Original approach for the localization of objects in images

R. Vaillant, C. Monrocq, Y. Le Cun

Research output: Contribution to journalArticlepeer-review

Abstract

An original approach is presented for the localization of objects in an image which approach is neuronal and has two steps. In the first step, a rough localization is performed by presenting each pixel with its neighbourhood to a neural net which is able to indicate whether this pixel and its neighbourhood are the image of the search object. This first filter does not discriminate for position. From its result, areas which might contain an image of the object can be selected. In the second step, these areas are presented to another neural net which can determine the exact position of the object in each area. This algorithm is applied to the problem of localizing faces in images.

Original languageEnglish (US)
Pages (from-to)245-250
Number of pages6
JournalIEE Proceedings: Vision, Image and Signal Processing
Volume141
Issue number4
DOIs
StatePublished - Aug 1994

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Original approach for the localization of objects in images'. Together they form a unique fingerprint.

Cite this