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.

An Attention Module for Object Detection in Cluttered Images

Lecca, Michela
2009-01-01

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.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11582/5221
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact