NOMALIZE THE IMAGE
in [Matlab]
|
From: mops zaki on 24 May 2010 06:56 i have to do normalization...for it first i have to calculate mean and variance of the image i use M = mean(I5(:)) ; to calculate mean...but the size of image reduce to 1x1 after mean.. WAT I HAVE DONE WRONG MY FULL CODE IS.. clear all image=imread('0001hv1.bmp'); %Designing guasian filter%%%%%%%%%%%%%%%%%%(LOW PASS) sigma=0.8; H=fspecial('gaussian',[5 5],sigma); I5=imfilter(image,H); figure(2),imshow(I5); M = mean(I5(:)) ; HELP ME PLZ
From: Wayne King on 24 May 2010 07:34 "mops zaki" <zaki_achi(a)hotmail.com> wrote in message <htdm05$kgj$1(a)fred.mathworks.com>... > i have to do normalization...for it first i have to calculate mean and variance of the image > i use M = mean(I5(:)) ; to calculate mean...but the size of image reduce to 1x1 after mean.. WAT I HAVE DONE WRONG > > MY FULL CODE IS.. > clear all > image=imread('0001hv1.bmp'); > %Designing guasian filter%%%%%%%%%%%%%%%%%%(LOW PASS) > sigma=0.8; > H=fspecial('gaussian',[5 5],sigma); > I5=imfilter(image,H); > figure(2),imshow(I5); > M = mean(I5(:)) ; > > HELP ME PLZ Hi, did you just intend to calculate the mean of each column in the image? Then, just enter: M = mean(I5); Your line M = mean(I5(:)); is equivalent to M = mean(mean(I5)); you're calculating the mean of the column means. That's why it's a scalar. Wayne
From: Sean on 24 May 2010 07:42 "mops zaki" <zaki_achi(a)hotmail.com> wrote in message <htdm05$kgj$1(a)fred.mathworks.com>... > i have to do normalization...for it first i have to calculate mean and variance of the image > i use M = mean(I5(:)) ; to calculate mean...but the size of image reduce to 1x1 after mean.. WAT I HAVE DONE WRONG > > MY FULL CODE IS.. > clear all > image=imread('0001hv1.bmp'); > %Designing guasian filter%%%%%%%%%%%%%%%%%%(LOW PASS) > sigma=0.8; > H=fspecial('gaussian',[5 5],sigma); > I5=imfilter(image,H); > figure(2),imshow(I5); > M = mean(I5(:)) ; The mean of a vector is always going to be a scalar. What else would you expect? Is this what you're trying to do? http://bigwww.epfl.ch/demo/jlocalnormalization/index.html If so; you're not going to want the mean of the whole image(:) but rather local means. Also note 'sigma' is a built-in function
From: mops zaki on 24 May 2010 07:47 "Wayne King" <wmkingty(a)gmail.com> wrote in message <htdo7e$ej4$1(a)fred.mathworks.com>... > "mops zaki" <zaki_achi(a)hotmail.com> wrote in message <htdm05$kgj$1(a)fred.mathworks.com>... > > i have to do normalization...for it first i have to calculate mean and variance of the image > > i use M = mean(I5(:)) ; to calculate mean...but the size of image reduce to 1x1 after mean.. WAT I HAVE DONE WRONG > > > > MY FULL CODE IS.. > > clear all > > image=imread('0001hv1.bmp'); > > %Designing guasian filter%%%%%%%%%%%%%%%%%%(LOW PASS) > > sigma=0.8; > > H=fspecial('gaussian',[5 5],sigma); > > I5=imfilter(image,H); > > figure(2),imshow(I5); > > M = mean(I5(:)) ; > > > > HELP ME PLZ > > Hi, did you just intend to calculate the mean of each column in the image? Then, just enter: > > M = mean(I5); > > Your line > M = mean(I5(:)); > is equivalent to > M = mean(mean(I5)); > you're calculating the mean of the column means. That's why it's a scalar. > > Wayne hi i want to calculate mean of whole image....ofter calulating mean i have to subtract the mean image from the original one....
From: mops zaki on 24 May 2010 07:50
"Sean " <sean.dewolski(a)nospamplease.umit.maine.edu> wrote in message <htdoms$ftr$1(a)fred.mathworks.com>... > "mops zaki" <zaki_achi(a)hotmail.com> wrote in message <htdm05$kgj$1(a)fred.mathworks.com>... > > i have to do normalization...for it first i have to calculate mean and variance of the image > > i use M = mean(I5(:)) ; to calculate mean...but the size of image reduce to 1x1 after mean.. WAT I HAVE DONE WRONG > > > > MY FULL CODE IS.. > > clear all > > image=imread('0001hv1.bmp'); > > %Designing guasian filter%%%%%%%%%%%%%%%%%%(LOW PASS) > > sigma=0.8; > > H=fspecial('gaussian',[5 5],sigma); > > I5=imfilter(image,H); > > figure(2),imshow(I5); > > M = mean(I5(:)) ; > > The mean of a vector is always going to be a scalar. What else would you expect? > Is this what you're trying to do? > http://bigwww.epfl.ch/demo/jlocalnormalization/index.html > > If so; you're not going to want the mean of the whole image(:) but rather local means. > > Also note 'sigma' is a built-in function thanx sean...but i want mean of entire image...becuze this mean image would be subractes from original image.... zaki |