Aligning non-exact copies of artworks with their original

Title

Aligning non-exact copies of artworks with their original

 Author

Quin, Tristan (TU Delft Electrical Engineering, Mathematics and Computer Science)

Contributor

Wiersma, R.T. (mentor) ORCID 0000-0001-7900-7253
Eisemann, E. (mentor) ORCID 0000-0003-4153-065X
Marroquim, Ricardo (mentor) ORCID 0000-0001-8299-7067
Lofi, C. (graduation committee) ORCID 0000-0001-5641-5510

 Degree granting institution

Delft University of Technology

 Programme

Computer Science and Engineering

 Project

CSE3000 Research Project

 Date

2022-06-23

 Abstract

This research investigates the efficacy and reliability of geometric matching for the specific case of aligning non-exact copies of artistic works with the original from which they were derived. The purpose of which is to provide a foundation for comparison in any further analysis conducted by conservators and art historians. An overview of the image alignment field as a whole is provided as well as a discussion of the particulars of aligning artworks. A variety of demonstrative results indicate the strengths and weaknesses of the technique in this domain and are accompanied by a discussion of the headline conclusions.

 Subject

Image registration
Image alignment
Artwork
Geometric transformation
Convolutional neural network
Semantic alignment

 To reference this document use:

http://resolver.tudelft.nl/uuid:44a96bc4-0066-4558-8182-9b4681caea32

 Part of collection

Student theses

 Document type

bachelor thesis

 Rights

© 2022 Tristan Quin
Files
PDF Aligning_non_exact_copies ... iginal.pdf 26.01 MB
Close viewer