image structure and a matching scheme that are insensitive to a wide range of appearance changes. The representation is a collection of local affine frames that are constructed ...
    • Geometric min-Hashing: Finding a (Thick) Needle in a Haystack 

      Autor: Chum, Ondřej; Perd’och, Michal; Matas, Jiří
      (IEEE, 2009-06)
      We propose a novel hashing scheme for image retrieval, clustering and automatic object discovery. Unlike commonly used bag-of-words approaches, the spatial extent of image features is exploited in our method. The geometric ...
    • Global Line Search Algorithm Hybridized with Quadratic Interpolation and Its Extension to Separable Functions 

      Autor: Baudiš, Petr; Pošík, Petr
      (ACM, 2015)
      We propose a novel hybrid algorithm“Brent-STEP” for uni- variate global function minimization, based on the global line search method STEP and accelerated by Brent’s method, a local optimizer that combines quadratic ...
    • Gradient based progressive probabilistic Hough transform 

      Autor: Galambos, C.; Kittler, J.; Matas, J.
      (IEEE/IET, 2001-06)
      The authors look at the benefits of exploiting gradient information to enhance the progressive probabilistic Hough transform (PPHT). It is shown that using the angle information in controlling the voting process and in ...
    • Guest Editors’ Introduction to the Special Section on CVPR Papers 

      Autor: Baker, Simon; Matas, Jiří; Zabih, Ramin
      (IEEE, 2008-10)
    • High-Dimensional Mutual Information Estimation For Image Registration 

      Autor: Kybic, Jan
      (IEEE, 2004-10)
      We present a new algorithm for mutual information estimation for image registration based on the nearest neighbor entropy estimator of Kozachenko and Leonenko. We modify the algorithm to be numerically robust and computationally ...