In this paper we present a hybrid generative-discriminative approach for image categorization in real-world images, based on Latent Dirichlet Allocation and SVM classifiers. We use SVMs with non-linear kernels on different visual features in a multiple kernel combination framework. A major contribution of our work is also the introduction of a novel dataset, called MICC-Flickr101, based on the popular Caltech101 and collected from Flickr. We demonstrate the effectiveness and efficiency of our method testing it on both datasets, and we evaluate the impact of combining image features and tags for object recognition.

Combining Generative and Discriminative Models for Classifying Social Images from 101 Object Categories / L. Ballan;M. Bertini;A. Del Bimbo;A. M. Serain;G. Serra;B. F. Zaccone. - STAMPA. - (2012), pp. 1731-1734. (Intervento presentato al convegno International Conference on Pattern Recognition (ICPR) tenutosi a Tsukuba, Japan nel 2012).

Combining Generative and Discriminative Models for Classifying Social Images from 101 Object Categories

BALLAN, LAMBERTO;BERTINI, MARCO;DEL BIMBO, ALBERTO;SERRA, GIUSEPPE;
2012

Abstract

In this paper we present a hybrid generative-discriminative approach for image categorization in real-world images, based on Latent Dirichlet Allocation and SVM classifiers. We use SVMs with non-linear kernels on different visual features in a multiple kernel combination framework. A major contribution of our work is also the introduction of a novel dataset, called MICC-Flickr101, based on the popular Caltech101 and collected from Flickr. We demonstrate the effectiveness and efficiency of our method testing it on both datasets, and we evaluate the impact of combining image features and tags for object recognition.
2012
Proc. of International Conference on Pattern Recognition (ICPR)
International Conference on Pattern Recognition (ICPR)
Tsukuba, Japan
2012
L. Ballan;M. Bertini;A. Del Bimbo;A. M. Serain;G. Serra;B. F. Zaccone
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/656339
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 5
social impact