Description: This bash script provides a way to identify similar photos (e.g. similar size, content, distribution ) and not exact duplicates. This is particularly helpful when training images for Machine Learning purposes.
How it works:
the script inside a folder
the script recursively scans all directories for any image files and stores them for further processing
compares each image with the rest of the set
if the images differ in size, scale them down to a 300x300 square and compare
if the images are of equal size, compare them and produce the Root Mean Square Error of their pixel values
continue with next image in the set
To Search:
File list (Check if you may need any files):
1985533ImgCompare.sh.tar
Download