Efficient numerical analysis of optical imaging data: A comparative study
详细信息 查看全文
- 作者：David Duarte-Correa ; Alberto Pastrana-Palma ; Carlos A. Olvera-Olvera ; Sergio R. Ram¨ªrez-Rodr¨ªguez ; Daniel Alaniz-Lumbreras ; Domingo G¨®mez-Mel¨¦ndez ; Ismael de la Rosa ; Salvador Noriega ; Vianey Torres ; Victor M. Casta?o
- 关键词：Interest points ; Detector ; Computing time
- 刊名：Optik - International Journal for Light and Electron Optics
- 出版年：2013
- 出版时间：November, 2013
- 年：2013
- 卷：124
- 期：21
- 页码：4685-4692
- 全文大小：4308 K
文摘
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 ¡Á 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.