Back to Search
Start Over
Combined Invariants to Gaussian Blur and Affine Transformation
- Source :
- ICPR
- Publication Year :
- 2021
- Publisher :
- IEEE, 2021.
-
Abstract
- The paper presents a new theory of combined moment invariants to Gaussian blur and spatial affine transformation. The blur kernel may be arbitrary oriented, scaled and elongated. No prior information about the kernel parameters and about the underlaying affine transform is required. The main idea, expressed by the Substitution Theorem, is to substitute pure blur invariants into traditional affine moment invariants. Potential applications of the new descriptors are in blur-invariant image recognition and in robust template matching.
- Subjects :
- Computer science
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Gaussian blur
02 engineering and technology
01 natural sciences
Strain
symbols.namesake
Image resolution
Pattern recognition
0103 physical sciences
0202 electrical engineering, electronic engineering, information engineering
010306 general physics
business.industry
Template matching
Substitution (logic)
Image recognition
Fourier transforms
Moment (mathematics)
Kernel
Fourier transform
Kernel (image processing)
Computer Science::Computer Vision and Pattern Recognition
Pattern recognition (psychology)
symbols
020201 artificial intelligence & image processing
Artificial intelligence
Affine transformation
business
Algorithm
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2020 25th International Conference on Pattern Recognition (ICPR)
- Accession number :
- edsair.doi.dedup.....6fe41222a440aefc7c08a3388a20b6db