michaeln's profile - activity

*This is a follow up to an earlier post, except we are now broadening our range to include anyone located anywhere (not just locally). We are also giving a better explanation of what is needed.

We need a multithreaded Python script running on our Linux server to read forms and extract the textual content in JSON format. We already have OpenCV and Tessaract installed, as well as a Python script that reads basic forms with simple checkboxes. It works by converting checkboxes to a series of characters that Tesseract can understand. The problem is with forms that have lines and boxes and other shapes. Our Python script supposedly reads these forms (there are over a hundred lines of code) to find and extract the text parts and feed them to Tesseract. We don't know for certain because the script is timing out somewhere. Our part-time developer dropped the ball and skipped town. We just need someone to finish up what he started. Telecommuting is okay.

I'm looking for an OpenCV developer near Washington State to help with reading forms. Experience with Tesseract preferred.