2026-09-19T17:53:42Zhttps://krex.k-state.edu/server/oai/request

oai:krex.k-state.edu:2097/36512026-09-02T16:02:07Zcom_2097_1col_2097_4

Jakkula, Vinayak Reddy 2010-04-19T16:39:21Z 2010-04-19T16:39:21Z 2010-04-19T16:39:21Z 2010 May http://hdl.handle.net/2097/3651 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. Master of Science Masters Department of Electrical and Computer Engineering Christopher L. Lewis en_US Kansas State University © 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). http://rightsstatements.org/vocab/InC/1.0/ Feature Extraction Laplacian of Gaussian Engineering, Electronics and Electrical (0544) Efficient feature detection using OBAloG: optimized box approximation of Laplacian of Gaussian Thesis open.access