This is a modified version of Hessian-Affine detector proposed by Krystian Mikolajczyk. The initial scale selection is based on scale-space extrema of the Hessian operator. As it was shown by Lindeberg, Hessian operator has similar scale-selection properties as Laplace operator, thus with the Hessian we can simultaneously localize both position and scale of scale-space extrema (unlike in the Hessian-Laplace version proposed by Mikolajczyk). The affine adaptation procedure (also known as Baumberg iteration) is then applied on the scale covariant "Hessian-Hessian" points. The gravity vector assumption is used to fix the rotation uncertainty. Then, SIFT descriptors are computed on the affine normalized patches with measurement region of radius r = 3*sqrt{3}*s, where s is the scale of the point.

haff_cvpr09 image_name.ppm

The binary rewrites output file: `image_name.ppm.hesaff.sift`

.

The output format is compatible with the binaries available from the page "Affine Covariant Features". The geometry of an affine region is specified by:
`u,v,a,b,c`

in `a(x-u)(x-u)+2b(x-u)(y-v)+c(y-v)(y-v)=1`

. The top left corner of the image is at `(u,v)=(0,0)`

. The geometry of an affine region is followed by N descriptor values (N = 128).

N

m

u_{1 }v_{1 }a_{1 }b_{1} c_{1} d_{1,1}d_{1,2} d_{1,3 }... d_{1,N}

:

:

u_{m }v_{m }a_{m }b_{m} c_{m} d_{m,1}d_{m,2} d_{m,3 }... d_{m,N}

- Perdoch, M. and Chum, O. and Matas, J.: Efficient Representation of Local Geometry for Large Scale Object Retrieval. In proceedings of CVPR09. June 2009.[talk][bib]
- Perdoch M.: Maximally Stable Extremal Regions and Local Geometry for Visual Correspondences. PhD thesis.

- Current open sourced version at github.
- Version of the detector used in CVPR09 paper, AMD64, Linux binary only..