Efficient numerical analysis of optical imaging data: A comparative study
| Autor: | Alberto Pastrana-Palma, Carlos A. Olvera-Olvera, Domingo Gómez-Meléndez, Daniel Alaniz-Lumbreras, Sergio R. Ramírez-Rodríguez, Salvador Noriega, David Duarte-Correa, Victor M. Castaño, Ismael de la Rosa, Vianey Torres |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Hessian matrix
Laplace transform Pixel business.industry Computer science Numerical analysis Detector ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Atomic and Molecular Physics and Optics Electronic Optical and Magnetic Materials symbols.namesake Computer Science::Graphics Optics Computer Science::Computer Vision and Pattern Recognition Hessian affine region detector symbols Computer vision Artificial intelligence Electrical and Electronic Engineering Zoom business Rotation (mathematics) ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | Optik. 124:4685-4692 |
| ISSN: | 0030-4026 |
| DOI: | 10.1016/j.ijleo.2013.01.116 |
| Popis: | The computational efficiency of 14 optical detectors over six types of transformations, namely: blur, illumination, rotation, viewpoint, zoom, and zoom-rotation changes, was analyzed. Images with the same resolution (750 × 500 pixels) were studied, in terms of correspondences, repeatability and computing time, and the correspondence was measured by using homographies i.e. projective transformations, to obtain the best efficiency for imaging applications. Results show that the multi-scale Harris Hessian detector is the most efficient for blur, illumination, and zoom-rotation changes. Meanwhile, multi-scale Hessian and Hessian Laplace are the best methods for rotation, viewpoint, and zoom changes. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect