450 likes | 570 Views
Keypoints in Image Retrieval. Bram Platel Evgenya Balmashnova Luc Florack Bart ter Haar Romeny. Introduction. Question: can top-points be used for object-retrieval tasks?. Interest Points.
E N D
Keypointsin Image Retrieval Bram Platel Evgenya Balmashnova Luc Florack Bart ter Haar Romeny
Introduction • Question: can top-points be used for object-retrieval tasks?
Interest Points • The locations of particularly characteristic points are called the interest points or key points. • These interest points have to be as invariant as possible, but at the same time they have to carry a lot of distinctive information.
Why Interest Points in Scale Space? • Information in interest points is defined by their neighborhood. But how big should we choose this neighborhood? • Let’s take the corners of the mouth as interest points. • The red circles are the areas in which the information is gathered. • If we make the picture bigger, the size of the neighborhood is too small. • The neighborhood should scale with the image
Why Interest Points in Scale Space? • When the interest points are detected in scale space they do not only have spatial coordinates x and y, but also a scale . • This scale tells us how big the neighborhood should be.
Which Interest Points to Use? • Our interest points have to be detected in scale space. • They also have to… • …contain a lot of information • …be reproducible • …be stable • …be well understood
Maxima Saddles Critical Points L=0 Minimum Critical Points, Paths and Top-Points
Top-Points Det(H)=0 Maxima Saddles Critical Points L=0 Minimum Critical Points, Paths and Top-Points
Possible to calculate them for every Function of the Image L(x,y,) Original Gradient Magnitude Laplacian Det(H)
Detecting Critical Paths • Since for a critical path L=0 • Intersection of Level Surfaces Lx=0 with Ly=0 • Will give the critical paths.
Detecting Top-Points • Since for a top-point both L=0 and Det[H]=Lxx Lyy-Lxy2=0 • We can find them by intersecting the paths with the level surface Det[H]=0
Allowed Trans. Invariance of Top Points • Top-points are invariant to certain transformations. • By invariant we mean that they move according to the transformation.
Reconstruction • It is possible to make a reconstruction of the original image from its top-points. • We can generate reconstructed images which give the same (plus more) top-points as the original image. • This reconstruction resembles the original image.
Original Image Reconstruction Top-Points and Features
Metameric Class Original By adjusting boundary and smoothness constraints we can improve the visual performance. For this 300x300 picture 1000 top-points with 6 features were used.
y x Localization of Top-Points • For points close to top-points it is possible to calculate a vector pointing towards the position of the top-point. Approximated Top-Points Displacement Vectors Real Locations
Localization of Top-Points • For points close to top-points it is possible to calculate a vector pointing towards the position of the top-point. • This enables us to use fast top-point detection algorithms which do not have to be very accurate.
Stability of Top-Points • The locations of top-points change when noise is added to the image.
Stability of Top-Points • We can calculate the variance of the displacement of top- points under noise. • We need 4th order derivatives in the top-points for that.
Stable Paths Unstable Paths Thresholding on Stability
1 2 3 4 5 8 7 9 6 Database Query Image Database Image Retrieval
Experiments • A simple image retrieval task. • Using a small version of the Olivetti Faces Database. • Consisting of 200 images of 20 different people (10 p.p.)
Scale y x The Deep Structure of an Image Look at all scales simultaneously
Top Points Det(H)=0 Maxima Saddles Critical Points u=0 Minimum Critical Points, Paths and Top Points
Comparing Top Points of Images Compare EMD
A B wi fij cij uj Earth Movers Distance (EMD) Piles Holes [*]Rubner, Tomasi, Guibas, 1998, IEEE Conf. on Computer Vision
Results • Using Euclidean Distance • Using Eberly Distance • As b. including stability norm • As c. including 2nd order derivatives.
Distinctive Features • To distinguish top-points from each other a set of distinctive features are needed in every top-point. • These local features describe the neighborhood of the top-point.
Differential Invariants • We use the complete set of irreducible 3rd order differential invariants. • These features are rotation and scaling invariant.
The top-points and differential invariants are calculated for the query object and the scene.
compare • We now compare the differential invariant features. distance = 0.5 distance = 0.2 distance = 0.3
smallest distance distance = 0.2 The vectors with the smallest distance are paired.
A set of coordinates is formed from the differences in scale (Log(o1)- Log(s2)) and in angles (o1- s2). (1, 1)
Important Clusters Clustering (,) Dq • If these coordinates are plotted in a scatter plot clusters can be identified. • In this scatter plot we find two dense clusters For these clusters we calculate the mean and
The translations we find correspond to the location of the objects in the scene.
C2 C1 In this example we have two clusters of correctly matched points.
We can transform the outline of the query object and project it on the scene image.
Conclusion • Top-points have proved to be invariant interest points which are useful for matching. • The differential invariants have shown to be very distinctive. • Experiments show good results.