📄

Text Recognition(OCR) - PaddleOCR

🛠

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
    • image
  • Output: Extracted text
    • Text content: English & Korean characters
    • image

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