HELLO FRIENDS, I want to detect an image from a set of images using matlab.I did using correlation.Is there any transform method i.e like fourier transform or any other way(pattern recognisation method) to detect a face of an image.If any one can tell where i can get material it would be great help to me. thanks in advance niranjan |
|
FACE DETECTION USING TRANSFORM METHODS ,HELP WANTED
Started by ●February 6, 2002
Reply by ●February 7, 20022002-02-07
Hi Niranjan, If I understood correctly this is what you are looking for. You have a reference image and you want to find a best match from several images..right? This seems like you can do SAD (Sum of Abs difference) for each image and take the one which is giving minimum SAD that will give the image which will have high correlation. -biju --- tniranjan9 <> wrote: > HELLO FRIENDS, > I want to detect an image from a set of images using > matlab.I did > using correlation.Is there any transform method i.e > like fourier > transform or any other way(pattern recognisation > method) to detect a > face of an image.If any one can tell where i can get > material it > would be great help to me. > thanks in advance > niranjan > > ------------------------ Yahoo! Groups Sponsor > > _____________________________________ > 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: > > To Post: > > To Leave: > > Archives: http://www.yahoogroups.com/group/imagedsp > > More Groups: http://www.dsprelated.com > > ">http://docs.yahoo.com/info/terms/ ===== ciao, -biju __________________________________________________ |
|
Reply by ●February 7, 20022002-02-07
tniranjan, "Digital Imaging" by Gonzalez and Woods is a good book. Published 1992. Regards, Marlo --- tniranjan9 <> wrote: > HELLO FRIENDS, > I want to detect an image from a set of images using > matlab.I did > using correlation.Is there any transform method i.e > like fourier > transform or any other way(pattern recognisation > method) to detect a > face of an image.If any one can tell where i can get > material it > would be great help to me. > thanks in advance > niranjan > __________________________________________________ |
Reply by ●February 8, 20022002-02-08
--- Biju Ravindran <> wrote: Hi, you can try with Artificial neural networks to identify a particular image (and even its distorted versions) among a set of images reg manj Hi Niranjan, > If I understood correctly this is what > you > are looking for. You have a reference image and you > want to find a best match from several > images..right? > > This seems like you can do SAD (Sum of Abs > difference) > for each image and take the one which is giving > minimum SAD that will give the image which will have > high correlation. > -biju > > --- tniranjan9 <> wrote: > > HELLO FRIENDS, > > I want to detect an image from a set of images > using > > matlab.I did > > using correlation.Is there any transform method > i.e > > like fourier > > transform or any other way(pattern recognisation > > method) to detect a > > face of an image.If any one can tell where i can > get > > material it > > would be great help to me. > > thanks in advance > > niranjan > > > > > > > > ------------------------ Yahoo! Groups Sponsor > > > > _____________________________________ > > 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: > > > > To Post: > > > > To Leave: > > > > Archives: > http://www.yahoogroups.com/group/imagedsp > > > > More Groups: http://www.dsprelated.com > > > > ">http://docs.yahoo.com/info/terms/ > > > > ===== > ciao, > -biju > > __________________________________________________ __________________________________________________ |