Zpět na vyhledávání

Bc. Martin Galajda

Master's thesis

Detecting and Extracting Information from Images on the Web

Detecting and Extracting Information from Images on the Web
Abstract:
Nové pokroky v oblasti počítačového videnia boli úspešne aplikované na riešenie rozličných problémov. Táto práca sa zaoberá aplikáciou týchto nových techník na získavanie užitočných informácií z webu s cieľom vylepšíť cielenú reklamu. Práca obsahuje výskum na state-of-the-art techniky pre detekciu objektov, ktoré využivajú techniku hlbokého učenia. Vyskúmané techniky boli implementované a porovnané …more
Abstract:
New advancements in computer vision have been successfully applied to solve various problems. This thesis is concerned with applying new techniques to extract useful information from the images present on the web to support targeted advertising. The thesis contains research on state-of-the-art techniques for object detection, which leverage deep learning. The researched techniques are implemented and …more
 

Keywords

deep learning computer vision convolutional neural networks machine learning object detection image classification targeted advertising
 
Language used: English
Date on which the thesis was submitted / produced: 9. 12. 2019
Identifier: https://is.muni.cz/th/hhxco/

Thesis defence

  • Date of defence: 6. 2. 2020
  • Supervisor: doc. RNDr. Pavel Matula, Ph.D.
  • Reader: RNDr. Roman Stoklasa, Ph.D.

Citation record

Cite this text

Full text of thesis

Contents of on-line thesis archive
Published in Theses:
  • světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatiky
Složka Reference to the local database directory of the institution