Генерування зображень номерних знаків методами глибинного навчання

Loading...
Thumbnail Image
Date
2023
Authors
Марчук, Владислав
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The main objective of this thesis is to develop a software application that utilizes the method of unpaired image-to-image translation for generating Ukrainian license plate images. To achieve this objective, the following research questions will be addressed: How can the method of unpaired image-to-image translation be adapted for generating Ukrainian license plates? What deep learning architecture and training procedure should be employed to achieve high-quality and realistic license plate generation? How does the generated output compare to real Ukrainian license plates in terms of visual quality and similarity? What are the limitations and potential challenges of the proposed approach?
Description
Keywords
GAN-based methods, Conditional GAN (CGAN), AC-GAN, bi-Lipschitz mapping, Alzheimer's disease, master thesis
Citation