CODEWITHSUNDEEP
javaimage-processing
user2808109
user2808109

Reputation: 51

Java - Image Recognition

I have about 5000 images with water marks on them and 5000 identical images with no watermarks. The file names of each set of images are not correlated to each other in any way. I'm looking for an API in Java preferably that I can use to pair each water marked image with its non-water marked pair.

Upvotes: 5

Views: 37802

Answers (2)

Spektre
Spektre

Reputation: 51933

I think this is more about performance then about the image comparison itself and the answer is written in such manner so if you need help with the comparison itself comment me ...

  1. create simplified histogram for each image

    let say 8 values per each channel limiting to 4 bits per each intensity level. That will lead to 3*8*4=3*32 bits per image

  2. sort images

    take above histogram and consider it as a single number and sort the images of A group by it does not matter if ascending or descending

  3. matching A and B grouped images

    now the corresponding images should have similar histograms so take image from unsorted group B (watermarked), bin-search all the closest match in A group (original) and then compare more with more robust methods just against selected images instead of 5000.

  4. add flag if image from A group is already matched

    so you can ignore already matched images in bullet #3 to gain more speed

[Notes]

there are other ways to improvement like use Perceptual hash algorithms

Upvotes: 3

jgrocha
jgrocha

Reputation: 3062

You can use the OpenCV library. It can be used in Java. Please follow http://docs.opencv.org/doc/tutorials/introduction/desktop_java/java_dev_intro.html

Regarding image compare, you can see another useful answer here: Checking images for similarity with OpenCV

Upvotes: 7

Related Questions