reason for converting image into double

while reading the, why have to convert an image into double format.

[nabeel raza]

For Example:

I2 = im2double(I);

I2 = im2double(I,'indexed');

I2 = im2double(I) converts the intensity image I to double precision, rescaling the data if necessary. I can be a grayscale intensity image, a truecolor image, or a binary image. If the input image is of class double, then the output image is identical.

Answer 1

[Matz Johansson Bergström]

The reason is precision. Say you read an image using (write this in the Matlab prompt)

>>Im = imread('filename');
>>class(Im)
 uint8

The format is integers from 0 to 255. Now if we want to manipulate the image, we can write

>>class(Im*0.5)
 uint8

Notice that the format is still integer and not double. This means that we have lost precision. All subsequent manipulatins to the matrix Im will be in integer precision, unless we write something like

Im = im2double(Im)

Answer 2

[Walter Roberson]

http://uk.mathworks.com/matlabcentral/answers/233674-why-an-image-is-converted-to-double-using-i-im2double-i-in-matlab