Thesis Details

Fast Analysis of Borders in Image

Bachelor's Thesis Student: Kolesár Matej Academic Year: 2019/2020 Supervisor: Herout Adam, prof. Ing., Ph.D.
Czech title
Rychlá analýza hranic v obraze
Language
English
Abstract

This thesis focuses on the problem of detecting edges in natural images while maintaining high performance per image. First, the existing approaches are analysed and from them the relevant information is extracted. This information is then used to design two architectures that use convolutional neural networks. One architecture is based on RCF and enriches the output, while the other is a combination of RCF and RCN. This combination provides better up-sampling and enriches the output even more. Evaluation was performed on the BSDS500 dataset and the best result was for achieved for the model that combined RCF and RCN with an ODS score of 0.675.

Keywords

neural network, machine learning, convolution neural network, edge detection

Department
Degree Programme
Information Technology
Files
Status
defended, grade B
Date
8 July 2020
Reviewer
Committee
Čadík Martin, doc. Ing., Ph.D. (DCGM FIT BUT), předseda
Bařina David, Ing., Ph.D. (DCGM FIT BUT), člen
Burget Radek, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Jaroš Jiří, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Citation
KOLESÁR, Matej. Fast Analysis of Borders in Image. Brno, 2020. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2020-07-08. Supervised by Herout Adam. Available from: https://www.fit.vut.cz/study/thesis/19586/
BibTeX
@bachelorsthesis{FITBT19586,
    author = "Matej Koles\'{a}r",
    type = "Bachelor's thesis",
    title = "Fast Analysis of Borders in Image",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2020,
    location = "Brno, CZ",
    language = "english",
    url = "https://www.fit.vut.cz/study/thesis/19586/"
}
Back to top