Documente Academic
Documente Profesional
Documente Cultură
Nick Kingsbury
Signal Processing and Communications Laboratory Department of Engineering, University of Cambridge, UK. email: ngk@eng.cam.ac.uk web: www.eng.cam.ac.uk/~ngk
1 / 30
Introduction
Dual-Tree CWT
Features of the Dual Tree Complex Wavelet Transform (DT CWT) Good shift invariance = negligible aliasing. Hence transfer function through each subband is independent of shift and wavelet coefs can be interpolated within each subband, independent of all other subbands. Good directional selectivity in 2-D, 3-D etc. derives from analyticity in 1-D (ability to separate positive from negative frequencies). Similarity to Primary (V1) Cortex lters of the human visual system. Perfect reconstruction with short support lters. Limited redundancy 2:1 in 1-D, 4:1 in 2-D etc. Low computation much less than the undecimated ( trous) DWT.
3 / 30
Dual-Tree CWT
Figure: Dual tree of real lters for the Q-shift CWT, giving real and imaginary parts of complex coefcients from tree a and tree b respectively.
Nick Kingsbury (Univ. of Cambridge) Dual-Tree Wavelets & Vision UDRC 2013 (2) 4 / 30
Dual-Tree CWT
Tree a Tree b
wavelet
1
|a + jb|
wavelet
3
wavelet
5
20
15
10
0 5 sample number
10
15
20
5 / 30
Dual-Tree CWT
8
UDRC 2013 (2) 6 / 30
DT CWT in 2-D
DT CWT in 2-D
0.6 0.4
10
10
20 10 5 0 5 10 15
30
dB
40
50
60 40 20 0 20 40 60
15
45
75
75
45
15(deg)
70
Level 4 Wavelets
80
Magnitude
0.4
0.3
0.2
Real
20 0
Imaginary
20 40 60
0.1
Real DWT
Time (samples)
e j 1 x . e j 2 y = e j (1 x +2 y )
90 45(?) 0
Figure: Basis functions of 2-D Q-shift complex wavelets (top), and of 2-D real wavelet lters (bottom), all illustrated at level 4 of the transforms. The complex wavelets provide 6 directionally selective lters, while real wavelets provide 3 lters, only two of which have a dominant direction. The 1-D bases, from which the 2-D complex bases are derived, are shown to the right.
Nick Kingsbury (Univ. of Cambridge) Dual-Tree Wavelets & Vision UDRC 2013 (2) 8 / 30
DT CWT in 2-D
Imaginary part
Real part
9 / 30
DT CWT in 2-D
Figure: Four-level DT CWT decomposition of Lenna into 6 subbands per level (only
the central 128 128 portion of the image is shown for clarity). A colour-wheel palette is used to display the complex wavelet coefcients.
Nick Kingsbury (Univ. of Cambridge) Dual-Tree Wavelets & Vision UDRC 2013 (2) 10 / 30
DT CWT in 2-D
DT CWT
DWT
wavelets: level 1
level 2
level 3
level 4
Figure: Wavelet and scaling function components at levels 1 to 4 of an image of a light circular disc on a dark background, using the 2-D DT CWT (upper row) and 2-D DWT (lower row). Only half of each wavelet image is shown in order to save space.
Nick Kingsbury (Univ. of Cambridge) Dual-Tree Wavelets & Vision UDRC 2013 (2) 11 / 30
Keypoint detection
|wk ,d (x)|
d =1 3 1 d =1 3 1 6
or
|wk ,d (x)|2
Interpolate and accumulate Ekp (k , x) across groups of relevant scales k to create the Accumulated Map. Pick keypoints as locations of maxima in the Accumulated Map.
Nick Kingsbury (Univ. of Cambridge) Dual-Tree Wavelets & Vision UDRC 2013 (2) 12 / 30
Keypoint detection
13 / 30
Keypoint detection
14 / 30
4 4
16 / 30
Modication of 45 and 135 subband responses for improved rotational symmetry (shown at level 4).
(a) DualTree Complex Wavelets: Real Part
2
15 45 75 105 135 165
modified
original
0 2
1.5
1.5
(a) Original 2-D impulse responses; (b) 2-D responses, modied to have lower centre frequencies (reduced by 1/ 1.8) in the 45 and 135 subbands, and even / odd symmetric real / imaginary parts; (c) Original and modied 1-D lters.
Imaginary Part
15
45
75
105
135
165
13-point circular pattern for sampling DT CWT coefs at each keypoint location
0.5
0.5
L K J 1 0.5 0 0.5 I
Bandpass interpolation calculates the required samples and can be performed on each subband independently because of the shift-invariance of the transform: 1. Shift by {1 , 2 } down to zero frequency (i.e. multiply by ej (1 x1 +2 x2 ) at each point {x1 , x2 }); 2. Lowpass interpolate to each new point (spline / bi-cubic / bi-linear); 3. Shift up by {1 , 2 } (multiply by e j (1 y1 +2 y2 ) at each new point {y1 , y2 }).
18 / 30
m1 m2 m3 m4 m5 m6 P= m1 m2 m 3 m 4 m5 m6
j1 i2 h3 g4 f5 e6 d1 c2 b3 a4 l5 k6
k1 j2 i3 h4 g5 f6 e1 d2 c3 b4 a5 l6
l1 k2 j3 i4 h5 g6 f1 e2 d3 c4 b5 a6
a1 l2 k3 j4 i5 h6 g1 f2 e3 d4 c5 b6
b1 a2 l3 k4 j5 i6 h1 g2 f3 e4 d5 c6
c1 b2 a3 l4 k5 j6 i1 h2 g3 f4 e5 d6
Column 1
8 9 10 11 12
6 5 4 3 2 10 11 12
7 6 5 4 11 12 1
10
8 7 6 5
Column 2
10
Column 3
11
Column 4
12
11 12 1 2 3
9 8 7 6 5 1 2 3
12
10 9 8 7 2 3 4
11 10 9 8
Column 5
Column 6
Column 7
Each column of P comprises a set of rotationally symmetric samples from the 6 subbands and their conjugates ( ), whose orientations are shown by the arrows and locations in the 13-point pattern by the letters. Numbers for each arrow give the row indices in P .
Nick Kingsbury (Univ. of Cambridge) Dual-Tree Wavelets & Vision UDRC 2013 (2) 19 / 30
Each set of curves shows the output of the normalised correlator for 48 angles in 7.5 increments, when the test image is rotated in 5 increments from 0 to 90 . Levels 4 and 5 of the DT CWT were used in an 8-column P matrix format. The diameter of the 13-point sampling pattern is half the width of the subimages shown.
Rotation (degrees)
1
Rotation (degrees)
Nick Kingsbury (Univ. of Cambridge) Dual-Tree Wavelets & Vision UDRC 2013 (2) 21 / 30
Rotation (degrees)
1
Rotation (degrees)
Nick Kingsbury (Univ. of Cambridge) Dual-Tree Wavelets & Vision UDRC 2013 (2) 22 / 30
23 / 30
12
8 2 4 6 8
16 4 8 12 16
Background images show magnitudes of DT CWT coefs for subband 1, oriented for edges at 15 above the horizontal.
Nick Kingsbury (Univ. of Cambridge) Dual-Tree Wavelets & Vision UDRC 2013 (2) 25 / 30
0 x
Left) No change of orientation; Right) Average over rotations from 0 to 90 in steps of 7.5 .
Nick Kingsbury (Univ. of Cambridge) Dual-Tree Wavelets & Vision UDRC 2013 (2) 26 / 30
0 x
1.1
1.2
1.3 Scale
1.4
1.5
Left) Average over dilations from 1.0 to 1.4, with respect to shift; Right) Mean correlation values with respect to scale change (dilation), no shift.
Nick Kingsbury (Univ. of Cambridge) Dual-Tree Wavelets & Vision UDRC 2013 (2) 27 / 30
Frequency
6000
4000
2000
0 0.2
0.8
The histograms demonstrate the increase in false positive detection rate when shift and scale tolerances are introduced.
Nick Kingsbury (Univ. of Cambridge) Dual-Tree Wavelets & Vision UDRC 2013 (2) 28 / 30
For colour keypoint detection, we add the wavelet energies from the DT CWT of each R, G and B component, so that we get the total wavelet response to any changes in RGB-space; and use this to form a single Accumulated Map. Alternatively we could do this in a perceptually more uniform space such as Lab. We perform contrast equalisation over local image regions to handle variations between lighted / shaded parts of the image and between images. For colour feature matching, we form 3 polar-matching matrices into a single matrix [PR PG PB ] and perform matching with this. Prior to matching, we normalise each composite P-matrix with a single scaling factor for all 3 colours, so that relative amplitudes of colour variations are maintained, despite lighting changes.
29 / 30
Conclusions
Conclusions
New local Keypoint Detectors and Feature Descriptors have been proposed for use when comparing the similarity of detected objects in images. They have the following properties:
They are based on a modied form of the efcient Dual-Tree Complex Wavelet Transform. The modications improve the rotational symmetry of the 6 directionally selective subbands at each scale. The 12-point circular sampling patterns and the Polar Matching Matrix P are dened such that arbitrary rotations of an object can be accomodated efciently in the matching process. Shift-tolerant and scale-tolerant extensions of the basic P -matrix method give greater robustness at the expense of some increase in false-positive rate. There is scope for applying non-linear pre-processing (e.g. magnitude compression and phase adjustment) to the complex wavelet coefcients prior to matching, to improve resilience to illumination and viewpoint changes.