Indexing images or videos from their content

In light of the explosion of images and videos that are produced, archived and exchanged on the Internet and in private networks, the manual annotation of their content has become an impossible task. To overcome this hurdle, we contribute to developing technologies that allow for indexing and searching images and videos according to the visual elements they contain. For example, the underlying faces, textual content and places can be recognized by our software. Coherent storage and retrieval of information is achieved through the use of standard, yet evolved metadata formats such as MPEG-7 and RDF.

Related technologies: Test bed for the audio-visual MPEG-7 indexing of documentary films, test bed for indexing and searching filming locations, manual annotation software for generating the visual objects ground-truth in videos, same location image matching engine.

Teams

Industries

Releases

Recent news

  • Computer Research Institute of Montreal announces new patent
    18/04/2017

    We are happy to announce one new patent granted for the work of our Vision and Imaging team.

    +

Upcoming event

  • Atelier SiM5 : Vous voulez améliorer votre site Web? Utiliser mieux les médias sociaux?
    2 May 2017 8:30
    CRIM (405, avenue Ogilvy, bureau 101, Montréal)
    L'atelier SiM5 "Vous voulez améliorer votre site Web? Utiliser mieux les médias sociaux" se tiendra le 2 mai 2017 dans les locaux du CRIM.
    +

Recent Publications

  • PeopleBot

    +
  • Détection de menaces par classification de paquets de pare-feu

    +