Affine-adapted Interest Point Operators
The interest points obtained from the multi-scale Harris operator with automatic scale selection are invariant to translations, rotations and uniform rescalings in the spatial domain. The images that constitute the input to a computer vision system are, however, also subject to perspective distortions. To obtain an interest point operator that is more robust to perspective transformations, a natural approach is to devise a feature detector that is invariant to affine transformations. In practice, affine invariant interest points can be obtained by applying affine shape adaptation where the shape of the smoothing kernel is iteratively warped to match the local image structure around the interest point or equivalently a local image patch is iteratively warped while the shape of the smoothing kernel remains rotationally symmetric. Hence, besides the commonly used multi-scale Harris operator, affine shape adaptation can be applied to other corner detectors as listed in this article as well as to differential blob detectors such as the Laplacian/Difference of Gaussian operator, the determinant of the Hessian and the Hessian-Laplace operator.
Read more about this topic: Corner Detection
Famous quotes containing the words interest and/or point:
“Treading the soil of the moon, palpating its pebbles, tasting the panic and splendor of the event, feeling in the pit of one’s stomach the separation from terra ... these form the most romantic sensation an explorer has ever known ... this is the only thing I can say about the matter. The utilitarian results do not interest me.”
—Vladimir Nabokov (1899–1977)
“All Coolidge had to do in 1924 was to keep his mean trap shut, to be elected. All Harding had to do in 1920 was repeat “Avoid foreign entanglements.” All Hoover had to do in 1928 was to endorse Coolidge. All Roosevelt had to do in 1932 was to point to Hoover.”
—Robert E. Sherwood (1896–1955)