Multi-template matching: a versatile tool for object-localization in microscopy images
LSV Thomas, J Gehrig - BMC bioinformatics, 2020 - Springer
Background The localization of objects of interest is a key initial step in most image analysis
workflows. For biomedical image data, classical image-segmentation methods like …
workflows. For biomedical image data, classical image-segmentation methods like …
Local rotation invariance in 3D CNNs
Abstract Locally Rotation Invariant (LRI) image analysis was shown to be fundamental in
many applications and in particular in medical imaging where local structures of tissues …
many applications and in particular in medical imaging where local structures of tissues …
Exploring local rotation invariance in 3D CNNs with steerable filters
Abstract Locally Rotation Invariant (LRI) image analysis was shown to be fundamental in
many applications and in particular in medical imaging where local structures of tissues …
many applications and in particular in medical imaging where local structures of tissues …
Tensorial template matching for fast cross-correlation with rotations and its application for tomography
A Martinez-Sanchez, U Homberg, JM Almira… - … on Computer Vision, 2024 - Springer
Object detection is a main task in computer vision. Template matching is the reference
method for detecting objects with arbitrary templates. However, template matching …
method for detecting objects with arbitrary templates. However, template matching …
Fast normalized cross-correlation for template matching with rotations
JM Almira, H Phelippeau… - Journal of Applied …, 2024 - Springer
Normalized cross-correlation is the reference approach to carry out template matching on
images. When it is computed in Fourier space, it can handle efficiently template translations …
images. When it is computed in Fourier space, it can handle efficiently template translations …
Robust multi-organ nucleus segmentation using a locally rotation invariant bispectral U-Net
Abstract Locally Rotation Invariant (LRI) operators have shown great potential to robustly
identify biomedical textures where discriminative patterns appear at random positions and …
identify biomedical textures where discriminative patterns appear at random positions and …
Steer'n'Detect: fast 2D template detection with accurate orientation estimation
Motivation Rotated template matching is an efficient and versatile algorithm to analyze
microscopy images, as it automates the detection of stereotypical structures, such as …
microscopy images, as it automates the detection of stereotypical structures, such as …
A Bispectral 3D U-Net for Rotation Robustness in Medical Segmentation
Segmentation models achieved expert-level performance in a large variety of medical
applications. However, their robustness to rotations is rarely discussed and can be crucial …
applications. However, their robustness to rotations is rarely discussed and can be crucial …
[PDF][PDF] Fast normalized cross-correlation for template matching with rotations
JM Almira Picazo, H Phelippeau, A Martínez-Sánchez - 2024 - digitum.um.es
Normalized cross-correlation is the reference approach to carry out template matching on
images. When it is computed in Fourier space, it can handle efficiently template translations …
images. When it is computed in Fourier space, it can handle efficiently template translations …
On the realization and analysis of circular harmonic transforms for feature detection
HL Kennedy - Journal of Real-Time Image Processing, 2021 - Springer
Circular-harmonic spectra are a compact representation of local image features in two
dimensions. It is well known that the computational complexity of such transforms is greatly …
dimensions. It is well known that the computational complexity of such transforms is greatly …