Novel Convolution Kernels for Computer Vision and Shape Analysis based on Electromagnetism
This work addresses the need for general-purpose convolution kernels in computer vision and shape analysis, though it appears incremental as it builds on existing kernel methods with a new physics-based approach.
The paper tackled the problem of developing convolution kernels for computer vision by introducing novel kernels based on electromagnetic principles, and demonstrated their application for shape and stroke analysis with features like resolution independence and robustness to noise.
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