Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/75557
Citations
Scopus Web of ScienceĀ® Altmetric
?
?
Type: Journal article
Title: Flexible spatial configuration of local image features
Author: Carneiro, G.
Jepson, A.
Citation: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007; 29(12):2089-2104
Publisher: IEEE Computer Soc
Issue Date: 2007
ISSN: 0162-8828
1939-3539
Statement of
Responsibility: 
Gustavo Carneiro and Allan D. Jepson
Abstract: Local image features have been designed to be informative and repeatable under rigid transformations and illumination deformations. Even though current state-of-the-art local image features present a high degree of repeatability, their local appearance alone usually does not bring enough discriminative power to support a reliable matching, resulting in a relatively high number of mismatches in the correspondence set formed during the data association procedure. As a result, geometric filters, commonly based on global spatial configuration, have been used to reduce this number of mismatches. However, this approach presents a trade off between the effectiveness to reject mismatches and the robustness to non-rigid deformations. In this paper, we propose two geometric filters, based on semilocal spatial configuration of local features, that are designed to be robust to non-rigid deformations and to rigid transformations, without compromising its efficacy to reject mismatches. We compare our methods to the Hough transform, which is an efficient and effective mismatch rejection step based on global spatial configuration of features. In these comparisons, our methods are shown to be more effective in the task of rejecting mismatches for rigid transformations and non-rigid deformations at comparable time complexity figures. Finally, we demonstrate how to integrate these methods in a probabilistic recognition system such that the final verification step uses not only the similarity between features, but also their semi-local configuration.
Keywords: Local image feature; feature clustering; visual object recognition; wide baseline matching; long-range matching
Rights: Copyright 2007 IEEE
RMID: 0020114290
DOI: 10.1109/TPAMI.2007.1126
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.