This project focus on the problem of detecting affine invariant features in arbitrary images and on the performance evaluation of region detectors/descriptors.
- Region detector
- Harris-Affine & Hessian Affine:
- MSER （ Maximaly stable extremal regions）:
- IBR & EBR（Intensity extrema based detector & Edge based detector）:
- Salient regions:
- All Detectors – Survey:
- Region descriptor
- Detectors evaluation – Matlab files to compute the repeatability.
- Descriptors evaluation – Matlab files to compute the matching score.
- images in PPM format
- homographies between image pairs.
- five different changes in imaging conditions:
- viewpoint changes,
- scale changes, image blur,
- JPEG compression, and
the viewpoint change test the camera varies from a fronto-parallel view to one with significant foreshortening at approximately 60 degrees to the camera
The scale changes by about a factor of four.
The light changes are introduced by varying the camera aperture.
- JPEG compression
The JPEG sequence is generated using a standard xv image browser with the image quality parameter varying from 40\% to 2\%
|Harris & Hessian(also Windows)(1921206B)||8-6-2006||Scale & affine invariant feature detectors used in Mikolajczyk CVPR06 and CVPR08 for object class recognition. Efficient implementation of both, detectors and descriptors. Currently only sift descriptor was tested with the detectors but the other descriptors should work as well. Package contains a PCA basis for projections on fewer number of dimensions. Run with pca projection and take as many SIFT dimensions as you wish. Run without options for help. Includes windows executable which requires cygwin.
./extract_features -harhes -i img.png -sift -pca harhessift.basis
|Scale Saliency||8-9-2006||Some problems were reported for the Salient region detector. Please, try the new versions from the author’s homepage.|
|Detectors & Descriptors||12-6-2007||Same as Harris and Hessian above but more parameters are made available for setting, a few bugs fixed etc. It’s suitable for extracting features for recognition in terms of feature number and type.|
|SURF detector||10-7-2007||Speeded Up Robust Features – fast implementation of SIFT using integral images.|
|FAST corner detector||10-7-2007||Features from Accelerate|