"This site requires JavaScript to work correctly"
Header minimieren

Zineddine Bettouche, M.Sc

  • Angewandte Künstliche Intelligenz
  • Computer Vision
  • Automatisierungstechnik

Fakultät Angewandte Informatik

Wissenschaftliche Mitarbeiter:innen

Wissenschaftlicher Mitarbeiter

Sortierung:
Vortrag

  • Zineddine Bettouche

A Deeper Comprehension of Researcher Activity By Means of Transformers

In: Deggendorfer Wissenschaftliches Kolloquium

Technische Hochschule Deggendorf

  • 20.01.2023 (2023)
  • Angewandte Informatik
  • DIGITAL
Beitrag in Sammelwerk/Tagungsband

  • Andreas Fischer
  • Zineddine Bettouche

High-pass Filters Preprocessing in Image Tracing with Convolutional Autoencoders

pg. 7-12.

  • (2022)
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.
  • Angewandte Informatik
  • DIGITAL
Beitrag in Sammelwerk/Tagungsband

  • Zineddine Bettouche
  • Andreas Fischer

Mapping Researcher Activity based on Publication Data by means of Transformers

  • (2022)
  • Angewandte Informatik
  • DIGITAL
Zeitschriftenartikel

  • Zineddine Bettouche
  • Andreas Fischer

Improving Image Tracing with Convolutional Autoencoders by High-Pass Filter Preprocessing

In: International Journal on Advances in Software (IARIA Journals) vol. 15 pg. 141 - 151.

  • (2022)
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.
  • Angewandte Informatik
  • DIGITAL