text-recognition-ocr¶

• Main author - HEIA-FR
• Code
• Deployment configuration
• Staging
• Production

Description¶

This service takes a PNG or JPG image as input and performs optical text recognition (OCR) on it using Tesseract 5. The result is returned as a JSON containing the detected text and its bounding boxes.

Model¶

This service uses Tesseract through pytesseract. For more details about Tesseract 5, head to its github page.

Environment variables¶

Check the Core concepts > Service > Environment variables documentation for more details.

Run the tests with Python¶

Check the Core concepts > Service > Run the tests with Python documentation for more details.

Start the service locally¶

Check the Core concepts > Service > Start the service locally documentation for more details.