DSPRelated.com
Forums
   Forums    More Forums    imagedsp  

Help on undergraduate thesis

Started by icecoldasice ●March 25, 2002
Greetings.

I'd like to know your opinion about the subject for my undergraduate
thesis.

I'd like to implement algorithms for low-level image processing in
different hardware plattforms (like FPGAs, DSPs, microcontroller,
even the PC) and make a comparisson about performace, real-world
aplications, cost, ease of implementation... for each plattform.

I should begin working on it in less than a month, that's why i ask
for your opinion.

Do u think it is a good choice for a thesis?
Do u think i could add a few things?

Thanks for all of your answers.



Reply by Steve Nordhauser ●March 27, 20022002-03-27
Mr./Ms. icecold,
It would certainly be interesting. From an industry point of view, I
have been involved in implementing image processing algorithms on all
the platforms you have listed. The complexity of the algorithm
typically dictates the engine but until it is benchmarked, it is hard to
know where the tradeoff is. For undergraduate, are you going to stick
to relatively easy to implement functions like convolutions, erosions,
histogramming? I think compression would be beyond the scope of what
you can do in a reasonable amount of time.

You might want to talk to one of the technical trade journals: Advanced
imaging, Vision systems design and see if they would want to publish
your results. Like I said, the results would be interesting. Now that
would look good on a resume.

--
Steve Nordhauser
Silicon Imaging, Inc.
digital that funny 'at' symbol nycap.rr.com
icecoldasice wrote:

>Greetings.
>
>I'd like to know your opinion about the subject for my undergraduate
>thesis.
>
>I'd like to implement algorithms for low-level image processing in
>different hardware plattforms (like FPGAs, DSPs, microcontroller,
>even the PC) and make a comparisson about performace, real-world
>aplications, cost, ease of implementation... for each plattform.
>
>I should begin working on it in less than a month, that's why i ask
>for your opinion.
>
>Do u think it is a good choice for a thesis?
>Do u think i could add a few things?
>
>Thanks for all of your answers. >
>



Reply by Jaime Andres Aranguren Cardona ●March 29, 20022002-03-29

Hi,

I also agree that this seems to be a very interesting topic for undergraduate thesis. How long is your timeframe? Maybe would take you long time to do somehow good implementations on all of those platforms.

Bestr regards,

JaaC

Steve Nordhauser <d...@nycap.rr.com> wrote:

Mr./Ms. icecold,
It would certainly be interesting.  From an industry point of view, I
have been involved in implementing image processing algorithms on all
the platforms you have listed.  The complexity of the algorithm
typically dictates the engine but until it is benchmarked, it is hard to
know where the tradeoff is.  For undergraduate, are you going to stick
to relatively easy to implement functions like convolutions, erosions,
histogramming?  I think compression would be beyond the scope of what
you can do in a reasonable amount of time.

You might want to talk to one of the technical trade journals: Advanced
imaging, Vision systems design and see if they would want to publish
your results.  Like I said, the results would be interesting.  Now that
would look good on a resume.

--
Steve Nordhauser
Silicon Imaging, Inc.
digital that funny 'at' symbol nycap.rr.com
icecoldasice wrote:

>Greetings.
>
>I'd like to know your opinion about the subject for my undergraduate
>thesis.
>
>I'd like to implement algorithms for low-level image processing in
>different hardware plattforms (like FPGAs, DSPs, microcontroller,
>even the PC) and make a comparisson about performace, real-world
>aplications, cost, ease of implementation... for each plattform.
>
>I should begin working on it in less than a month, that's why i ask
>for your opinion.
>
>Do u think it is a good choice for a thesis?
>Do u think i could add a few things?
>
>Thanks for all of your answers.



_____________________________________
Note: If you do a simple "reply" with your email client, only the author of this message will receive your answer.  You need to do a "reply all" if you want your answer to be distributed to the entire group.

_____________________________________
About this discussion group:

To Join:  i...@yahoogroups.com

To Post:  i...@yahoogroups.com

To Leave: i...@yahoogroups.com

Archives: http://www.yahoogroups.com/group/imagedsp

More Groups: http://www.dsprelated.com

">Yahoo! Terms of Service.


Jaime Andr Aranguren Cardona
j...@ieee.org
jaime.arangure...@computer.org