NORMA eResearch @NCI Library

Painter Identification Based On Their Paintings

Patel, Priya Prakashbhai (2022) Painter Identification Based On Their Paintings. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (5MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


With the digitization of paintings and creation of vast online libraries containing paintings of different painters the classification of paintings has never been more important than now. To do these various techniques are used such as computer vision and Artificial intelligence are used. Previously the classification of painters was done by experts in the field but in this paper tries to classify these painters by Implementing Convolution Neural Network (CNN) models. Also, the work that is already done is in the classification of paintings is vastly based on the style of paintings rather than the painters that created then. So, this paper will focus on the classification of painters. There are five models implemented and compared in the paper. Out of all models pretrained ResNet50 with imagenet weights as base weights and adding more layers on it had the highest accuracy of 85.38 percent.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Convolution Neural Network; imagenet; Classification; Alexnet, Res-Net50
Subjects: N Fine Arts > ND Painting
Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 27 Feb 2023 17:26
Last Modified: 01 Mar 2023 17:52

Actions (login required)

View Item View Item