Improving Image Tracing with Convolutional Autoencoders by High-Pass Filter Preprocessing
Computer Vision and Pattern Recognition
2023-06-16 v1
Abstract
The process of transforming a raster image into a vector representation is known as image tracing. This study looks into several processing methods that include high-pass filtering, autoencoding, and vectorization to extract an abstract representation of an image. According to the findings, rebuilding an image with autoencoders, high-pass filtering it, and then vectorizing it can represent the image more abstractly while increasing the effectiveness of the vectorization process.
Cite
@article{arxiv.2306.09039,
title = {Improving Image Tracing with Convolutional Autoencoders by High-Pass Filter Preprocessing},
author = {Zineddine Bettouche and Andreas Fischer},
journal= {arXiv preprint arXiv:2306.09039},
year = {2023}
}