OCR - Text Recognition & Detection built-in OBS v0.0.7

The OCR Plugin for OBS provides real-time Optical Character Recognition (OCR) or Text Recognition & Detection abilities over any OBS Source that provides an image - can be Image, Video, Browser or any other Source. It is based on the incredible Tesseract open source OCR engine, compiled and running directly inside OBS for real-time operation on every frame rendered.

If you're looking for a solution to read scoreboards (2 min video) - check out ScoreSight! (https://obsproject.com/forum/resources/scoresight-ocr-tool-for-scoreboards.1884/)

If this free plugin has been valuable to you consider adding a to the GH repo, subscribing to my YouTube channel where I post updates, and supporting my work: GitHub, Patreon or OpenCollective. Join me on Discord

Do more with OCR:
Features:

• Add OCR Filter to any source with image or video output
• Choose from English model or Scoreboard model
• Output OCR result to an OBS Text Source
• Choose the segmentation mode: Word, Line, Page, etc.
• "Semantic Smoothing": getting more consistent outputs with higher accuracy and confidence by "averaging" several text outputs
• Timing/Running modes: per X-milliseconds
• Output formatting (with inja): e.g. "Score: {{score}}"
• Output text detection to image source
• Binarization methods (threshold, Otsu, Triangle, adaptive)
• Image Dilation
• Rescale (optimal Tesseract performance is at 35 pixels / character)

Coming soon:

• More languages built-in (pretrained Tesseract models)
• Allowing external model files
• More output capabilities e.g. Parsing, websocket event, etc.
• Extracting text from complex image layouts
• Different timing/run modes: per X-frames, image change, etc.
• Image stabilization
• Optical flow tracking for fast moving text
• Image processing: Perspective warping, auto-cropping, etc.
• Advanced binarization: Niblack, Sauvola

More tutorials coming soon!