Efficient feature detection using OBAloG: optimized box approximation of Laplacian of Gaussian
dc.contributor.author | Jakkula, Vinayak Reddy | |
dc.date.accessioned | 2010-04-19T16:39:21Z | |
dc.date.available | 2010-04-19T16:39:21Z | |
dc.date.graduationmonth | May | en_US |
dc.date.issued | 2010-04-19T16:39:21Z | |
dc.date.published | 2010 | en_US |
dc.description.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. | en_US |
dc.description.advisor | Christopher L. Lewis | en_US |
dc.description.degree | Master of Science | en_US |
dc.description.department | Department of Electrical and Computer Engineering | en_US |
dc.description.level | Masters | en_US |
dc.identifier.uri | http://hdl.handle.net/2097/3651 | |
dc.language.iso | en_US | en_US |
dc.publisher | Kansas State University | en |
dc.subject | Feature Extraction | en_US |
dc.subject | Laplacian of Gaussian | en_US |
dc.subject.umi | Engineering, Electronics and Electrical (0544) | en_US |
dc.title | Efficient feature detection using OBAloG: optimized box approximation of Laplacian of Gaussian | en_US |
dc.type | Thesis | en_US |