Comparison of SIFT Features With Other Local Features
There has been an extensive study done on the performance evaluation of different local descriptors, including SIFT, using a range of detectors. The main results are summarized below:
- SIFT and SIFT-like GLOH features exhibit the highest matching accuracies (recall rates) for an affine transformation of 50 degrees. After this transformation limit, results start to become unreliable.
- Distinctiveness of descriptors is measured by summing the eigenvalues of the descriptors, obtained by the Principal components analysis of the descriptors normalized by their variance. This corresponds to the amount of variance captured by different descriptors, therefore, to their distinctiveness. PCA-SIFT (Principal Components Analysis applied to SIFT descriptors), GLOH and SIFT features give the highest values.
- SIFT-based descriptors outperform other local descriptors on both textured and structured scenes, with the difference in performance larger on the textured scene.
- For scale changes in the range 2-2.5 and image rotations in the range 30 to 45 degrees, SIFT and SIFT-based descriptors again outperform other local descriptors with both textured and structured scene content.
- Introduction of blur affects all local descriptors, especially those based on edges, like shape context, because edges disappear in the case of a strong blur. But GLOH, PCA-SIFT and SIFT still performed better than the others. This is also true for evaluation in the case of illumination changes.
The evaluations carried out suggests strongly that SIFT-based descriptors, which are region-based, are the most robust and distinctive, and are therefore best suited for feature matching. However, most recent feature descriptors such as SURF have not been evaluated in this study.
SURF has later been shown to have similar performance to SIFT, while at the same time being much faster.
Recently, a slight variation of the descriptor employing an irregular histogram grid has been proposed that significantly improves its performance. Instead of using a 4x4 grid of histogram bins, all bins extend to the center of the feature. This improves the descriptor's robustness to scale changes.
The Rank SIFT technique was shown to improve the performance of the standard SIFT descriptor for affine feature matching. A SIFT-Rank descriptor is generated from a standard SIFT descriptor, by setting each histogram bin to its rank in a sorted array of bins. The Euclidean distance between SIFT-Rank descriptors is invariant to arbitrary monotonic changes in histogram bin values, and is related to Spearman's rank correlation coefficient.
Read more about this topic: Scale-invariant Feature Transform
Famous quotes containing the words comparison of, comparison, features and/or local:
“When we reflect on our past sentiments and affections, our thought is a faithful mirror, and copies its objects truly; but the colours which it employs are faint and dull, in comparison of those in which our original perceptions were clothed.”
—David Hume (1711–1776)
“Envy and jealousy are the private parts of the human soul. Perhaps the comparison can be extended.”
—Friedrich Nietzsche (1844–1900)
“The features of our face are hardly more than gestures which force of habit made permanent. Nature, like the destruction of Pompeii, like the metamorphosis of a nymph into a tree, has arrested us in an accustomed movement.”
—Marcel Proust (1871–1922)
“Reporters for tabloid newspapers beat a path to the park entrance each summer when the national convention of nudists is held, but the cult’s requirement that visitors disrobe is an obstacle to complete coverage of nudist news. Local residents interested in the nudist movement but as yet unwilling to affiliate make observations from rowboats in Great Egg Harbor River.”
—For the State of New Jersey, U.S. public relief program (1935-1943)