how to crop a interest part image
2 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
guitoune mohieddine
el 11 de Abr. de 2015
Editada: guitoune mohieddine
el 12 de Abr. de 2015
hellow
I have this image i segmented by kmeans méthod, and i get this résult
Now i want to crop it to get just the license plate
, so there is a solution ???
please help me .
0 comentarios
Respuesta aceptada
Image Analyst
el 11 de Abr. de 2015
Just get profiles and use find:
verticalProfile = sum(binaryImage, 2); % Sum along columns in each row.
row1 = find(verticalProfile, 1, 'first');
row2 = find(verticalProfile, 1, 'last');
horizontalProfile = sum(binaryImage, 1); % Sum along rows in each column.
column1 = find(horizontalProfile, 1, 'first');
column2 = find(horizontalProfile, 1, 'last');
croppedImage = binaryImage(row1:row2, column1:column2);
4 comentarios
Image Analyst
el 12 de Abr. de 2015
guitone's "Answer" moved here:
Thank you for reply, but there is an error:
Index exceeds matrix dimensions.
Error in test (line 51)
greenChannel = rgbImage(:, :, 2)
Can you help me?
Image Analyst
el 12 de Abr. de 2015
You're obviously not using the image that you posted and gave to me. The image you posted is a color image, but the one you're using is a grayscale image. So you need to put this code after your call to imread():
if numberOfColorBands >= 3
% Crop the image
rgbImage = rgbImage(50:400, 100:600, :);
% Extract the individual red, green, and blue color channels.
redChannel = rgbImage(:, :, 1);
greenChannel = rgbImage(:, :, 2);
blueChannel = rgbImage(:, :, 3);
% Crop the image
grayImage = redChannel;
else
% It's already gray scale.
% Crop the image
grayImage = rgbImage(50:400, 100:600, :);
end
Más respuestas (1)
guitoune mohieddine
el 12 de Abr. de 2015
Editada: guitoune mohieddine
el 12 de Abr. de 2015
0 comentarios
Ver también
Categorías
Más información sobre Image Segmentation and Analysis en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!