Search Results for author:
Found 17 papers, 6 papers with code
Universal Collection of Euclidean Invariants between Pairs of Position-Orientations
To perform equivariant convolutional-like operations in these architectures one needs Euclidean invariant kernels on M(3) x M(3).
Orientation Scores should be a Piece of Cake
We axiomatically derive a family of wavelets for an orientation score, lifting from position space $\mathbb{R}^2$ to position and orientation space $\mathbb{R}^2\times S^1$, with fast reconstruction property, that minimise position-orientation uncertainty.
Segmentation tool for images of cracks
Machine learning algorithms can be used for augmenting the capability of classical visual inspection of bridge structures, however, the implementation of such an algorithm requires a massive annotated training dataset, which is time-consuming to produce.
Deep Learning for Segmentation of Cracks in High-Resolution Images of Steel Bridges
First, we present a novel and challenging dataset comprising of images of cracks in steel bridges.
PDE-CNNs: Axiomatic Derivations and Applications
From a machine learning perspective, we list several practically desirable axioms and derive from these which PDEs should be used in a PDE-CNN, this being our main contribution.
Optimal Transport on the Lie Group of Roto-translations
We develop a Sinkhorn like algorithm that can be efficiently implemented using fast and accurate distance approximations of the Lie group and GPU-friendly group convolutions.
Analysis of (sub-)Riemannian PDE-G-CNNs
Typically, G-CNNs have the advantage over CNNs that they do not waste network capacity on training symmetries that should have been hard-coded in the network.
Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis
This study is focused on histopathology image analysis applications for which it is desirable that the arbitrary global orientation information of the imaged tissues is not captured by the machine learning models.
Ranked #5 on
Breast Tumour Classification
on PCam
PDE-based Group Equivariant Convolutional Neural Networks
We solve the PDE of interest by a combination of linear group convolutions and non-linear morphological group convolutions with analytic kernel approximations that we underpin with formal theorems.
Lesion Segmentation in Ultrasound Using Semi-pixel-wise Cycle Generative Adversarial Nets
The method takes the advantage of a fully convolutional neural network (FCN) and a generative adversarial net to segment a lesion by using prior knowledge.
Roto-Translation Covariant Convolutional Networks for Medical Image Analysis
We propose a framework for rotation and translation covariant deep learning using $SE(2)$ group convolutions.
Retrieving challenging vessel connections in retinal images by line co-occurrence statistics
We propose to find line co-occurrence statistics from the centerlines of blood vessels in retinal images and show its remarkable similarity to a well-known probabilistic model for the connectivity pattern in the primary visual cortex.
Template Matching via Densities on the Roto-Translation Group
We propose a template matching method for the detection of 2D image objects that are characterized by orientation patterns.
Invertible Orientation Scores of 3D Images
The enhancement and detection of elongated structures in noisy image data is relevant for many biomedical applications.
Numerical Approaches for Linear Left-invariant Diffusions on SE(2), their Comparison to Exact Solutions, and their Applications in Retinal Imaging
We also provide an improvement of Mathematica algorithms for evaluating Mathieu-functions, crucial in implementations of the exact solutions.
Vesselness via Multiple Scale Orientation Scores
The multi-scale Frangi vesselness filter is an established tool in (retinal) vascular imaging.
A Multi-Orientation Analysis Approach to Retinal Vessel Tracking
This paper presents a method for retinal vasculature extraction based on biologically inspired multi-orientation analysis.
