Shape classification using simplification and tangent function
CSECS'09 Proceedings of the 8th WSEAS International Conference on Circuits, systems, electronics, control & signal processing
Invariant pattern recognition using the RFM descriptor
Pattern Recognition
The generalization of the R-transform for invariant pattern representation
Pattern Recognition
Pollen grains contour analysis on verification approach
HAIS'12 Proceedings of the 7th international conference on Hybrid Artificial Intelligent Systems - Volume Part I
Object recognition using radon transform-based RST parameter estimation
ACIVS'12 Proceedings of the 14th international conference on Advanced Concepts for Intelligent Vision Systems
Hi-index | 0.00 |
This paper proposes a novel feature-based invariant descriptor termed Radon composite features (RCFs) for planar shapes. Instead of analyzing shapes directly in the spatial domain, some shape features are extracted from the Radon transform plane using statistical and spectral analysis. The proposed method overcomes the drawbacks of existing shape representation techniques since it accomplishes the invariances to common geometrical transformations without any normalization process, which usually causes inaccuracies. A novel hierarchical strategy with RCFs can achieve low complexity and coarse-to-fine retrieval, and perform accurately when retrieving shapes, while remaining robust against variations. Experiments demonstrate that RCF provides a higher degree of discrimination as compared with several state-of-the-art approaches.