Home // COMPUTATION TOOLS 2022, The Thirteenth International Conference on Computational Logics, Algebras, Programming, Tools, and Benchmarking // View article

High-pass Filters Preprocessing in Image Tracing with Convolutional Autoencoders

Authors:
Andreas Fischer
Zineddine Bettouche

Keywords: image quality, vector graphics, neural networks, autoencoders, high-pass filters, vectorization, complexity theory, information technology

Abstract:
Image tracing describes the task of converting a raster image into a vector format. This paper investigates different processing pipelines that can extract an abstract representation of an image by means of high-pass filtering, autoencoding, and vectorization. Results indicate that reconstructing an image using Autoencoders, then filtering it with high-pass filters, and finally vectorizing it, can represent the image more abstractly while improving the efficiency of the vectorization process.

Pages: 7 to 12

Copyright: Copyright (c) The Government of Germany, 2022. Used by permission to IARIA.

Publication date: April 24, 2022

Published in: conference

ISSN: 2308-4170

ISBN: 978-1-61208-954-6

Location: Barcelona, Spain

Dates: from April 24, 2022 to April 28, 2022