quoccuongle/MultimodalOCR
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
qywh2023
2025-06-20 20:26:16 +08:00
committed by GitHub
parent ad8dd82e4c
commit 1eef3f65c7
1 changed files with 4 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@@ -21,11 +21,11 @@ OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Vis
[![Google Drive](https://img.shields.io/badge/Google%20Drive-Download-green?logo=google-drive)](https://drive.google.com/file/d/1Hk1TMu--7nr5vJ7iaNwMQZ_Iw9W_KI3C/view?usp=sharing)
**OCRBench v2** is a large-scale bilingual text-centric benchmark with currently the most comprehensive set of tasks (4× more tasks than the previous multi-scene benchmark OCRBench), the widest coverage of scenarios (31 diverse scenarios including street scene, receipt, formula, diagram, and so on), and thorough evaluation metrics, with a total of 10, 000 human-verified question-answering pairs and a high proportion of difficult samples. More details can be found in [OCRBench v2 README](./OCRBench_v2/README.md).
# OCRBench & OCRBench v2
**This is the repository of the [OCRBench](./OCRBench/README.md) & [OCRBench v2](./OCRBench_v2/README.md).**
<p align="center">
<img src="https://v1.ax1x.com/2024/12/30/7VhCnP.jpg" width="88%" height="80%">
<p>
**OCRBench** is a comprehensive evaluation benchmark designed to assess the OCR capabilities of Large Multimodal Models. It comprises five components: Text Recognition, SceneText-Centric VQA, Document-Oriented VQA, Key Information Extraction, and Handwritten Mathematical Expression Recognition. The benchmark includes 1000 question-answer pairs, and all the answers undergo manual verification and correction to ensure a more precise evaluation. More details can be found in [OCRBench README](./OCRBench/README.md).
@@ -33,12 +33,6 @@ OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Vis
<img src="./OCRBench/images/all_data.png" width="88%" height="80%">
</p>
**OCRBench v2** is a large-scale bilingual text-centric benchmark with currently the most comprehensive set of tasks (4× more tasks than the previous multi-scene benchmark OCRBench), the widest coverage of scenarios (31 diverse scenarios including street scene, receipt, formula, diagram, and so on), and thorough evaluation metrics, with a total of 10, 000 human-verified question-answering pairs and a high proportion of difficult samples. More details can be found in [OCRBench v2 README](./OCRBench_v2/README.md).
<p align="center">
<img src="https://v1.ax1x.com/2024/12/30/7VhCnP.jpg" width="88%" height="80%">
<p>
# News
* ```2024.12.31``` 🚀 [OCRBench v2](./OCRBench_v2/README.md) is released.
* ```2024.12.11``` 🚀 OCRBench has been accepted by [Science China Information Sciences](https://link.springer.com/article/10.1007/s11432-024-4235-6).