DocumentCode :
595053
Title :
Combining generative and discriminative models for classifying social images from 101 object categories
Author :
Ballan, L. ; Bertini, Marco ; Del Bimbo, Alberto ; Serain, A.M. ; Serra, Giovanni ; Zaccone, B.F.
Author_Institution :
Media Integration & Commun. Center, Univ. of Florence, Florence, Italy
fYear :
2012
fDate :
11-15 Nov. 2012
Firstpage :
1731
Lastpage :
1734
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.
Keywords :
image classification; object recognition; support vector machines; 101 object categories; Caltech101; Latent Dirichlet allocation; MICC-Flickr101; SVM classifiers; hybrid generative-discriminative model approach; image categorization; image features; multiple kernel combination framework; nonlinear kernels; object recognition; real-world images; social image classification; tags; visual features; Hybrid power systems; Kernel; Object recognition; Standards; Support vector machines; Training; Visualization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location :
Tsukuba
ISSN :
1051-4651
Print_ISBN :
978-1-4673-2216-4
Type :
conf
Filename :
6460484
Link To Document :
بازگشت