Hi all,
I am a Computer Science student in my final year. My graduation project is to build a face recognition system (based on Principle Component Analysis and possibly Artificial Neural Networks) on FPGA. Since software is the focus of our college study, hardware is not quite my domain of expertise. I have been doing some reading on the subject, but of course it's nothing in comparison to years of experience. So, I was wondering if you can provide me with some guidance on the following points:
- Which would be a better approach: implementing such system in HDL, or using a soft microprocessor, which if I understand correctly will make it possible to implement the system in assembly or even C. What about mixing them, which I think is referred to as a hardware/software co-design approach; would that be too hard to accomplish? What would its advantage be over either of the two approaches?
- If the use of a microprocessor is suggested, what are the recommendations for the type of microprocessor or the specific implementation?
- I already went and bought an XESS XSA-200 prototyping board, which operates a Spartan-II XC2S200-5FG256 (200k gates) FPGA. After spending the last couple of months with it, I realize it might be a bit low- end. The question is, would it be possible to fit the probably-complex image processing system on it, or is it possible that I would reach a point where I can't fit my design on it no matter what?
I realize this is a relatively long post, so I'd be grateful for any answers to any part of it.
Thank you for reading this far, and thanks in advance for any replies.
Best Regards, Islam Ossama
4th year, Computer Science Dept. Faculty of Computer and Information, Helwan University, Cairo, Egypt.