Hi there,
My name is Peter. I have 10+ software engineering experience in C++, image processing, computer graphics and machine learning. Among other things I have built systems for recognizing people in CCTV cameras, people silhouettes from Kinect cameras, and programs for detecting hand written letters (albeit clearly separated).
In order to plan work for your project better I need more information:
- what platform should it be built for - Windows / OSX / Linux?
- what is the language of the written text that needs to be converted - is it English?
- how legible is the text that program will analyze?
- does the pdf contain anything else apart from text to be analyzed - for example other text, pictures, diagrams, graphics etc?
- is it written by one person or several random people?
- can text appear anywhere in the page or only in some designated places?
- what is the minimum success rate that you will be happy with?
Ideally, I would like to get a sample of a pdf file to be able to give you a better idea of what can be realistically done. Without seeing that document no serious programmer will commit to that task.
Hope you will consider my application.
Regards
Peter