Shape recognition with coarse-to-fine point correspondence under image deformations

Authors:
Huixuan Tang;Hui Wei
Affiliations:
Department of Computer Science, Lab of Algorithm for Cognitive Model, Intelligent Information Processing Laboratory, Fudan University, Shanghai, P.R. China;Department of Computer Science, Lab of Algorithm for Cognitive Model, Intelligent Information Processing Laboratory, Fudan University, Shanghai, P.R. China
Venue:
Proceedings of the 2005 joint Chinese-German conference on Cognitive systems
Year:
2005

Citing 18
Cited 0

The Curvature Primal Sketch

IEEE Transactions on Pattern Analysis and Machine Intelligence
HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects

IEEE Transactions on Pattern Analysis and Machine Intelligence
Mathematical elements for computer graphics (2nd ed.)

Mathematical elements for computer graphics (2nd ed.)
The use of maximum curvature points for the recognition of partially occluded objects

Pattern Recognition
Scale-Based Detection of Corners of Planar Curves

IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognizing general curved objects efficiently

Geometric invariance in computer vision
Local Invariants For Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Visual learning and recognition of 3-D objects from appearance

International Journal of Computer Vision
Computer Vision: A Modern Approach

Computer Vision: A Modern Approach
Modeling with Triangular B-Splines

IEEE Computer Graphics and Applications
Flexible Syntactic Matching of Curves and Its Application to Automatic Hierarchical Classification of Silhouettes

IEEE Transactions on Pattern Analysis and Machine Intelligence
What can be seen in three dimensions with an uncalibrated stereo rig

ECCV '92 Proceedings of the Second European Conference on Computer Vision
Matching of 3-D curves using semi-differential invariants

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization

Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization
Shape matching of partially occluded curves invariant under projective transformation

Computer Vision and Image Understanding
Image Processing, Analysis, and Machine Vision

Image Processing, Analysis, and Machine Vision
Wide-baseline multiple-view correspondences

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Invariant matching and identification of curves using B-splines curve representation

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Matching techniques are part-and-parcel of shape recognition. A coarse-to-fine method is presented which finds point correspondence between open or closed curves and is invariant to various image deformations, including affine transformation, perspective distortion, non-rigid motion and so forth. The method is inspired by the idea to use point correspondences established at one level to generate a priori information, which is either topological or geometric, to match features at finer levels. This has all been achieved through an analysis of the curve topology and a synthesis of the B-spline interpolation techniques. This is in contrast to existing multi-scale methods for curve matching that use pure feature correlation or 3D structure recovery at a fixed scale. The presented method proves to be robust and accurate and can serve as a powerful aid to measure similarity of shape, as demonstrated in various experiments on real images.