The project page is: Pocket OCR

The source code is available at github: http://github.com/rcarlsen/Pocket-OCR

There is certainly a lot of improvement to be made. Automatic color correction. Page layout recognition. Perspective correction…the list could go on. The code is there, so…fork away!

(the thumbnail is a bit tongue-in-cheek…but honest. good conversion requires a good source image: well-lit, macro, focused and tightly cropped seems best)

For the M5 Bus trip assignment for our Applications class I worked up a mix of Twitter, GPS location, digital photos and Google Maps. I had previously synchronized the clocks for the camera, phone and TomTom GPS unit…and used these timestamps later to literally mash the Twitter XML and TomTom GPX files together with a custom Java application. Geocoding the photographs was done using the gpsdings java application.

Google Maps will display carefully formed KML (Keyhole Markup Language) files, which is nice because Google Earth can open the same file.

The project is available at http://robertcarlsen.net/m5. Although this entry is focused specifically on the technical side, I welcome comments here on the thoughts presented on the project page.