Scene classification via pLSA
A. Bosch, Andrew Zisserman and X. Munoz
In: ECCV 2006, 7-13 May 2006, Graz, Austria.
Given a set of images of scenes containing multiple object categories (e.g. grass, roads, buildings) our objective is to discover these objects in each image in an unsupervised manner, and to use this object distribution to perform scene classification. We achieve this discovery 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. The scene classification on the object distribution is carried out by a k-nearest neighbour classifier.
We investigate the classification performance under changes in the visual vocabulary and number of latent topics learnt, and develop a novel vocabulary using colour SIFT descriptors. Classification performance is compared to the supervised approaches of Vogel & Schiele and Oliva & Torralba, and the semi-supervised approach of Fei Fei & Perona using their own datasets and testing protocols. In all cases the combination of (unsupervised) pLSA followed by (supervised) nearest neighbour classification achieves superior results. We show applications of this method to image retrieval with relevance feedback and to scene classification in videos.
|EPrint Type:||Conference or Workshop Item (Poster)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Mudigonda Pawan Kumar|
|Deposited On:||01 May 2006|