Pattern recognition is an essential part of any high-level image analysis system. The CRPSM, in the framework of the European Projects GMOSS and GMOSAIC, has developed some techniques able to automatically recognize and extract potential made-man structures which could be present in complex aerial and satellites images. In particular, this paper aims at describing several of the developed techniques which allow the automatic detection of given objects of interest. These techniques are based on different approaches, therefore the results provided by them are compared and the their advantages and disadvantages are highlighted. The purpose described above is obtained by using several algorithms developed by CRPSM in the last few years based on the Mathematical Morphology, Geometrical Moment Invariant and Neural Networks approaches.

Comparing Neural Networks, Invariant Moments and Mathematical Morphology Performances for the Automatic Object Recognition / SANTILLI, GIANCARLO; LANEVE, Giovanni. - (2011), pp. 1-4. ((Intervento presentato al convegno 34th International Symposium on Remote Sensing of Environment tenutosi a Sydney; Australia nel 10 - 15 Aprile 2011.

Comparing Neural Networks, Invariant Moments and Mathematical Morphology Performances for the Automatic Object Recognition

SANTILLI, GIANCARLO;LANEVE, Giovanni
2011

Abstract

Pattern recognition is an essential part of any high-level image analysis system. The CRPSM, in the framework of the European Projects GMOSS and GMOSAIC, has developed some techniques able to automatically recognize and extract potential made-man structures which could be present in complex aerial and satellites images. In particular, this paper aims at describing several of the developed techniques which allow the automatic detection of given objects of interest. These techniques are based on different approaches, therefore the results provided by them are compared and the their advantages and disadvantages are highlighted. The purpose described above is obtained by using several algorithms developed by CRPSM in the last few years based on the Mathematical Morphology, Geometrical Moment Invariant and Neural Networks approaches.
File allegati a 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: http://hdl.handle.net/11573/708262
 Attenzione

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

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact