Wolfram Language & System 11.0 (2016)|Legacy Documentation

This is documentation for an earlier version of the Wolfram Language.View current documentation (Version 11.2)


gives an image in which each pixel is the absolute difference of the corresponding pixels in image1 and image2.


  • The images image1 and image2 must have the same dimensions.
  • ImageDifference works with arbitrary single-channel or multi-channel images.
  • If image1 or image2 is a single-channel image, the absolute difference is computed from each channel of the other image in ImageDifference[image1,image2].
  • If image1 and image2 are both multichannel images, the values in each channel are compared separately.
  • ImageDifference[image1,image2] gives an image with the largest type of either image1 or image2.
  • For binary images, ImageDifference effectively finds the logical XOR of pixel values.
  • ImageDifference works with Image3D objects.

ExamplesExamplesopen allclose all

Basic Examples  (2)Basic Examples  (2)

Find differences between two versions of an image:

Click for copyable input

Logical XOR of two binary images:

Click for copyable input
Introduced in 2010
| Updated in 2012