QtStreamOCR

A multimedia application to perform OCR on video streams using Qt 6, OpenCV, and Tesseract.

Features

• Video playback from file or webcam.
• Monochrome filter with 4 selectable color palettes.
• Real-time video rendering using VideoItem (QQuickPaintedItem).
• OCR on captured frames (F4 key) using Tesseract in a worker thread.
• UI built with QML, logic in C++.

Prerequisites

• Qt 6.5+ (Core, Quick, Multimedia, Widgets)
• OpenCV 4.x
• Tesseract OCR (libtesseract-dev, libleptonica-dev)
• CMake 3.16+
• C++17 compiler

Installation (Linux/Ubuntu/Debian)

You need to install the development libraries for OpenCV and Tesseract. Run the following commands:

sudo apt update
sudo apt install libopencv-dev tesseract-ocr libtesseract-dev libleptonica-dev pkg-config

Build Instructions

mkdir build
cd build
cmake ..
make

Usage

1. Run the application: ./appQtStreamOCR
2. Click "Upload Video" to select a video file, or "Webcam" to start the camera.
3. Use the Color Palette on the left to change the monochrome filter.
4. Press F4 to capture the current frame.
   • The frame will appear in the bottom list.
   • OCR will be performed, and text will appear in the right panel.