Visual database engines are usually based on predefined criteria for retrieving the images in response to a given query.In this paper,we propose a novel approach based on neural networks by which the retrieval criterion is derived on the basis of learning from examples. In particular, the proposed approach uses a graph-based image representation that denotes the relationships among regions in the image and on recursive neural networks which can process directed ordered acyclic graphs. The graph-based representation combines structural and sub-symbolic features of the image, while recursive neural networks can discover the optimal representation for searching the image database. A set of preliminary experiments on artificial images clearly indicate that the proposed approach is very promising.

DE MAURO, C., Diligenti, M., Gori, M., Maggini, M. (2003). Similarity learning for graph-based image representations. PATTERN RECOGNITION LETTERS, 24(8), 1115-1122 [10.1016/S0167-8655(02)00258-1].

Similarity learning for graph-based image representations

DILIGENTI, MICHELANGELO;GORI, MARCO;MAGGINI, MARCO
2003-01-01

Abstract

Visual database engines are usually based on predefined criteria for retrieving the images in response to a given query.In this paper,we propose a novel approach based on neural networks by which the retrieval criterion is derived on the basis of learning from examples. In particular, the proposed approach uses a graph-based image representation that denotes the relationships among regions in the image and on recursive neural networks which can process directed ordered acyclic graphs. The graph-based representation combines structural and sub-symbolic features of the image, while recursive neural networks can discover the optimal representation for searching the image database. A set of preliminary experiments on artificial images clearly indicate that the proposed approach is very promising.
2003
DE MAURO, C., Diligenti, M., Gori, M., Maggini, M. (2003). Similarity learning for graph-based image representations. PATTERN RECOGNITION LETTERS, 24(8), 1115-1122 [10.1016/S0167-8655(02)00258-1].
File in questo prodotto:
File Dimensione Formato  
PRL03.pdf

non disponibili

Tipologia: PDF editoriale
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 408.2 kB
Formato Adobe PDF
408.2 kB 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/11365/21293
 Attenzione

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