PiTextReader

Scan printed text and converts to speech for the blind.

Overview

PiTextReader allows someone with impaired vision to “read” text from envelopes, letters and other items. It snapshots an image of the item, converts to plain text using OCR (Optical Character Recognition) and then speaks the text using text-to-speech.

The Reader is designed to be as absolutely simple to use as possible. No Internet needed, no graphical interface, only one button. Just place the item to be read onto the stand and press a button. After a few moments, the text will be read back to them.

Credits

This project has been forked from the original PiTextReader project by rgrokett.

It is developed by the french solidarity association My Human Kit and its volonteers.

Documentation

The documentation is available (in french) in the wikilab

(The original documentation in english is available on the original repository in pdf)

Utilities

• install.sh -- Installation script
• scripts/test.sh -- Tests each component of the Reader
• scripts/focus.sh -- Assist focusing camera using a PC browser

File structure

• pirextreader.py main script
• app.py main app
• constantes.py defines GPIO pins, default settings and command lines
• reader.py OCR and text to speech function
• player.py manage audio player
• server_led.py manage led lighting (neopixels)
• textreader.py standalone script to test image to speech processes
• logger.py logging utilities
• scripts/ contains utility scripts described above
• sounds/ contains helpers sounds
• sandbox/ contains experimental and deprecated scripts

Software stack

PiTextReader uses several command line utilities to perform image to speech:

• tesseract-ocr for OCR
• picoTTS for Text-To-Speech
• mplayer to play audio files