This repository contains example code for using the Dynamsoft Capture Vision SDK to detect documents in images.

• Dynamsoft Capture Vision Trial License

  errorCode, errorMsg = LicenseManager.init_license(
      "LICENSE-KEY")

• SDK Installation

  pip install -r requirements.txt

• Windows
• Linux
• macOS

• camera.py: Detect documents from a camera video stream.
• file.py: Detect documents from an image file and display the results in a window.
• orientation_detection.py: Normalize a document using Dynamsoft Capture Vision SDK, and detect the orientation of the document using Tesseract OCR.

How to Implement Document Detection in Python Using Dynamsoft Capture Vision SDK