460 likes | 576 Views
Object Recognition by Implicit Invariants Jan Flusser Jaroslav Kautsky Filip Šroubek. Institute of Information Theory and Automation Prague, Czech Republic Flinders University of South Australia Adelaide, Australia. General m otiva tion.
E N D
Object Recognition by Implicit Invariants Jan Flusser Jaroslav Kautsky Filip Šroubek Institute of Information Theory and AutomationPrague, Czech RepublicFlinders University of South AustraliaAdelaide, Australia
General motivation How can we recognize deformed objects?
Problem formulation Curved surface deformation of the image g = D(f) D -unknown deformation operator
What are explicit invariants? Functionals defined on the image space L such that • E(f) = E(D(f))for all admissibleD • Fourier descriptors, moment invariants, ...
What are explicit invariants? Functionals defined on the image space L such that • E(f) = E(D(f))for all admissibleD • For many deformations explicit invariants do not exist.
What are implicit invariants? Functionals defined on L x L such that • I(f,D(f)) = 0for all admissibleD • Implicit invariants exist for much bigger set of deformations
Our assumption about D Image deformation is a polynomial transform r(x) of order > 1of the spatial coordinates f’(r(x)) = f(x)
What are moments? Moments are “projections” of the image function into a polynomial basis
How are the moments transformed? m’ = A.m • A depends on r and on the polynomial basis • A is not a square matrix • Transform r does not preserve the order of the moments • Explicit moment invariants cannot exist. If they existed, they would contain all moments.
Construction of implicit momentinvariants • Eliminate the parameters of r from the system • Each equation of the reduced system is an implicit invariant m’ = A.m
Object recognitionAmsterdam Library of Object Imageshttp://staff.science.uva.nl/˜aloi/
ALOI database 99% recognition rate
The bottle again 100% recognition rate
Implementation How to avoid numerical problems with high dynamic range of standard moments?
Implementation How to avoid numerical problems with high dynamic range of standard moments? We used orthogonal Czebyshev polynomials
Summary • We proposed a new concept of implicit invariants • We introduced implicit moment invariants to polynomial deformations of images
Any questions? Thank you !
Common types of moments Geometric moments
Special case If an explicit invariant exist, then I(f,g) = |E(f) – E(g)|
Orthogonal moments • Legendre • Zernike • Fourier-Mellin • Czebyshev • Krawtchuk, Hahn
Outlook for the futureand open problems • Discriminability? • Robustness? • Other transforms?
Basic approaches Základní přístupy Brute force Normalized position inverse problem Description of the objects by invariants
Our assumption about D Image degradation is a polynomial transform r(x) of the spatial coordinates of order > 1
Construction of implicit momentinvariants • Eliminate the parameters of r from the system • Each equation of the reduced system is an implicit invariant
How are the moments transformed? • A depends on r and on the moment basis • A is not a square matrix • Transform r does not preserve the moment orders • Explicit moment invariants cannot exist. If they existed, they would contain all moments.