Fuzzy Clustering to Encode Contextual Information in Artistic Image Classification

Abstract

Automatic art analysis comprises of utilizing diverse processing methods to classify and categorize works of art. When working with this kind of pictures, we have to take under consideration different considerations compared to classical picture handling, since works of art alter definitely depending on the creator, the scene delineated or their aesthetic fashion. This extra data improves the visual signals gotten from the images and can lead to better performance. However, this information needs to be modeled and embed alongside the visual features of the image. This is often performed utilizing deep learning models, but they are expensive to train. In this paper we utilize the Fuzzy C-Means algorithm to create a embedding strategy based on fuzzy memberships to extract relevant information from the clusters present in the contextual information. We extend an existing state-of-the-art art classification system utilizing this strategy to get a new version that presents similar results without training additional deep learning models.

ARTxAI: Explainable Artificial Intelligence Curates Deep Representation Learning for Artistic Images Using Fuzzy Techniques

“…In order to achieve these aims, we present different ways to obtain such features, using only visual cues of the image and when additional information is also available. We also propose a new way to represent the contextual embeddings from different paintings using fuzzy memberships that expands previous approaches in this sense [31], [32]. We shall study how the Fuzzy C-Means clustering algorithm [33] and an adapted version of a fuzzy-rule based fuzzy clustering algorithm can be used to construct an embedding space and how this embedding captures relevant information from the original texts.…”