Neural Network Architecture for Identifying Image Copies

Question

I have a large image collection and wish to identify the images within that collection that appear to copy other images from the collection.

To give you a sense of the kinds of image pairs that I wish to classify as matches, please consider these examples:

I have hand classified roughly .25M pairs of matching images, and now wish to use those hand labelled matches to train a neural network model. I am just not sure which architecture would be ideally suited for this task.

I originally thought a Siamese Network might be appropriate, as they have been used for similar tasks, but the output from those classifiers seems more ideally suited to finding different figurations of the same object (which is not what I want), rather than different printings of the same figuration (which is what I want).

If anyone can help recommend papers or architectures ideally suited to identifying images given the training data I have prepared, I would be tremendously grateful for any insights you can offer.

toodef · Answer

U need to read about triplet loss function. Triplet loss function gets result embeddings from a network, that process 3 images by a network (2 similar and 1 non-similar) for one step:

After that loss computing as:

For more details read the paper from triplet loss authors.

Also may help PSNR, but this is not Deep Learning.

Naveen Meka · Answer

If the images are more similar like you posted, you can go with Structural similarity index which gives output in the range -1 to 1. any thing more than 0.9 can be considered similar.

Neural Network Architecture for Identifying Image Copies

2 Answers

Add your own answers!

Ask a Question