Problem in Neural Network

8 views (last 30 days)
Mohammad
Mohammad on 25 Aug 2013
Commented: Image Analyst on 26 Mar 2022
When I try to run the code
img = edu_imgpreprocess(I);
for cnt = 1:50
bw2 = edu_imgcrop(img{cnt});
charvec = edu_imgresize(bw2);
out(:,cnt) = charvec;
end
P = out(:,1:40);
T = [eye(10) eye(10) eye(10) eye(10) ];
Ptest = out(:,41:50);
For 26 alphabets making a change in the code as follows:
img = edu_imgpreprocess(I);
for cnt = 1:26
bw2 = edu_imgcrop(img{cnt});
charvec = edu_imgresize(bw2);
out(:,cnt) = charvec;
end
P = out(:,1:20);
T = [eye(10) eye(10) eye(10) eye(10) ];
Ptest = out(:,21:26);
It gives me an error of
Error using rgb2gray>parse_inputs (line 81)
MAP must be a m x 3 array.
Error in rgb2gray (line 35)
X = parse_inputs(varargin{:});
Error in edu_imgpreprocess (line 3)
Igray = rgb2gray(I);
Error in char3 (line 8)
img = edu_imgpreprocess(I);
Kindly help please. Thanks.
  3 Comments
Mo'ath Al-Hayek
Mo'ath Al-Hayek on 26 Mar 2022
can you share with us your code after modification?
Image Analyst
Image Analyst on 26 Mar 2022
@Mo'ath Al-Hayek probably not since @Mohammad has not been here in 9 years so he'll probably never see your message. Or if he does, he doesn't have the code anymore. You're best off just posting your own question in your own new discussion thread (not here).

Sign in to comment.

Answers (2)

Image Analyst
Image Analyst on 29 Sep 2013
Edited: Image Analyst on 26 Mar 2022
If this is still a problem for you, what did you pass in for (the badly-named) I? Do a "whos I" before that line and say what is in the command window. Changes are it's not a regular, normal RGB image.
Replace this:
Igray = rgb2gray(I);
with this:
if ndims(I) == 3
Igray = rgb2gray(I);
else
Igray = I;
end

Dabira
Dabira on 26 Jun 2014
Please tell me where did yu find out.m I cant find it
  2 Comments
Walter Roberson
Walter Roberson on 22 Nov 2016
In the code in the Question here, out is an array not a function.

Sign in to comment.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!