Extension of Moment Features’ Invariance to Blur
| Autor: | Jiří Boldyš, Jan Flusser |
|---|---|
| Rok vydání: | 2008 |
| Předmět: |
Statistics and Probability
Image moment Discrete mathematics Applied Mathematics Substitution (logic) Condensed Matter Physics Invariant theory Moment (mathematics) Algebra Transformation (function) Modeling and Simulation Invariants of tensors Geometry and Topology Computer Vision and Pattern Recognition Algebraic number Tensor calculus Mathematics |
| Zdroj: | Journal of Mathematical Imaging and Vision. 32:227-238 |
| ISSN: | 1573-7683 0924-9907 |
| DOI: | 10.1007/s10851-008-0091-4 |
| Popis: | Moment invariants are features calculated on an image, which do not change their values after a transformation of the image. This paper focuses on the so called combined invariants, which obey additional requirement of invariance to image blurring. Our first contribution is a review of achievements most relevant to the derivation of algebraic, moment and combined invariants. The review explains and develops parallels between the moment and the blur invariants. Gradually, it reveals new properties, simplifying construction of the combined invariants, but having more general extent. Resulting substitution rules for easy construction of the combined invariants from other invariants are thus the main results of this paper. All the conclusions can be understood without knowledge of the tensor calculus. This paper addresses construction of the combined invariants in arbitrary dimension. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink