Convolutional Neural Network Architectures for Template Matching

Spurio, Federico (2022) Convolutional Neural Network Architectures for Template Matching. [Laurea magistrale], Università di Bologna, Corso di Studio in Artificial intelligence [LM-DM270]
Documenti full-text disponibili:
[img] Documento PDF (Thesis)
Disponibile con Licenza: Creative Commons: Attribuzione - Non commerciale - Non opere derivate 4.0 (CC BY-NC-ND 4.0)

Download (2MB)


The Neural Networks customized and tested in this thesis (WaldoNet, FlowNet and PatchNet) are a first exploration and approach to the Template Matching task. The possibilities of extension are therefore many and some are proposed below. During my thesis, I have analyzed the functioning of the classical algorithms and adapted with deep learning algorithms. The features extracted from both the template and the query images resemble the keypoints of the SIFT algorithm. Then, instead of similarity function or keypoints matching, WaldoNet and PatchNet use the convolutional layer to compare the features, while FlowNet uses the correlational layer. In addition, I have identified the major challenges of the Template Matching task (affine/non-affine transformations, intensity changes...) and solved them with a careful design of the dataset.

Tipologia del documento
Tesi di laurea (Laurea magistrale)
Autore della tesi
Spurio, Federico
Relatore della tesi
Correlatore della tesi
Corso di studio
Ordinamento Cds
Parole chiave
deep learning,machine learning,computer vision,template matching,neural network
Data di discussione della Tesi
6 Ottobre 2022

Altri metadati

Statistica sui download

Gestione del documento: Visualizza il documento