2. • SIFT is an algorithm in computer vision to detect and
describe local features in images.
• Feature description is obtained by extracting interesting
points on the object in a training image. This description
is used to identify the object in an image containing many
other objects.
• The relative positions between these features in the
original scene shouldn't change from one image to
another. For example, if only the four corners of a door
were used as features, they would work regardless of the
door's position; but if points in the frame were also
used, the recognition would fail if the door is opened or
closed.
3.
4. • Scale Invariance
• Rotation Invariance
• Illumination Invariance
• Viewpoint Invariance (Mostly)
• Computationally Expensive
• Variant to Light Color Changes
• Variant to non-uniform Illumination (i.e. Shadows)
5. • The performance evolution of different local descriptors and their
comparison with SIFT are summarized below:
• SIFT and SIFT-like GLOH features exhibit the highest
matching accuracies 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 (Gradient Location and Orientation
Histogram) and SIFT features give the highest values.
6. • SIFT-based descriptors outperform other contemporary
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 contemporary 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.
7. • SURF (Speeded Up Robust Features) is a robust local
feature detector. It has shown to have similar
performance to SIFT, while at the same time being much
faster.
• The standard version of SURF is several times faster
than SIFT and claimed by its authors to be more robust
against different image transformations than SIFT. SURF
is based on sums of 2D Haar wavelet responses and
makes an efficient use of integral images.
• It uses an integer approximation to the determinant of
Hessian blob detector, which can be computed extremely
quickly with an integral image. For features, it uses the
sum of the Haar wavelet response around the point of
interest. Again, these can be computed with the aid of the
integral image.
8. • LESH is a recently proposed image descriptor which can
be used to get a description of the underlying shape.
• The LESH feature descriptor is built on local energy
model of feature perception.
• It is designed to be scale invariant.
• It encodes the underlying shape by accumulating local
energy of the underlying signal along several filter
orientations, several local histograms from different parts
of the image/patch are generated and concatenated
together into a 128-dimensional compact spatial
histogram.
• The LESH features can be used in applications like
shape-based image retrieval, object detection, and pose
estimation.
9. • GLOH is a robust image descriptor that can be used in
computer vision tasks.
• It is a SIFT-like descriptor that considers more spatial
regions for the histograms.
• The higher dimensionality of the descriptor is reduced to
64 through principal components analysis (PCA).