Efficient feature detection using OBAloG: optimized box approximation of Laplacian of Gaussian

This thesis presents a novel approach for detecting robust and scale invariant interest points in images. The detector accurately and efficiently approximates the Laplacian of Gaussian using an optimal set of weighted box filters that take advantage of integral images to reduce computations. When combined with state-of-the art descriptors for matching, the algorithm performs better than leading feature tracking algorithms including SIFT and SURF in terms of speed and accuracy.

Grantor dc:publisher

Kansas State University

Year dc:date.issued

2010

Author dc:creator

• Jakkula, Vinayak Reddy

• Feature Extraction
• Laplacian of Gaussian

Statement dc:rights

• © the author. This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).

Licence dc:rights.uri

• http://rightsstatements.org/vocab/InC/1.0/

Language dc:language.iso

en_US

Handle dc:identifier.uri

http://hdl.handle.net/2097/3651

OAI identifier oai:identifier

oai:krex.k-state.edu:2097/3651