To cite this record: http://ddd.uab.cat/record/52595
An Attention Module for Object Detection in Cluttered Images
Lecca, Michela

Date: 2009
Abstract: In this paper, we propose a visual attention module that automatically detects the regions of an input previously unseen image, which are more likely occupied by a known object. The module can be integrated in many object recognition systems for reducing the image space in which to search the object, and the computational costs. The strategy has been tested on two public real-world image databases showing good performances. Moreover, we measured the usefulness of this selective visual attention by comparing the performances of the SIFT recognition algorithm with and without the proposed attention module.
Rights: Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades. Creative Commons
Language: Anglès.
Document: article ; recerca ; publishedVersion
Published in: ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 8 n. 2 (2009) p. 68-83, ISSN 1577-5097



16 p, 2.0 MB

The record appears in these collections:
Articles > Published articles > ELCVIA : Electronic Letters on Computer Vision and Image Analysis

 Record created 2010-01-18, last modified 2014-06-08



   Favorit i Compartir
QR image