Thesis Details

Generativní neuronové sítě pro ručně psané písmo

Master's Thesis Student: Ševčík Pavel Academic Year: 2021/2022 Supervisor: Hradiš Michal, Ing., Ph.D.
English title
Generative Neural Networks for Handwritten Text
Language
Czech
Abstract

The aim of this study was to create a generative neural network for handwritten text lines. The model produces variable-sized images of handwritten text lines based on the expected style. The proposed method exceeds existing models in the image quality and can be used to generate both individual words and entire lines of handwritten text. It combines the use of the attention mechanism to extract the features for each character from the text query and their arranging on the line by inserting spaces between them. The new approach allows more granular control of the symbol positions on the line, which leads to smoother style interpolations. In contrast to the previous approach, the proposed method uses the Gaussian filter to spread the individual symbols features to the surrounding area. This approach also allows to train the model for symbols position predictions using the adversarial loss (GAN). In addition, annotations of symbol horizontal positions on the lines of the IAM dataset of handwritten text have been created.

Keywords

Generating training data, handwritten text, generative neural networks, GAN, AdaIN, Transformer

Department
Degree Programme
Files
Status
defended, grade A
Date
21 June 2022
Reviewer
Committee
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT), předseda
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Češka Milan, doc. RNDr., Ph.D. (DITS FIT BUT), člen
Hradiš Michal, Ing., Ph.D. (DCGM FIT BUT), člen
Rozman Jaroslav, Ing., Ph.D. (DITS FIT BUT), člen
Zbořil František V., doc. Ing., CSc. (DITS FIT BUT), člen
Citation
ŠEVČÍK, Pavel. Generativní neuronové sítě pro ručně psané písmo. Brno, 2022. Master's Thesis. Brno University of Technology, Faculty of Information Technology. 2022-06-21. Supervised by Hradiš Michal. Available from: https://www.fit.vut.cz/study/thesis/24871/
BibTeX
@mastersthesis{FITMT24871,
    author = "Pavel \v{S}ev\v{c}\'{i}k",
    type = "Master's thesis",
    title = "Generativn\'{i} neuronov\'{e} s\'{i}t\v{e} pro ru\v{c}n\v{e} psan\'{e} p\'{i}smo",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2022,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/24871/"
}
Back to top