<  Back to the Polytechnique Montréal portal

Novel convolution kernels for computer vision and shape analysis based on electromagnetism

Dominique Beaini, Sofiane Achiche, Yann-Seing Law-Kam Cio and Maxime Raison

Report (2018)

[img]
Preview
Terms of Use: Creative Commons Attribution Non-commercial No Derivatives.
Download (1MB)
Cite this document: Beaini, D., Achiche, S., Law-Kam Cio, Y.-S. & Raison, M. (2018). Novel convolution kernels for computer vision and shape analysis based on electromagnetism (Report).
Show abstract Hide abstract

Abstract

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.

Uncontrolled Keywords

Shape analysis; Stroke analysis; Computer vision; Electromagnetic potential field; Feature extraction; Image filtering; Image convolution

Open Access document in PolyPublie
Subjects: 2100 Génie mécanique > 2100 Génie mécanique
2600 Robotique > 2603 Vision artificielle
2700 Technologie de l'information > 2700 Technologie de l'information
2700 Technologie de l'information > 2708 Traitement d'images et traitement vidéo
Department: Département de génie mécanique
Research Center: Non applicable
Funders: CRSNG/NSERC, FRQNT/INTER, MEDITIS
Date Deposited: 20 Jun 2018 15:34
Last Modified: 24 Oct 2018 16:13
PolyPublie URL: https://publications.polymtl.ca/3162/

Statistics

Total downloads

Downloads per month in the last year

Origin of downloads

Repository Staff Only