Iconographic Classification and Content-Based Recommendation for Digitized Artworks

TL;DR

This paper introduces a prototype system that combines iconographic classification with content-based recommendation for digitized artworks, leveraging AI and Iconclass vocabulary to improve cataloging and navigation in heritage collections.

Contribution

It presents a novel integrated workflow using computer vision and symbolic reasoning to classify and recommend artworks based on iconographic content.

Findings

Demonstrates the potential of AI-driven iconographic classification.

Shows improved navigation in heritage repositories.

Validates the effectiveness of combining visual detection with symbolic inference.

Abstract

We present a proof-of-concept system that automates iconographic classification and content-based recommendation of digitized artworks using the Iconclass vocabulary and selected artificial intelligence methods. The prototype implements a four-stage workflow for classification and recommendation, which integrates YOLOv8 object detection with algorithmic mappings to Iconclass codes, rule-based inference for abstract meanings, and three complementary recommenders (hierarchical proximity, IDF-weighted overlap, and Jaccard similarity). Although more engineering is still needed, the evaluation demonstrates the potential of this solution: Iconclass-aware computer vision and recommendation methods can accelerate cataloging and enhance navigation in large heritage repositories. The key insight is to let computer vision propose visible elements and to use symbolic structures (Iconclass hierarchy) to reach meaning.