Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI Mobile Application for Archaeological Dating of Bronze Dings

Chuntao Li, Ruihua Qi, Chuan Tang, Jiafu Wei, Xi Yang, Qian Zhang, Rixin Zhou

TL;DR

The paper addresses the challenge of dating artifacts where expert judgment can vary by developing an image-based archaeological dating approach for Chinese bronze Dings. It combines a ConvNeXt-based classifier for period prediction with a SparseR-CNN detector for marking diagnostic feature parts, trained on approximately 4,000 labeled images annotated by experts. The system is packaged as a WeChat Mini Program, enabling users to upload photos, receive a four-prediction shortlist, and view feature parts and reference artifacts. Results show practical accuracy across multiple periods and demonstrate a education-focused deployment with broad accessibility for study and public engagement.

Abstract

We develop an AI application for archaeological dating of bronze Dings. A classification model is employed to predict the period of the input Ding, and a detection model is used to show the feature parts for making a decision of archaeological dating. To train the two deep learning models, we collected a large number of Ding images from published materials, and annotated the period and the feature parts on each image by archaeological experts. Furthermore, we design a user system and deploy our pre-trained models based on the platform of WeChat Mini Program for ease of use. Only need a smartphone installed WeChat APP, users can easily know the result of intelligent archaeological dating, the feature parts, and other reference artifacts, by taking a photo of a bronze Ding. To use our application, please scan this QR code by WeChat.

AI Mobile Application for Archaeological Dating of Bronze Dings

TL;DR

The paper addresses the challenge of dating artifacts where expert judgment can vary by developing an image-based archaeological dating approach for Chinese bronze Dings. It combines a ConvNeXt-based classifier for period prediction with a SparseR-CNN detector for marking diagnostic feature parts, trained on approximately 4,000 labeled images annotated by experts. The system is packaged as a WeChat Mini Program, enabling users to upload photos, receive a four-prediction shortlist, and view feature parts and reference artifacts. Results show practical accuracy across multiple periods and demonstrate a education-focused deployment with broad accessibility for study and public engagement.

Abstract

We develop an AI application for archaeological dating of bronze Dings. A classification model is employed to predict the period of the input Ding, and a detection model is used to show the feature parts for making a decision of archaeological dating. To train the two deep learning models, we collected a large number of Ding images from published materials, and annotated the period and the feature parts on each image by archaeological experts. Furthermore, we design a user system and deploy our pre-trained models based on the platform of WeChat Mini Program for ease of use. Only need a smartphone installed WeChat APP, users can easily know the result of intelligent archaeological dating, the feature parts, and other reference artifacts, by taking a photo of a bronze Ding. To use our application, please scan this QR code by WeChat.
Paper Structure (7 sections, 2 figures, 1 table)

This paper contains 7 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Application
  3. Deployment
  4. Data
  5. Inference
  6. Discussion
  7. Summary

Figures (2)

  • Figure 1: Interface of our application (in Chinese). The top left figure shows the main page, user can upload a photo by pressing the middle buttons , as shown in the top right figure. And then, the dating results are shown as the bottom left figure. The inferred period is shown in the middle, the feature parts are marked by yellow boxes in the top figure, and the reference artifacts are shown in the bottom. Pressing a reference artifact, its information is shown as the bottom right figure.
  • Figure 2: Examples of bronzes from 11 periods in the order as Table \ref{['tab:periods']}.