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:
“We teach boys to be such men as we are. We do not teach them to aspire to be all they can. We do not give them a training as if we believed in their noble nature. We scarce educate their bodies. We do not train the eye and the hand. We exercise their understandings to the apprehension and comparison of some facts, to a skill in numbers, in words; we aim to make accountants, attorneys, engineers; but not to make able, earnest, great- hearted men.”
—Ralph Waldo Emerson (1803–1882)
“Intolerance respecting other people’s religion is toleration itself in comparison with intolerance respecting other people’s art.”
—Wallace Stevens (1879–1955)
“Art is the child of Nature; yes,
Her darling child, in whom we trace
The features of the mother’s face,
Her aspect and her attitude.”
—Henry Wadsworth Longfellow (1807–1882)
“Hey, you dress up our town very nicely. You don’t look out the Chamber of Commerce is going to list you in their publicity with the local attractions.”
—Robert M. Fresco, and Jack Arnold. Dr. Matt Hastings (John Agar)