Tensorial template matching for fast cross-correlation with rotations and its application for tomography
Not on the map. Why?
Abstract (arXiv)
Object detection is a main task in computer vision. Template matching is the reference method for detecting objects with arbitrary templates. However, template matching computational complexity depends on the rotation accuracy, being a limiting factor for large 3D images (tomograms). Here, we implement a new algorithm called tensorial template matching, based on a mathematical framework that represents all rotations of a template with a tensor field. Contrary to standard template matching, the computational complexity of the presented algorithm is independent of the rotation accuracy. Using both, synthetic and real data from tomography, we demonstrate that tensorial template matching is much faster than template matching and has the potential to improve its accuracy
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 9 of its 41 references that are in the map. First posted on arXiv 5 Aug 2024.
Builds on
9 of 41 references.
References · 9
- 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
- 2017Convolutional neural network architecture for geometric matchingcited by 138
- 2018Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographscited by 23
- 2023Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinementcited by 9
- 2022SHREC 2021: Classification in cryo-electron tomogramscited by 5
- 2023Fast Normalized Cross-Correlation for Template Matching with Rotationscited by 3
- 2018Principled Design and Implementation of Steerable Detectorscited by 2
- 2022Probabilistic bounds on best rank-one approximation ratiocited by 2
- 2022Complexity and computation for the spectral norm and nuclear norm of order three tensors with one fixed dimensioncited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.