Efficient feature detection using OBAloG: optimized box approximation of Laplacian of Gaussian
Date
2010-04-19T16:39:21Z
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Kansas State University
Abstract
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.
Description
Keywords
Feature Extraction, Laplacian of Gaussian
Graduation Month
May
Degree
Master of Science
Department
Department of Electrical and Computer Engineering
Major Professor
Christopher L. Lewis
Date
2010
Type
Thesis