Institutional Repository of Vilnius University
Odos vėžio klasifikavimas naudojant konvoliucinius neuroninius tinklus /
Abstract
dc:descriptionThe problem of skin cancer recognition on way is analyzed in this work. For example, late detection of melanoma can spread to human body and reduce survival rate. On the other hand, early detection of melanoma can be clinically surgered. Therefore, it is essential to recognize changes in human skin and prevent the spread of malignant diseases. Artificial neural networks show successful results in solving image recognition problems. To solve the problem of this works, convolutional neural networks were used due to their efficiency in solving image recognition problems. To find out with which neural network architecture parameters the model accurately recognizes diseases, experiments were performed with VGG16 and Lenet architecture and different parameters using the publicly available skin cancer dataset MNIST HAM10000.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Golotylecas, Aurimas,
- Contributors dc:contributor
-
- Kurasova, Olga
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:ELABAETD107116241&prefLang=en_US