English

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.

Keywords

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}
}
R2 v1 2026-06-28T11:05:49.864Z