Study and Evaluation of Pre-trained CNN Networks for Cultural Heritage Image Classification

The classification of digital images is an essential task during the restoration and preservation of cultural heritage (CH). In computer vision, cultural heritage classification relies on the classification of asset images regarding a certain task such as type, artist, genre, style identification, etc. CH classification is challenging as various CH asset images have similar colors, textures, and shapes. In this chapter, the aim is to study and evaluate the use of pre-trained deep convolutional neural networks such as VGG16, VGG-19, ResNet50, and Inception-V3 for cultural heritage images classification using transfer learning techniques. The main idea is to start with CNN models previously trained for definite tasks with specific datasets and classes, instead of designing a full stand-alone CNN-based model. Two image datasets are used to validate the performance of these models in CH images classification. The experimental results showed that the Inception-V3-based model can achieve high levels of classification accuracy compared to other pre-trained CNNs studied in this chapter.