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.
** See Full Instructions in the PiTextReader.pdf document **
This checkout has been updated for current Raspberry Pi OS / Debian Bookworm systems:
- Python 3 is used explicitly.
- The camera command now prefers
rpicam-still, with fallback support forlibcamera-stilland legacyraspistill. python3 -m http.serverreplaces the old Python 2SimpleHTTPServer.gpiozeroreplaces directRPi.GPIOusage.- A systemd service replaces the old crontab-at-boot startup path.
Run the installer from the project directory:
./install.shThe installer installs these Raspberry Pi OS packages:
alsa-utilsflitepython3-gpiozeropython3-lgpiorpicam-apps-coretesseract-ocr
It then creates and enables a pitextreader.service systemd unit using the
directory where install.sh was run.
Start the reader immediately:
sudo systemctl start pitextreader.serviceCheck service status and logs:
systemctl status pitextreader.service
journalctl -u pitextreader.serviceRun manually for testing:
python3 pitextreader.pyModern Raspberry Pi OS releases use rpicam-still for still image capture. The
old raspistill command only exists on legacy camera stacks. The main program,
installer, focus utility, and test utility all prefer rpicam-still.
The grayscale effect previously requested with raspistill -cfx 128:128 is
approximated with --saturation 0 for rpicam-still and libcamera-still.
- install.sh -- Installation script
- test.sh -- Tests each component of the Reader
- focus.sh -- Assist focusing camera using a PC browser