diff --git a/README.md b/README.md index 30bf3e1..bd8e102 100644 --- a/README.md +++ b/README.md @@ -2,6 +2,8 @@ Modern OCR web application powered by DeepSeek-OCR with a stunning React frontend and FastAPI backend. +![DeepSeek OCR in Action](assets/multi-bird.png) + > **Recent Updates (v2.1.1)** > - ✅ Fixed image removal button - now properly clears and allows re-upload > - ✅ Fixed multiple bounding boxes parsing - handles `[[x1,y1,x2,y2], [x1,y1,x2,y2]]` format @@ -286,6 +288,19 @@ For large images, the model uses dynamic cropping: - **Supports multiple boxes**: When finding multiple instances, format is `[[x1,y1,x2,y2], [x1,y1,x2,y2], ...]` - Frontend automatically displays all boxes overlaid on the image with unique colors +## Examples + +Here are some example images showcasing different OCR capabilities: + +### Visual Understanding +![Helmet Description](assets/helmet.png) + +### Table Extraction from Chart +![Chart to Table](assets/table_from_chart.png) + +### Image Description +![Describe Mode](assets/describe.png) + ## Troubleshooting ### GPU not detected diff --git a/assets/describe.png b/assets/describe.png new file mode 100644 index 0000000..ab734ce Binary files /dev/null and b/assets/describe.png differ diff --git a/assets/helmet.png b/assets/helmet.png new file mode 100644 index 0000000..27f4a0f Binary files /dev/null and b/assets/helmet.png differ diff --git a/assets/multi-bird.png b/assets/multi-bird.png new file mode 100644 index 0000000..7fdfdf3 Binary files /dev/null and b/assets/multi-bird.png differ diff --git a/assets/table_from_chart.png b/assets/table_from_chart.png new file mode 100644 index 0000000..949a662 Binary files /dev/null and b/assets/table_from_chart.png differ