@InProceedings{MehdiMirza-Mohammadi2009,
author="Mehdi Mirza-Mohammadi
and Sergio Escalera
and Petia Radeva",
title="Contextual-Guided Bag-of-Visual-Words Model for Multi-class Object Categorization",
booktitle="13th International Conference on Computer Analysis of Images and Patterns",
year="2009",
publisher="Springer Berlin Heidelberg",
volume="5702",
pages="748--756",
abstract="Bag-of-words model (BOW) is inspired by the text classification problem, where a document is represented by an unsorted set of contained words. Analogously, in the object categorization problem, an image is represented by an unsorted set of discrete visual words (BOVW). In these models, relations among visual words are performed after dictionary construction. However, close object regions can have far descriptions in the feature space, being grouped as different visual words. In this paper, we present a method for considering geometrical information of visual words in the dictionary construction step. Object interest regions are obtained by means of the Harris-Affine detector and then described using the SIFT descriptor. Afterward, a contextual-space and a feature-space are defined, and a merging process is used to fuse feature words based on their proximity in the contextual-space. Moreover, we use the Error Correcting Output Codes framework to learn the new dictionary in order to perform multi-class classification. Results show significant classification improvements when spatial information is taken into account in the dictionary construction step.",
optnote="HuPBA; MILAB",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=1185), last updated on Fri, 19 Sep 2014 10:28:21 +0200",
isbn="978-3-642-03766-5",
issn="0302-9743",
doi="10.1007/978-3-642-03767-2_91"
}