Masked image displaying wrong intensity

Question

Fotaras Sitof 2017-9-21

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/357655-masked-image-displaying-wrong-intensity

评论： Fotaras Sitof 2017-9-21

Hey guys,

I have a 3D image: [256x256x160] and a mask: [256x256x160]. The mask is a binary image of 0 and 255. After applying the mask on the image:

if true
  % masked_image = image.*mask;
end

I get a masked_image that has totally wrong intensity values. In fact, its values are nowhere to be found on the original image. They are just too big. All I want to achieve is extract the original image's intensities at the location of the mask and calculate the mean value of that ROI. I can see from 'imshow' that the mask is aligned properly on the image. However, applying the mask is unsuccessful and I don't understand why.

Many thanks for your help.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

OCDER 2017-9-21

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/357655-masked-image-displaying-wrong-intensity#answer_282486

编辑：OCDER 2017-9-21

在 MATLAB Online 中打开

Try this instead, which will select only the pixels in image dictated by the mask:

%to get the masked image without changing the dimension of the image
masked_image = image.*(mask > 0);
%or if you want just the pixels
masked_image_pixels = image(mask > 0);

Note that mask should really be a logical array, not a uint8 array, which is what (mask > 0) is taking care of for you.

In your original code, the issue is that you are using a uint8 mask matrix to multiply element-by-element with the image matrix. This means doing the following:

image .* mask
(value from the image matrix) x (255 or 0 from the "binary" uint8 mask matrix)

which would explain the large numbers.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Fotaras Sitof 2017-9-21

Thanks for the clarification. It makes sense now. After the mask was converted to 0 and 1 rather than 0 and 255 the extracted ROIs have proper values.

请先登录，再进行评论。