Abstract
Image deformations due to relative motion between an observer and an object may be used to infer 3-D structure. Up to the first order, these deformations can be written in terms of an affine transform. A novel approach is adopted to measuring affine transforms which correctly handles the problem of corresponding deformed patches. The patches are filtered using Gaussians and derivatives of Gaussians and the filters deformed according to the affine transform. The problem of finding the affine transform is therefore reduced to that of finding the appropriate deformed filter to use. In the special case where the affine transform can be written as a scale change and an in-plane rotation, the Gaussian and first derivative equations are solved for the scale. The robustness of the method is demonstrated experimentally.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Keywords
Affine transformationAffine coordinate systemAffine geometry of curvesAffine shape adaptationAffine plane (incidence geometry)Harris affine region detectorAffine combinationRotation (mathematics)Robustness (evolution)Affine hullMathematicsScale (ratio)GaussianAffine geometryArtificial intelligenceComputer visionAlgorithmComputer scienceGeometryPlane (geometry)Affine spacePhysics
Affiliated Institutions
Related Publications
Probabilistic visual learning for object detection
We present an unsupervised technique for visual learning which is based on density estimation in high-dimensional spaces using an eigenspace decomposition. Two types of density ...
Symmetric phase-only matched filtering of Fourier-Mellin transforms for image registration and recognition
Presents a new method to match a 2D image to a translated, rotated and scaled reference image. The approach consists of two steps: the calculation of a Fourier-Mellin invariant ...
Principal warps: thin-plate splines and the decomposition of deformations
The decomposition of deformations by principal warps is demonstrated. The method is extended to deal with curving edges between landmarks. This formulation is related to other a...
Shiftable multiscale transforms
One of the major drawbacks of orthogonal wavelet transforms is their lack of translation invariance: the content of wavelet subbands is unstable under translations of the input ...
Affine invariant model-based object recognition
New techniques are described for model-based recognition of the objects in 3-D space. The recognition is performed from single gray-scale images taken from unknown viewpoints. T...
Publication Info
- Year
- 2002
- Type
- article
- Pages
- 754-755
- Citations
- 11
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
11
OpenAlex
Cite This
R. Manmatha,
J. Oliensis
(2002).
Extracting affine deformations from image patches. I. Finding scale and rotation.
, 754-755.
https://doi.org/10.1109/cvpr.1993.341158
Identifiers
- DOI
- 10.1109/cvpr.1993.341158