• Home
  1. Home
  2. Towards the machine learning based image processing
Master
English

Towards the machine learning based image processing

Contributors

Taran, Olga

Directors

Voloshynovskyy, Svyatoslav

Defense date

2016

Abstract

The goal of this Thesis is to investigate the mathematical tools and theoretical aspects of the most representative and efficient algorithms in each class of image denoising methods. Basing ourselves on the discovered common features and underlying assumptions we establish a systematisation of modern state-of-the-art algorithms. For each class of algorithms in the Thesis we identify its weaknesses and theoretical limits. The most efficient algorithms have been studied from the point of view of opportunities to serve as a basis for building an universal algorithm for solving the majority of the problems in image processing. In conclusion, in this Thesis, we define the most perspective algorithms for future development, generalisation and extension to image compression, inpainting and restoration.

Keywords

  • Denoising
  • Local self-similarity
  • Patch processing techniques
  • Sparsity

UNIGE affiliation entities

UNIGE research groups

Citation (ISO format)

TARAN, Olga. Towards the machine learning based image processing. Master, 2016.

Main files (1)

Master thesis

Identifiers

  • PID : unige:87770
132views
17downloads

Technical informations

Creation

26/09/2016 10:27:00

First validation

26/09/2016 10:27:00

Update

15/03/2023 00:46:26

Status update

15/03/2023 00:46:26

Last indexation

31/10/2024 04:36:15
All rights reserved by Archive ouverte UNIGE and the University of Geneva
OpenAIRE Indexed & Validated