Detecting Legend Items on Historical Maps Using GPT-4o with In-Context Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909833154789376 |
|---|---|
| author | Kirsanova, Sofia Chiang, Yao-Yi Duan, Weiwei |
| author_facet | Kirsanova, Sofia Chiang, Yao-Yi Duan, Weiwei |
| contents | Historical map legends are critical for interpreting cartographic symbols. However, their inconsistent layouts and unstructured formats make automatic extraction challenging. Prior work focuses primarily on segmentation or general optical character recognition (OCR), with few methods effectively matching legend symbols to their corresponding descriptions in a structured manner. We present a method that combines LayoutLMv3 for layout detection with GPT-4o using in-context learning to detect and link legend items and their descriptions via bounding box predictions. Our experiments show that GPT-4 with structured JSON prompts outperforms the baseline, achieving 88% F-1 and 85% IoU, and reveal how prompt design, example counts, and layout alignment affect performance. This approach supports scalable, layout-aware legend parsing and improves the indexing and searchability of historical maps across various visual styles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08385 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Detecting Legend Items on Historical Maps Using GPT-4o with In-Context Learning Kirsanova, Sofia Chiang, Yao-Yi Duan, Weiwei Computer Vision and Pattern Recognition Artificial Intelligence Databases Information Retrieval H.2.8; H.3.3; I.2.10; I.4.8 Historical map legends are critical for interpreting cartographic symbols. However, their inconsistent layouts and unstructured formats make automatic extraction challenging. Prior work focuses primarily on segmentation or general optical character recognition (OCR), with few methods effectively matching legend symbols to their corresponding descriptions in a structured manner. We present a method that combines LayoutLMv3 for layout detection with GPT-4o using in-context learning to detect and link legend items and their descriptions via bounding box predictions. Our experiments show that GPT-4 with structured JSON prompts outperforms the baseline, achieving 88% F-1 and 85% IoU, and reveal how prompt design, example counts, and layout alignment affect performance. This approach supports scalable, layout-aware legend parsing and improves the indexing and searchability of historical maps across various visual styles. |
| title | Detecting Legend Items on Historical Maps Using GPT-4o with In-Context Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Databases Information Retrieval H.2.8; H.3.3; I.2.10; I.4.8 |
| url | https://arxiv.org/abs/2510.08385 |