Search Results - "Rangoni, Yves"

  • Showing 1 - 11 results of 11
Refine Results
  1. 1

    Semi-automatic ground truth generation using unsupervised clustering and limited manual labeling: Application to handwritten character recognition by Vajda, Szilárd, Rangoni, Yves, Cecotti, Hubert

    Published in Pattern recognition letters (01-06-2015)
    “…•We propose a fast and accurate semi-automatic labeling strategy.•Human expert knowledge (time and cost) is reduced to minimum.•Unsupervised clustering and…”
    Get full text
    Journal Article
  2. 2

    Large-scale detection of non-technical losses in imbalanced data sets by Glauner, Patrick, Boechat, Andre, Dolberg, Lautaro, State, Radu, Bettinger, Franck, Rangoni, Yves, Duarte, Diogo

    “…Non-technical losses (NTL) such as electricity theft cause significant harm to our economies, as in some countries they may range up to 40% of the total…”
    Get full text
    Conference Proceeding
  3. 3

    Labelling logical structures of document images using a dynamic perceptive neural network by Rangoni, Yves, Belaïd, Abdel, Vajda, Szilárd

    “…This paper proposes a new method for labelling the logical structures of document images. The system starts with digitised images of paper documents, performs…”
    Get full text
    Journal Article
  4. 4

    Neighborhood Features Help Detecting Non-Technical Losses in Big Data Sets by Glauner, Patrick, Meira, Jorge Augusto, Dolberg, Lautaro, State, Radu, Bettinger, Franck, Rangoni, Yves

    “…Electricity theft occurs around the world in both developed and developing countries and may range up to 40% of the total electricity distributed. More…”
    Get full text
    Conference Proceeding
  5. 5

    Recognition Driven Page Orientation Detection by Rangoni, Y., Shafait, F., van Beusekom, J., Breuel, T.M.

    “…In document image recognition, orientation detection of the scanned page is necessary for the following procedures to work correctly as they assume that the…”
    Get full text
    Conference Proceeding
  6. 6

    Neighborhood Features Help Detecting Non-Technical Losses in Big Data Sets by Glauner, Patrick, Meira, Jorge, Dolberg, Lautaro, State, Radu, Bettinger, Franck, Rangoni, Yves, Duarte, Diogo

    Published 04-07-2016
    “…Electricity theft is a major problem around the world in both developed and developing countries and may range up to 40% of the total electricity distributed…”
    Get full text
    Journal Article
  7. 7

    Large-Scale Detection of Non-Technical Losses in Imbalanced Data Sets by Glauner, Patrick O, Boechat, Andre, Dolberg, Lautaro, State, Radu, Bettinger, Franck, Rangoni, Yves, Duarte, Diogo

    Published 26-02-2016
    “…Non-technical losses (NTL) such as electricity theft cause significant harm to our economies, as in some countries they may range up to 40% of the total…”
    Get full text
    Journal Article
  8. 8

    Evaluation of robustness and performance of Early Stopping Rules with Multi Layer Perceptrons by Lodwich, A., Rangoni, Y., Breuel, T.

    “…In this paper, we evaluate different early stopping rules (ESR) and their combinations for stopping the training of multi layer perceptrons (MLP) using the…”
    Get full text
    Conference Proceeding
  9. 9

    XML Data Representation in Document Image Analysis by Belaid, A., Falk, I., Rangoni, Y.

    “…This paper presents the XML-based formats ALTO, TEI, METS used for digital libraries and their interest for data representation in a document image analysis…”
    Get full text
    Conference Proceeding
  10. 10

    Data categorization for a context return applied to logical document structure recognition by Rangoni, Y., Belaid, A.

    “…The purpose of this work is to develop a pattern recognition system simulating the human vision. A transparent neural network, with context returns is used…”
    Get full text
    Conference Proceeding
  11. 11

    Automatic indexing and reformulation of ancient dictionaries by Belaid, A., Turcan, I., Pierrel, J.M., Belaid, Y., Rangoni, Y., Hadjamar, H.

    “…We discuss automatic indexing and reformulation of ancient dictionaries. The objective is to make easy the access to ancient printed documents from XVI to XIX…”
    Get full text
    Conference Proceeding