Artificial intelligence-based image interpretation system: Unlocking a new dimension of artwork analysis

Abstract

This paper presents an artificial intelligence-based image interpretation system for automated, multi-perspective analysis of visual artworks. The system integrates a multimodal perception-generation pipeline that combines visual feature encoding with structured knowledge retrieval to enable context-aware art understanding. Specifically, the system employs a graph retrieval-augmented generation (GRAG) framework built upon an art context knowledge graph (ACKG). This framework not only models the relationships among artists, styles, historical periods, and cultural symbols, but also performs graph-based entity retrieval and subgraph reasoning to efficiently extract semantically relevant contextual knowledge. Subsequently, this knowledge is integrated with visual representations to generate high-quality textual interpretations. We evaluate the system on two public painting datasets, SemArt and Artpedia, and compare it with several state-of-the-art methods. Experimental results demonstrate that our approach significantly outperforms baseline models in both descriptive accuracy and richness of artistic context, while also achieving higher scores in human evaluations. These findings provide a new technological pathway and practical reference for applications in art education, intelligent museum guidance, and public art appreciation.