Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/113332
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Sparse flexible models of local features
Author: Carneiro, G.
Lowe, D.
Citation: Proceedings of the 9th European Conference on Computer Vision (ECCV 2006), as published in Lecture Notes in Computer Science, 2006 / vol.3953 LNCS, pp.29-43
Publisher: Springer-Verlag
Publisher Place: Berlin, Heidelberg
Issue Date: 2006
Series/Report no.: Lecture Notes in Computer Science; v. 3953
ISBN: 3540338322
9783540338321
ISSN: 0302-9743
1611-3349
Conference Name: 9th European Conference on Computer Vision (ECCV 2006) (07 May 2006 - 13 May 2006 : Graz, Austria)
Statement of
Responsibility: 
Gustavo Carneiro and David Lowe
Abstract: In recent years there has been growing interest in recognition models using local image features for applications ranging from long range motion matching to object class recognition systems. Currently, many state-of-the-art approaches have models involving very restrictive priors in terms of the number of local features and their spatial relations. The adoption of such priors in those models are necessary for simplifying both the learning and inference tasks. Also, most of the state-of-the-art learning approaches are semi-supervised batch processes, which considerably reduce their suitability in dynamic environments, where unannotated new images are continuously presented to the learning system. In this work we propose: 1) a new model representation that has a less restrictive prior on the geometry and number of local features, where the geometry of each local feature is influenced by its k closest, neighbors and models may contain hundreds of features; and 2) a novel unsupervised on-line learning algorithm that is capable of estimating the model parameters efficiently and accurately. We implement a visual class recognition system using the new model and learning method proposed here, and demonstrate that our system produces competitive classification and localization results compared to state-of-the-art methods. Moreover, we show that the learning algorithm is able to model not only classes with consistent texture (e.g., faces), but also classes with shape only (e.g., leaves), classes with a common shape but with a great variability in terms of internal texture (e.g., cups), and classes of flexible objects (e.g., snake).
Rights: © Springer-Verlag Berlin Heidelberg 2006
RMID: 0020114262
DOI: 10.1007/11744078_3
Published version: https://www.springer.com/gp/book/9783540338321
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.