Project Detail

Description

The scope of this project is to scan OCR Images in a given directory. These images will then be processed and a text file with the same name should be provided within the same folder, or a subfolder.

Essentially a step-through of what needs to happen:

1) Your application constantly scans a directory for images contained in that directory.

2) Program picks an image file, cleans noise/processes image.

(There are a few ways we can integrate those first 2 steps)

3) Program does an OCR scan of the image

4) Program creates a standard text file (with the same name as the image). Example, scanning myarticle.jpg must result in myarticle.txt. We could even except myarticle.jpg.txt if you don't want to parse out the extension of the image.

5) Program looks for the next image in the folder.

If there are other options available as to the final implementation of your program, please feel free to suggest it if it will speed things up. We have simply provided a 'path of least resistance' but are certainly open to different methods of integrating the final program.

If you have any questions or would like to propose your project outline, please PM me, as I am looking to find the most qualified individual for this task.

Please provide an estimated/accurate turn-around time in your bid.

Please note that this is not the only site we're reviewing bids on, so you are competing with other freelancers on other freelance job sites.

Thank you for your interest and we look forward to accepting a qualified bid.

---------------------------------------------------------------------

The CAPTCHA in question can be found at the following location...

http://www.hqnetwork.com/media/Tcom_CAPTCHA.rar