Abstract
Image classification is one of the most important tasks in the digital era. In terms of cultural heritage, it is important to develop classification methods that obtain good accuracy, but also are less computationally intensive, as image classification usually uses very large sets of data. This study aims to train and test four classification algorithms: (i) the multilayer perceptron, (ii) averaged one dependence estimators, (iii) forest by penalizing attributes, and (iv) the k-nearest neighbor rough sets and analogy based reasoning, and compares these with the results obtained from the Convolutional Neural Network (CNN). Three types of features were extracted from the images: (i) the edge histogram, (ii) the color layout, and (iii) the JPEG coefficients. The algorithms were tested before and after applying the attribute selection, and the results indicated that the best classification performance was obtained for the multilayer perceptron in both cases.
Highlights
Cultural heritage represents a set of unique practices, objects, places, values, and artistic works that are formed throughout history in different countries and regions
It can be observed that the Multilayer Perceptron (MLP) algorithm performed the best with 85% of correctly classified instances, followed by RSeslibKnn with 82% of correctly classified instances, Averaged One Dependence Estimators (AODE) with 79%, and Forest PA with 78%
A large dataset comprised of 4000 images classified into five categories was used, and several key findings were derived from the study: (i) the neural network based algorithms performed much better when classifying images compared to the other algorithms; (ii) the k-nearest neighbor classifier performed better than the decision tree based classifier; (iii) all classifiers performed better after reducing the attribute number, except for the k-nearest neighbor classifier, which lost its prediction accuracy; and (iv) images of columns were most frequently misclassified, while images representing the dome were most frequently correctly classified by these algorithms
Summary
Cultural heritage represents a set of unique practices, objects, places, values, and artistic works that are formed throughout history in different countries and regions. Each society has its own cultural heritage that is usually passed on from generation to generation, enabling sharing and learning. Various types of cultural heritage can be found worldwide including archaeological sites, documents, photographs, historical monuments, and other elements. Cultural heritage can be grouped into two main categories: (i) tangible and (ii) intangible, according to UNESCO [1]. Tangible cultural heritage can further be grouped into movable and unmovable cultural heritage. Movable cultural heritage involves physical objects and artifacts such as paintings, sculptures and furniture, while immovable heritage includes buildings, monuments, and archaeological sites [1]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
