An archaeological Catalog Collection Method Based on Large Vision-Language Models

TL;DR

This paper introduces a new method leveraging large vision-language models to automate the collection of archaeological catalogs, addressing challenges in image detection and modal matching for artifact data extraction.

Contribution

The paper presents a novel three-module approach using large vision-language models for accurate and automated archaeological catalog collection, improving over existing methods.

Findings

Effective in collecting artifact images and descriptions

Demonstrated on pottery catalogs with successful results

Provides a reliable automated collection solution

Abstract

Archaeological catalogs, containing key elements such as artifact images, morphological descriptions, and excavation information, are essential for studying artifact evolution and cultural inheritance. These data are widely scattered across publications, requiring automated collection methods. However, existing Large Vision-Language Models (VLMs) and their derivative data collection methods face challenges in accurate image detection and modal matching when processing archaeological catalogs, making automated collection difficult. To address these issues, we propose a novel archaeological catalog collection method based on Large Vision-Language Models that follows an approach comprising three modules: document localization, block comprehension and block matching. Through practical data collection from the Dabagou and Miaozigou pottery catalogs and comparison experiments, we demonstrate the effectiveness of our approach, providing a reliable solution for automated collection of archaeological catalogs.