Master of Science / Department of Electrical and Computer Engineering / Christopher L. Lewis / 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.
| Identifer | oai:union.ndltd.org:KSU/oai:krex.k-state.edu:2097/3651 |
| Date | January 1900 |
| Creators | Jakkula, Vinayak Reddy |
| Publisher | Kansas State University |
| Source Sets | K-State Research Exchange |
| Language | en_US |
| Detected Language | English |
| Type | Thesis |
Page generated in 0.0021 seconds