Daniel Keysers

Studied Computer Science in Aachen, Germany and Madrid, Spain; PhD in Computer Science (Image Understanding, Pattern Recognition), RWTH Aachen, Germany; PostDoc at German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany; Joined Google Zurich in 2007 as Software Engineer, projects: YouTube Content-ID, Handwriting Recognition

Google Publications

Previous Publications


    Features for image retrieval: an experimental comparison

    Thomas Deselaers, Daniel Keysers, Hermann Ney

    Information Retrieval, vol. 11 (2008), pp. 77-107


    Deformation models for image recognition

    Daniel Keysers, Thomas Deselaers, Christian Gollan, Hermann Ney

    Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 29 (2007), pp. 1422-1435


    Discriminative Training for Object Recognition using Image Patches

    Thomas Deselaers, Daniel Keysers, Hermann Ney

    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2005)


    Improving a Discriminative Approach to Object Recognition using Image Patches.

    Thomas Deselaers, Daniel Keysers, Hermann Ney

    Pattern Recognition (DAGM) (2005)


    Adaptation in Statistical Pattern Recognition Using Tangent Vectors

    Daniel Keysers, Wolfgang Macherey, Hermann Ney, Joerg Dahmen

    IEEE Trans. Pattern Analysis Machine Intelligence, vol. 26 (2004), pp. 269-274


    Elastic image matching is NP-complete

    Daniel Keysers, Walter Unger

    Pattern Recognition Letters, vol. 24 (2003), pp. 445-453


    Maximum Entropy and Gaussian Models for Image Object Recognition

    Daniel Keysers, Franz Josef Och, Hermann Ney

    DAGM-Symposium (2002), pp. 498-506


    Improving Automatic Speech Recognition Using Tangent Distance

    Wolfgang Macherey, Daniel Keysers, Joerg Dahmen, Hermann Ney

    European Conference on Speech Communication and Technology (2001)


    Learning of Variability for Invariant Statistical Pattern Recognition

    Daniel Keysers, Wolfgang Macherey, Joerg Dahmen, Hermann Ney

    European Conference on Machine Learning (ECML) (2001), pp. 263-275