Bojik
asked on
Programming a Raspberry PI
Is it possible to program the Raspberry PI camera to do OCR?
Need it to recognize a list of characters and when seen, write the info to a file.
Need the following info with each entry;
Captured data
Date and time (down to the second)
Location (can be GPS or user entry)
And once a day (or at user request) upload data to a online database.
Need it to recognize a list of characters and when seen, write the info to a file.
Need the following info with each entry;
Captured data
Date and time (down to the second)
Location (can be GPS or user entry)
And once a day (or at user request) upload data to a online database.
ASKER
Are there other compact options that might work?
@Bojik - You can get started on building a proof of concept by leveraging two open-source projects:
You will use PyTesser as a wrapper to interact with the Tesseract OCR Software. Here's a link to a blog site with some code snippets to get you started. https://rdmilligan.wordpress.com/2014/11/21/ocr-on-raspberry-pi/ (link verified 5/31/2017).
Regards,
LaJuan
- Tesseract - OCR software supported by Google: https://github.com/tesseract-ocr/tesseract/blob/master/README.md
- PyTesser - Optical Character Recognition module for Python: https://code.google.com/archive/p/pytesser/
You will use PyTesser as a wrapper to interact with the Tesseract OCR Software. Here's a link to a blog site with some code snippets to get you started. https://rdmilligan.wordpress.com/2014/11/21/ocr-on-raspberry-pi/ (link verified 5/31/2017).
Regards,
LaJuan
@Bojik - When you say
compact options, what does that mean...
- How will the solution be used (automated or interactive)?
- How much space do you have to work with?
- What's the size of images you are scanning?
- Do you have any control over the images that you have to perform OCR on?
- Can you use QR Codes instead (lots of options available)?
ASKER
How will the solution be used (automated or interactive)?
***As automated as possible, as a item to be scanned comes across the camera it should auto detect and save the data (will work best with no user input between items)
How much space do you have to work with?
***3" by 4" by 1.5"
What's the size of images you are scanning?
***2" by 2" area
Do you have any control over the images that you have to perform OCR on?
***Yes, limited to 17 different characters and only 4 possible in each scan
Can you use QR Codes instead (lots of options available)?
***No
***As automated as possible, as a item to be scanned comes across the camera it should auto detect and save the data (will work best with no user input between items)
How much space do you have to work with?
***3" by 4" by 1.5"
What's the size of images you are scanning?
***2" by 2" area
Do you have any control over the images that you have to perform OCR on?
***Yes, limited to 17 different characters and only 4 possible in each scan
Can you use QR Codes instead (lots of options available)?
***No
This question needs an answer!
Become an EE member today
7 DAY FREE TRIALMembers can start a 7-Day Free trial then enjoy unlimited access to the platform.
View membership options
or
Learn why we charge membership fees
We get it - no one likes a content blocker. Take one extra minute and find out why we block content.
OCR is a processor and memory intensive operation, a Raspberry Pi has little processor power and memory.