Novel Convolution Kernels for Computer Vision and Shape Analysis based on Electromagnetism

06/20/2018
by   Dominique Beaini, et al.
0

Computer vision is a growing field with a lot of new applications in automation and robotics, since it allows the analysis of images and shapes for the generation of numerical or analytical information. One of the most used method of information extraction is image filtering through convolution kernels, with each kernel specialized for specific applications. The objective of this paper is to present a novel convolution kernels, based on principles of electromagnetic potentials and fields, for a general use in computer vision and to demonstrate its usage for shape and stroke analysis. Such filtering possesses unique geometrical properties that can be interpreted using well understood physics theorems. Therefore, this paper focuses on the development of the electromagnetic kernels and on their application on images for shape and stroke analysis. It also presents several interesting features of electromagnetic kernels, such as resolution, size and orientation independence, robustness to noise and deformation, long distance stroke interaction and ability to work with 3D images

READ FULL TEXT

page 10

page 11

page 12

page 14

page 15

page 18

page 20

page 23

research
09/12/2023

Padding-free Convolution based on Preservation of Differential Characteristics of Kernels

Convolution is a fundamental operation in image processing and machine l...
research
04/18/2020

Adaptive Attention Span in Computer Vision

Recent developments in Transformers for language modeling have opened ne...
research
11/30/2022

Pattern Attention Transformer with Doughnut Kernel

We present in this paper a new architecture, the Pattern Attention Trans...
research
12/25/2020

Kernel-Independent Sum-of-Exponentials with Application to Convolution Quadrature

We propose an accurate algorithm for a novel sum-of-exponentials (SOE) a...
research
06/05/2018

Deep Gaussian Processes with Convolutional Kernels

Deep Gaussian processes (DGPs) provide a Bayesian non-parametric alterna...
research
08/20/2021

Single Image Defocus Deblurring Using Kernel-Sharing Parallel Atrous Convolutions

This paper proposes a novel deep learning approach for single image defo...
research
03/01/2022

Beam-Shape Effects and Noise Removal from THz Time-Domain Images in Reflection Geometry in the 0.25-6 THz Range

The increasing need of restoring high-resolution Hyper-Spectral (HS) ima...

Please sign up or login with your details

Forgot password? Click here to reset