Institutional Repository of Vilnius University
Dirbtinių neuroninių tinklų taikymas automobilio kėbulo švaros analizei /
Abstract
dc:descriptionThe bachelor‘s thesis aims to analyze and classify cleanliness of automobile‘s body and size to optimize the process of automatic tunnel car wash. Theoretical material discussed in the thesis: artificial neural networks, machine learning, convolution, convolutional neural networks, transfer learning, learning strategies, CRISP DM model application to machine learning projects and comparison of models VGG16, InceptionV3, Xception. To achieve the goal of the thesis, 2 tasks are solved: automobile‘s body cleanliness classification to 3 classes and automobile‘s body type classification to 6 classes. Achieved results are 89% accuracy classifying body cleanliness and 80% accuracy classifying body type.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Dirmeikis, Tautvydas,
- Contributors dc:contributor
-
- Raudys, Aistis
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD107116312&prefLang=en_US