Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Scribe Verification in Chinese manuscripts using Siamese, Triplet, and Vision Transformer Neural Networks

Dimitrios-Chrysovalantis Liakopoulos, Yanbo Zhang, Chongsheng Zhang, Constantine Kotropoulos

Abstract

The paper examines deep learning models for scribe verification in Chinese manuscripts. That is, to automatically determine whether two manuscript fragments were written by the same scribe using deep metric learning methods. Two datasets were used: the Tsinghua Bamboo Slips Dataset and a selected subset of the Multi-Attribute Chinese Calligraphy Dataset, focusing on the calligraphers with a large number of samples. Siamese and Triplet neural network architectures are implemented, including convolutional and Transformer-based models. The experimental results show that the MobileNetV3+ Custom Siamese model trained with contrastive loss achieves either the best or the second-best overall accuracy and area under the Receiver Operating Characteristic Curve on both datasets.

Scribe Verification in Chinese manuscripts using Siamese, Triplet, and Vision Transformer Neural Networks

Abstract

The paper examines deep learning models for scribe verification in Chinese manuscripts. That is, to automatically determine whether two manuscript fragments were written by the same scribe using deep metric learning methods. Two datasets were used: the Tsinghua Bamboo Slips Dataset and a selected subset of the Multi-Attribute Chinese Calligraphy Dataset, focusing on the calligraphers with a large number of samples. Siamese and Triplet neural network architectures are implemented, including convolutional and Transformer-based models. The experimental results show that the MobileNetV3+ Custom Siamese model trained with contrastive loss achieves either the best or the second-best overall accuracy and area under the Receiver Operating Characteristic Curve on both datasets.
Paper Structure (15 sections, 3 equations, 4 figures, 3 tables)

This paper contains 15 sections, 3 equations, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Datasets
  4. Model Architectures
  5. Siamese CNN-based Models
  6. Triplet Network
  7. ViT Siamese Model
  8. Loss Functions
  9. Contrastive Loss
  10. Triplet Loss
  11. Data Preprocessing and Sampling Strategy
  12. Training Setup
  13. Evaluation Procedure
  14. Experiments and Results
  15. Conclusion and Future Work

Figures (4)

  • Figure 1: Representative examples from the Tsinghua Bamboo Slips dataset.
  • Figure 2: Representative examples from the MCCD dataset.
  • Figure 3: ROC curve of the MobileNetV3+ Custom Siamese model on the Tsinghua Bamboo Slips dataset.
  • Figure 4: ROC curve of the ResNet34 Custom Siamese model on the MCCD dataset.