Foto dell'editore

Learning Features for Robust Object Recognition

Stephan Hasler

Editore: Shaker Verlag Okt 2010, 2010
ISBN 10: 3832294449 / ISBN 13: 9783832294441
Nuovi / Taschenbuch / Quantità: 1
Da Rhein-Team Lörrach Ivano Narducci e.K. (Lörrach, Germania)
Copie del libro da altre librerie
Mostra tutte le  copie di questo libro
Aggiungere al carrello
Prezzo consigliato:
Prezzo: EUR 45,80
Convertire valuta
Spedizione: EUR 12,00
Da: Germania a: U.S.A.
Destinazione, tempi e costi

Lista dei preferiti


Dati bibliografici

Titolo: Learning Features for Robust Object ...

Casa editrice: Shaker Verlag Okt 2010

Data di pubblicazione: 2010

Legatura: Taschenbuch

Condizione libro: Neu


Neuware - In daily life humans easily distinguish large numbers of objects based on their visual appearance. Despite extensive efforts in recent years, modem recognition systems are unable to robustly reproduce this capability. The main problem is that any object can have an infinite number of appearances, due to different viewing positions, lighting conditions and occlusion. A technical system must leam to generalize over these irrelevant variances, while concentrating on the meaningful object information. This is done by the socalled feature extraction. In this work I investigate two new methods for feature leaming that should overcome the limitations of existing approaches. The first method is based on the holistic appearance of objects and tries to combine the advantages of supervised and unsupervised learning. I show for a constraint scenario that the obtained features improve the recognition performance. However the rigidness of the holistic coding prevents the application of the method to more complex, real world scenarios. Because of this in the second approach I use a more flexible representation that focuses on the presence of local object parts. After proposing a new supervised feature selection method, I show that the resulting representation yields a strong performance on various object databases and avoids some drawbacks of established recognition approaches. Finally I integrate the approach into areal-time recognition system that is the first one to robustly identify about 120 objects of arbitrary shape and texture under 3D rotation in front of cluttered background, and thus marks a major step towards invariant object recognition. 132 pp. Englisch. Codice inventario libreria 9783832294441

Info su libreria e pagamento

Metodi di pagamento

La libreria accetta i seguenti metodi di pagamento:

  • American Express
  • Assegno
  • Carte Bleue
  • Mastercard
  • PayPal
  • Visa

[Cercare nel catalogo della libreria]

[Tutti i libri della libreria]

[Fare una domanda alla libreria]

Libreria: Rhein-Team Lörrach Ivano Narducci e.K.
Indirizzo: Lörrach, Germania

Libreria AbeBooks dal: 11 gennaio 2012
Valutazione libreria: 5 stelle

Condizioni di vendita:

Allgemeine Geschäftsbedingungen (

Rhein-Team Lörrach, Inhaber Ivano Narducci e.K., Mühlestr. 1
D-79539 Lörrach, nachfolgend als Verkäufer bezeichnet.

§ 1 Allgemeines, Begriffsbestimmungen

(1) Der Verkäufer bietet unter dem Nutzernamen rhein-team unter der Plattform insbesondere Bücher an. Die folgenden Allgemeinen Geschäftsbedingungen (AGB) gelten für die Geschäftsbeziehung zwischen dem Verkäufer und dem Kunden in ihrer zum Zeitpunkt der Bestellung gültigen Fassung. Ferne...

[Ulteriori informazioni]

Condizioni di spedizione:

Die Ware wird innerhalb von 1-3 Tagen nach Bestelleingang verschickt. Bitte entnehmen Sie den voraussichtlichen Liefertermin Ihrer Bestellbestätigung. Die Versandkostenpauschalen basieren auf Durchschnittswerten für 1 kg schwere Bücher. Über abweichende Kosten (z.B. wegen eines sehr schweren Buches) werden Sie gegebenenfalls vom Verkäufer informiert.