Title: Sharif University of Technology A modified algorithm to obtain Translation, Rotation
1Sharif University of TechnologyA modified
algorithm to obtain Translation, Rotation
Scaleinvariant Zernike Moment shape Descriptors
- G.R. Amayeh
- Dr. S. Kasaei
- A.R. Tavakkoli
2Introduction
- Shape is one of the most important features to
human for visual distinguishing system. - Shape Descriptors
- Contour-Base
- Using contour information
- Neglect image details
- Region-Base
- Using region information
3Shape Descriptors
Fig.1 Same regions.
Fig.2 Same contours.
4Zernike Pseudo-Zernike Moments
- Zernike Moments of Order n, with m-repetition
- Zernike Moments Basis Function
(1)
(2)
(3)
5Zernike Pseudo-Zernike Moments
- Zernike Moment Radial Polynomials
- Pseudo-Zernike Radial Polynomials
(4)
(5)
6A Cross Section ofRadial Polynomials of ZM PsZM
Fig.3 ZM (blue) Ps. ZM (red) of 4-order with
repetition 0.
Fig.4 ZM (blue) Ps. ZM (red) of 6-order with
repetition 4.
Fig.5 ZM (blue) Ps. ZM (red) of 5-order with
repetition 1.
Fig.6 ZM (blue) Ps. ZM (red) of 7-order with
repetition 3.
73-D Illustration of Radial Polynomials of ZM
Ps.ZM
Fig.7 Radial polynomial of ZM of 7-order with
repetition 1.
Fig.8 Radial polynomial of Ps. ZM of 7-order
with repetition 1.
8Zernike Moments Properties
- Invariance Properties
- Zernike Moments are Rotation Invariant
- Rotation changes only moments phase.
- Variance Properties
- Zernike Moments are Sensitive to Translation
Scaling.
9Achieving Invariant Properties
- What is needed in segmentation problem?
- Moments need to be invariant to rotation, scale
and translation. - Solution to achieve invariant properties
- Normalization method.
- Improved Zernike Moments without Normalization
(IZM). - Proposed Method.
10Normalization Method
- Algorithm
- Translate images center of mass to origin.
- Scale image
11Normalization Method
Fig.9 From left to right, Original, Translated,
Scaled images (b1800).
12Normalization Method
Fig.10 From left to right, original image
normalized images with different b s.
13Normalization Method Drawbacks
- Interpolation Errors
- Down sampling image leads to loss of data.
- Up sampling image adds wrong information to
image.
14Improved Zernike Moments without Normalization
- Algorithm
- Translate images center of mass to origin.
- Finding the smallest surrounding circle and
computing ZMs for this circle. - Normalize moments
Fig.11 Images fitted circles.
(8)
15Drawbacks
- Increased Quantization Error.
- Since the SSC of images have a small number of
pixels, images resolution is low and this causes
more QE.
16Proposed Method
- Algorithm
- Computing a Grid Map.
- Performing translation and scale on the map
indexes.
Fig.12 Mapping.
17Proposed Method
- Translate origin of coordination system to the
center of mass
(9)
Fig(13). Translation of Coordination Origin.
18Proposed Method
- Scale coordination system
19Proposed Method
- Computing Zernike Moment in new coordinate
for where
. - We can show that the moments of in the
new coordinate system are equal to the moments of
in the old coordinate system.
20Proposed Method
b800
b1200 b1800
b2500
Fig.15 From left to right, original image
normalized images with different b s.
21Proposed Method
Fig.17 Zernike moments by proposed method
(b2550) IZM (Improved ZM with out
normalization ).
Fig.16 Original image.
22Experimental Results
Fig.16 Original image 70 scaled image.
Fig.17 Error of Zernike moments between
original image scaled image.
23Experimental Results
Fig.18 Original image 55 degree rotated image.
Fig.19 Error of Zernike moments between
original image rotated image.
24Experimental Results
Fig.21 Error of Zernike moments between
original scaled images.
Fig.20 Original image 120 scaled image.
25Experimental Results
Fig.23 Error of Zernike moments between
original image rotated image.
Fig.21 Original image 40 degree rotated image.
26Conclusions
- Principle of our method is same as the
Normalization method. - Does not resize the original image.
- No Interpolation Error.
- Reduces the quantization error. (using beta
parameter) - Trade off Between QE and power of distinguishing.
- Has all the benefits of both pervious methods.
27