I want to remove noise on image sample for handwriting recognition but I get some error

Question

I = imread('data1.jpg');
imshow(I)
J = imnoise(I,'salt%pepper',0.02);
figure,imshow(J)
K = filter2(fspecial('average',3),J)/255;
figure,imshow(K)
L = medfilt2(J,[3,3]);
figure,imshow(L)

I got this error when I run above code

"??? Error using ==> imnoise>ParseInputs at 231
Unknown noise type: 'salt%pepper'.

Error in ==> imnoise at 85
  [a, code, classIn, classChanged, p3, p4] = ParseInputs(varargin{:});

Error in ==> noisetry at 3
J = imnoise(I,'salt%pepper',0.02);"

I'm voting to close because the problem is caused by a simple typographical error and can't be reproduced — Benoit_11, Oct 13 '15 at 13:12
@BillBokeey i also get the same error. is that have any method to remove noise from an image? can you help me? — user5405704, Oct 13 '15 at 13:39
Are you sure you wrote 'salt & pepper' and not 'salt % pepper'? — BillBokeey, Oct 13 '15 at 13:43
yes. when i run above code i get this error "? Undefined function or method 'conv2' for input arguments of type 'double' and attributes 'full 3d real'. Error in ==> filter2 at 73 y = conv2(hcol, hrow, x, shape); Error in ==> noisetry at 5 K = filter2(fspecial('average',3),J)/255;" @BillBokeey — user5405704, Oct 13 '15 at 13:49
@BillBokeey thanks for your attention. but i got the error which i have mention above — user5405704, Oct 13 '15 at 13:51
@BillBokeey here are the error " "Undefined function or method 'conv2' for input arguments of type 'double' and attributes 'full 3d real'." — user5405704, Oct 13 '15 at 14:01
@BillBokeey " "Error in ==> filter2 at 73 y = conv2(hcol, hrow, x, shape);" — user5405704, Oct 13 '15 at 14:06
@BillBokeey "Error in ==> noisetry at 5 K = filter2(fspecial('average',3),J)/255;" — user5405704, Oct 13 '15 at 14:06

score 0 · Answer 1 · answered Oct 13 '15 at 14:16

0

Is your image black&white? If not convert it to B&W (JBW = rgb2gray(I)) and it should work. Function filter works only for 2 dimensional images.

I = imread('image.jpg');
imshow(I);
J = imnoise(I,'salt & pepper',0.02);
figure,imshow(J);
JBW = rgb2gray(I);
K = filter2(fspecial('average',3),JBW)/255;
figure,imshow(K);
L = medfilt2(JBW,[3,3]);
figure,imshow(L);

answered Oct 13 '15 at 14:16

Agnieszka Mikołajczyk

88
10

yes my image is black and white. so can you help me to solve all the error? @Agnieszka – user5405704 Oct 13 '15 at 14:23
Can you tell me what errors you got after computing the code I gave you? :) – Agnieszka Mikołajczyk Oct 13 '15 at 14:26
thanks for helping me :). the code that you had give to me no error. thanks so much. may ask you something? did you familiar with handwriting recognition ? @Agnieszka Mikolajckyk – user5405704 Oct 13 '15 at 14:33
Mikolajckyk did hough transform is the best technique for extract the handwriting sample? im little bit confuse – user5405704 Oct 21 '15 at 21:21
I don't know what would be the best. You can keep experimenting. – Agnieszka Mikołajczyk Oct 23 '15 at 06:49

I want to remove noise on image sample for handwriting recognition but I get some error

1 Answers1