When dealing with a pattern recognition task two major issues must be faced: "rstly, a feature extraction technique has to be applied to extract useful representations of the objects to be recognized; secondly, a classi"cation algorithm must be devised in order to produce a class hypothesis once a pattern representation is given. Adaptive graphical pattern recognition is proposed as a new approach to face these two issues when neither a purely symbolic nor a purely sub-symbolic representation seems adequate for the patterns. This approach is based on appropriate structured representations of patterns which are, subsequently, processed by recursive neural networks, that can be trained to perform the given classi"cation task using connectionist-based learning algorithms. In the proposed framework, the joint role of the structured representation and learning makes it possible to face tasks in which input patterns are a!ected by many di!erent sources of noise. We report some results that show how the proposed scheme can produce a very promisingperformancefortheclassi"cationofcompanylogoscorruptedbynoise. 2001PatternRecognitionSociety. Published by Elsevier Science Ltd. All rights reserved.

Diligenti, M., Gori, M., Maggini, M., Martinelli, E. (2001). Adaptive graphical pattern recognition for the classification of company logos. PATTERN RECOGNITION, 34(10), 2049-2061 [10.1016/S0031-3203(00)00127-8].

Adaptive graphical pattern recognition for the classification of company logos

DILIGENTI, MICHELANGELO;GORI, MARCO;MAGGINI, MARCO;MARTINELLI, ENRICO
2001-01-01

Abstract

When dealing with a pattern recognition task two major issues must be faced: "rstly, a feature extraction technique has to be applied to extract useful representations of the objects to be recognized; secondly, a classi"cation algorithm must be devised in order to produce a class hypothesis once a pattern representation is given. Adaptive graphical pattern recognition is proposed as a new approach to face these two issues when neither a purely symbolic nor a purely sub-symbolic representation seems adequate for the patterns. This approach is based on appropriate structured representations of patterns which are, subsequently, processed by recursive neural networks, that can be trained to perform the given classi"cation task using connectionist-based learning algorithms. In the proposed framework, the joint role of the structured representation and learning makes it possible to face tasks in which input patterns are a!ected by many di!erent sources of noise. We report some results that show how the proposed scheme can produce a very promisingperformancefortheclassi"cationofcompanylogoscorruptedbynoise. 2001PatternRecognitionSociety. Published by Elsevier Science Ltd. All rights reserved.
Diligenti, M., Gori, M., Maggini, M., Martinelli, E. (2001). Adaptive graphical pattern recognition for the classification of company logos. PATTERN RECOGNITION, 34(10), 2049-2061 [10.1016/S0031-3203(00)00127-8].
File in questo prodotto:
File Dimensione Formato  
PR01.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 468.44 kB
Formato Adobe PDF
468.44 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/11365/29492
 Attenzione

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