Localizing objects in images is a dificult task and represents the first step to the solution of the object recognition problem. This paper presents a novel approach to the localization problem based on recursive neural networks (RNNs). In particulal; a recursive learning paradigm is proposed to process directed acyclic graphs with labeled edges, and to realize mappings between graphs which are isomorph, i.e. that share the same topology of the links. The RNN model, that assumes a graph-based representation of images, uses a state transition function that depends on the edge labels and is independent from both the number and the order of the children of each node. Moreover, the presence of targets attached to the internal nodes guarantees a fast learning, particularly sensitive to the local features of the graph. Some preliminary experiments, carried out on artijcial images created using the COIL collection, are reported, showing very promising results.

Bianchini, M., Maggini, M., Sarti, L. (2006). Object localization using Input/Output Recursive Neural Networks. In Proceeedings of the 18th International Conference on Pattern Recognition (ICPR 2006) (pp.95-98). IEEE [10.1109/ICPR.2006.880].

Object localization using Input/Output Recursive Neural Networks

BIANCHINI, MONICA;MAGGINI, MARCO;SARTI, LORENZO
2006-01-01

Abstract

Localizing objects in images is a dificult task and represents the first step to the solution of the object recognition problem. This paper presents a novel approach to the localization problem based on recursive neural networks (RNNs). In particulal; a recursive learning paradigm is proposed to process directed acyclic graphs with labeled edges, and to realize mappings between graphs which are isomorph, i.e. that share the same topology of the links. The RNN model, that assumes a graph-based representation of images, uses a state transition function that depends on the edge labels and is independent from both the number and the order of the children of each node. Moreover, the presence of targets attached to the internal nodes guarantees a fast learning, particularly sensitive to the local features of the graph. Some preliminary experiments, carried out on artijcial images created using the COIL collection, are reported, showing very promising results.
2006
9780769525211
Bianchini, M., Maggini, M., Sarti, L. (2006). Object localization using Input/Output Recursive Neural Networks. In Proceeedings of the 18th International Conference on Pattern Recognition (ICPR 2006) (pp.95-98). IEEE [10.1109/ICPR.2006.880].
File in questo prodotto:
File Dimensione Formato  
ICPR06.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 2.98 MB
Formato Adobe PDF
2.98 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/11365/24065
 Attenzione

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