Extract English & Korean Text from Photos
Extracts English & Korean text from any image (photos, menus, signs, ID cards, documents, screenshots). Works on printed and handwritten text.
What it does
PaddleOCR reads English & Korean text from images and extracts it as searchable, copyable text. Point it at any photo with English & Korean text—a menu, sign, ID card, document, screenshot—and it automatically finds the text and converts it to digital characters. Fast on CPU, lightweight for mobile/edge devices. 92-95% accuracy on standard English & Korean documents.
Problem it solves
Read menus & signs | Extract text from menus, street signs, advertisements |
Digitize documents | Convert ID cards, invoices, forms, contracts to searchable text |
Translate text | Extract text to send for translation (no manual retyping needed) |
Screenshot text extraction | Copy text from screenshots, videos, or images |
Document processing | Batch process hundreds of Korean documents automatically |
Handwritten text | Works on both printed and handwritten text |
Input/Output
- Input: Any image with English & Korean text
- Format: JPEG, PNG, BMP, GIF, or PDF
- Resolution: Any size (optimized for 800×1200 to 2048×2048)
- Content: Photos, menus, signs, documents, screenshots, IDs, forms
- Text type: Printed or handwritten text
- Output: Extracted text
- Text content: English & Korean characters
Performance
- Accuracy by Text Type:
- Printed text: 92-95% accuracy (excellent)
- Handwritten text: 70-85% accuracy (reasonable, varies by handwriting)
- Clear, clean documents: 95%+ accuracy
- Poor quality/blurry images: 70-85% accuracy
- Mixed-language images: Good at isolating target text
- Real-World Scenarios:
- Restaurant menus: Excellent (printed, clear text)
- Street signs: Excellent (large, printed text)
- ID cards/documents: Excellent (official, standard format)
- Screenshots: Very good (digital text, crisp)
- Handwritten forms: Good (depends on handwriting legibility)
- Old/faded documents: Fair (may need post-processing)
- Blurry photos: Fair (depends on blur severity)
Technical Details
Architecture | PP-OCRv5 Korean |
Key Components | • Text Detection (DBNet): 3.6M parameters, outputs text bounding boxes via differentiable binarization
• Text Recognition (SVTR): 12M parameters, spatial vision transformer that decodes characters
• Orientation Classifier: 1.4M parameters (PP-LCNet), corrects rotated text |
Inference Pipeline | Detect text regions → Extract text lines → Classify orientation → Recognize characters → Map to image coordinates |
Training | • Framework: PaddlePaddle
• Optimizer: SGD with momentum + warmup/cosine decay
• Batch size: 256 (distributed)
• Data augmentation: RandAugment, elastic deformation |
Framework | • PaddlePaddle framework
• GPU recommended for inference |
Compliance & Provenance
Provider | Open-source |
Provider type | Specialized |
License | Apache 2.0 |
EU AI Act risk class | Minimal Risk |
Art. 50 transparency | Not applicable |
Region availability | Available globally |
Training data summary | Pending — provider has not yet published per Art. 53(d) |
For more on how we classify models and mark outputs, see our AI Policy.
Model Source
- GitHub: https://github.com/PaddlePaddle/PaddleOCR
- Paper: "PaddleOCR: A Practical Ultra Lightweight OCR System" (Baidu Research)
- License: apache-2.0