Is it possible to use this to find sub images in larger images?
So for instance if I have a picture of 20 books arranged neatly, and want to find 1 of those books, can this be used, and can we return a bounded box for that image?
I would suggest cropping the original image and adding each of the cropped portions. Unfortunately perceptual hashing does not make bounding box detection easy. :(
Is it possible to use this to find sub images in larger images?
So for instance if I have a picture of 20 books arranged neatly, and want to find 1 of those books, can this be used, and can we return a bounded box for that image?