Authors: Janković, Radmila 
Affiliations: Computer Science 
Mathematical Institute of the Serbian Academy of Sciences and Arts 
Title: Cultural heritage image classification using transfer learning for feature extraction: a comparison
Volume: 3266
Related Publication(s): The Book of Proceedings
Conference: 1st International Virtual Conference on Visual Pattern Extraction and Recognition for Cultural Heritage Understanding
Issue Date: 2022
Rank: M33
Image classification in the domain of cultural heritage becomes extremely important with the development of digitization practices. This study aims to analyze how classification performance on the small dataset representing cultural heritage changes depending on the feature extraction method. The dataset comprised of 150 images belonging to three classes: (i) archaeological sites, (ii) frescoes, and (iii) monasteries. Five transfer learning architectures were used to extract the features from images, while classification was per-formed using four traditional machine learning algorithms, mainly Random forest, Naïve Bayes, Decision tree, and Multilayer perceptron classifier. The results suggest that Random forest and Multilayer perceptron are the most suitable algorithms for classification of cultural heritage images, especially when used in combination with the DenseNet121 pre-trained architecture. Naïve Bayes also performed well, with a maximum accuracy of 100% obtained when features are extracted using EfficientNetB0. However, the Decision tree algorithm reached only moderate performance.
Keywords: Cultural heritage | classification | transfer learning

Files in This Item:
File Description SizeFormat
RJBabic.pdf992.81 kBAdobe PDFView/Open
Show full item record

Page view(s)

checked on May 9, 2024


checked on May 9, 2024

Google ScholarTM


This item is licensed under a Creative Commons License Creative Commons