jpg file parsing to extract info/text

I have an idea for a project that I wanted some advice/pointers on.

I am planning to write an application to automatically parse expense receipts in JPG format and automatically开发者_JS百科 extract the amount and also categorize using some learning algorithm. Is this at all doable? What libraries are available to parse jpg files to extract textual information and currency information from it?

Any pointers appreciated..I have a vanilla HP all in one scanner that I will use to scan all receipts.

Thanks RS

You will need a OCR plugin (Optical character recognition) this will recognize and retrieve text from images. It has been a while since I last used OCR software, not sure what the best SDK's / plugins are at the moment.

I did find an article on The Code Project which uses a OCR product from Leadtool.