英语翻译The difficulty in object indexing is to determine the id

英语翻译
The difficulty in object indexing is to determine the identity of an object under arbitrary viewing conditions in the presence of cluttered real-world scenes or occlusions.Local characterization has shown to be well adapted to this problem.The small size of the characteristic regions makes them robust against occlusion and background changes.To obtain robustness to changes of viewing conditions they should also be invariant to image transformations.Recent methods for indexing differ in the type of invariants used.Rotation invariants have been presented by [10],rotation and scale invariants by and affine invariants by.
Schmid and Mohr [10] extract a set of interest points and characterize each of the points by rotationally invariant descriptors which are combinations of Gaussian derivatives.Robustness to scale changes is obtained by computing Gaussian derivatives at several scales.Lowe extends
these ideas to scale invariance by maximizing the output of difference-of-Gaussian filters in scale-space.Tuytelaars et al.[13] have developed affine invariant descriptors by searching for affine invariant regions and describing them by color invariants.To find these regions they simultaneously use interest points and contours.Instead of using an initial set of features,Chomat et al.select the appropriate scale for every point in the image and compute descriptors at these scales.An object is represented by the set of these descriptors.All of the above methods are limited to a scale factorof2.