The nature of statistical learning theory
The nature of statistical learning theory
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Histograms of Oriented Gradients for Human Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
A Performance Evaluation of Local Descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence
Speeded-Up Robust Features (SURF)
Computer Vision and Image Understanding
| Hi-index | 0.00 |
Algorithms based on the local description of interest regions are well adapted to the task of detecting and matching equivalent points between two images. Classical descriptors such as SIFT or SURF are efficient when applied to regular images with rich information. When it comes to medical images, these algorithms are not longer applicable without adaptation. For this reason, we propose in this paper a feature-based framework for the detection of objects in medical images with poor information (e.g. X-Ray images). Our approach is based on a modified version of SURF. In order to illustrate our purpose, we apply our framework to the cervical vertebra detection on X-Ray images. The results show that this modified descriptor is an efficient solution in the medical domain. It allows to properly process the vertebra detection in better computing times than other classical descriptors.