Item


Scene Classification Using a Hybrid Generative/Discriminative Approach

We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent ";topics"; using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently, training a multiway classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly and training a multiway classifier on these vectors. To this end, we introduce a novel vocabulary using dense color SIFT descriptors and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learned, and the type of discriminative classifier used (k-nearest neighbor or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors’ own data sets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos

© IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, vol. 30, p. 712-727

IEEE

Author: Bosch Rué, Anna
Zisserman, Andrew
Muñoz Pujol, Xavier
Date: 2008
Abstract: We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent ";topics"; using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently, training a multiway classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly and training a multiway classifier on these vectors. To this end, we introduce a novel vocabulary using dense color SIFT descriptors and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learned, and the type of discriminative classifier used (k-nearest neighbor or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors’ own data sets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos
Format: application/pdf
Citation: Bosch, A., Zisserman, A., i Muñoz, X. (2008). Scene Classification Using a Hybrid Generative/Discriminative Approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30, 4, 712-727. Recuperat 19 maig 2010, a http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4359337
ISSN: 0162-8828
Document access: http://hdl.handle.net/10256/2317
Language: eng
Publisher: IEEE
Collection: Reproducció digital del document publicat a: http://dx.doi.org/10.1109/TPAMI.2007.70716
Articles publicats (D-ATC)
Is part of: © IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, vol. 30, p. 712-727
Rights: Tots els drets reservats
Subject: Algorismes computacionals
Discriminació visual
Imatges -- Processament
Reconeixement de formes (Informàtica)
Vídeo digital
Computer algorithms
Digital video
Image processing
Pattern recognition systems
Visual discrimination
Title: Scene Classification Using a Hybrid Generative/Discriminative Approach
Type: info:eu-repo/semantics/article
Repository: DUGiDocs

Subjects

Authors