All

What are you looking for?

All
Projects
Results
Organizations

Quick search

  • Projects supported by TA ČR
  • Excellent projects
  • Projects with the highest public support
  • Current projects

Smart search

  • That is how I find a specific +word
  • That is how I leave the -word out of the results
  • “That is how I can find the whole phrase”

Confidence measure for automatic face recognition

The result's identifiers

  • Result code in IS VaVaI

    <a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F11%3A43896939" target="_blank" >RIV/49777513:23520/11:43896939 - isvavai.cz</a>

  • Result on the web

  • DOI - Digital Object Identifier

Alternative languages

  • Result language

    angličtina

  • Original language name

    Confidence measure for automatic face recognition

  • Original language description

    The paper introduces confidence measure for automatic face recognition (AFR). Modified Kepenekci method based upon Gabor wavelets is used for AFR. The main goal of this work is automatic labelling of photographs. The recognition rate in real-world conditions is very low. Therefore, we propose a post-processing step to increase it. The confidence measure determines the probability that the recognition result is correct. It allows identifying of the incorrectly classified faces. Two confidence measures are proposed and evaluated on Czech New Agency (ČTK) data. The experiments show that confidence measure for AFR can be beneficial in some applications.

  • Czech name

  • Czech description

Classification

  • Type

    D - Article in proceedings

  • CEP classification

    IN - Informatics

  • OECD FORD branch

Result continuities

  • Project

  • Continuities

    S - Specificky vyzkum na vysokych skolach

Others

  • Publication year

    2011

  • Confidentiality

    S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Data specific for result type

  • Article name in the collection

    Proceedings International conference on knowledge discovery and information retrieval

  • ISBN

    978-989-8425-79-9

  • ISSN

  • e-ISSN

  • Number of pages

    4

  • Pages from-to

    365-368

  • Publisher name

    SciTePress

  • Place of publication

    Setúbal

  • Event location

    Paris

  • Event date

    Oct 26, 2011

  • Type of event by nationality

    WRD - Celosvětová akce

  • UT code for WoS article