Tools
Tools
Choudhury, Mrinmoy Dutta (2020) Automated Identification of Painters Over WikiArt Image Data Using Machine Learning Algorithms. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
Recent times have witnessed digitization of work from various sectors with the advancement of computer vision and artificial intelligence techniques. There has been a significant growth in the establishment of several online art libraries as well. A handful of work has previously been done on the classification of paintings based on style, however, very limited work has been performed towards classification of painters. The traditional approach of annotating images manually is time consuming and demands domain expertise. To enable efficient and faster annotation of image data, this project proposes the use of machine learning and deep learning algorithms to perform identification and classification of painters by extracting complex features from the images of available paintings. Several machine learning algorithms were implemented to accomplish this task and the results were compared using different evaluation matrices. The best classification accuracy of 75 percent was obtained using a pretrained ResNet-50 transfer learning approach. In addition to this, the results of the implemented models have been compared with the results of existing models in the subject.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Dan English |
| Date Deposited: | 22 Jan 2021 11:28 |
| Last Modified: | 22 Jan 2021 11:28 |
| URI: | https://norma.ncirl.ie/id/eprint/4438 |
Actions (login required)
 |
View Item |