Optical Character Recognition

This filter uses Tesseract for optical character recognition. To enable compilation of this filter, you need to configure FFmpeg with --enable-libtesseract.

It accepts the following options:

datapath

Set datapath to tesseract data. Default is to use whatever was set at installation.

language

Set language, default is "eng".

whitelist

Set character whitelist.

blacklist

Set character blacklist.

The filter exports recognized text as the frame metadata lavfi.ocr.text. The filter exports confidence of recognized words as the frame metadata lavfi.ocr.confidence.