0

I have this project I'm working on. A part of the project involves multiple test runs during which screenshots of an application window are taken. Now, we have to ensure that screenshots taken between consecutive runs match (barring some allowable changes). These changes could be things like filenames, dates, different logos, etc. within the application window that we're taking a screenshot of.

I had the bright idea to automate the process of doing this checking. Essentially my idea was this. If I could somehow mathematically quantify the difference between a screenshot from the N-1th run and the Nth run, I could create a binary labelled dataset that mapped feature vectors of some sort to a label (0 for pass or 1 for fail if the images do not adequately match up). The reason for all of this was so that my labelled data would help make the model understand what scale of changes are acceptable, because there are so many kinds that are acceptable.

Now lets say I have access to lots of data that I have meticulously labelled, in the thousands. So far I have tried using SIFT in opencv using keypoint matching to determine a similarity score between images. But this isn't an intelligent, learning process. Is there some way I could take some information from SIFT and use it as my x-value in my dataset?

Here are my questions:

  1. what would that be the information I need as my x-value? It needs to be something that represents the difference between two images. So maybe the difference between feature vectors from SIFT? What do I do when those vectors are of slightly different dimensions?

  2. Am I on the right track with thinking about using SIFT? Should I look elsewhere and if so where?

Thanks for your time!

bumblyboi
  • 11
  • 1
  • 5
  • If I am understanding your question correctly, you want to use SIFT to label your dataset. You would create some `x` based on your SIFT features, and based on the same x values (by thresholding them, for example) you would also create your `y` label. Essentially classifying the images. You would then want to use this dataset to train a CNN or something to do this classification more accurately. Is that right? – Ananda Dec 15 '20 at 03:39
  • yes yes exactly! I'm having a real hard time coming up with the specifics – bumblyboi Dec 15 '20 at 03:54

1 Answers1

0

The approach that is being suggested in the question goes like this -

  • Find SIFT features of two consecutive images.
  • Use those to somehow quantify the similarity between two images (sounds reasonable)
  • Use this metric to first classify the images into similar and non-similar.
  • Use this dataset to train a NN do to the same job.

I am not completely convinced if this is a good approach. Let's say that you created the initial classifier with SIFT features. You are then using this data to train a NN. But this data will definitely have a lot of wrong labels. Because if it didn't have a lot of wrong labels, what's stopping you from using your original SIFT based classifier as your final solution?

So if your SIFT based classification is good, why even train a NN? On the other hand, if it's bad, you are giving a lot of wrong labeled data to the NN for training. I think the latter is a probably a bad idea. I say probably because there is a possibility that maybe the wrong labels just encourage the NN to generalize better, but that would require a lot of data, I imagine.

Another way to look at this is, let's say that your initial classifier is 90% accurate. That's probably the upper limit of the performance for the NN that you are looking at when talking about training it with this data.

You said that the issue that you have with your first approach is that 'it's not a an intelligent, learning process'. I think it's the wrong approach to think that the former approach is always inferior to the latter. SIFT is a powerful tool that can solve a lot of problems without all the 'black-boxness' of an NN. If this problem can be solved with sufficient accuracy using SIFT, I think going after a learning based approach is not the way to go, because again, a learning based approach isn't necessarily superior.

However, if the SIFT approach isn't giving you good enough results, definitely start thinking of NN stuff, but at that point, using the "bad" method to label the data is probably a bad idea.

Also in relation, I think you could potentially be underestimating the amount of data that is needed for this. You mentioned data in the thousands, but that's honestly, not a lot. You would need a lot more, I think.

One way I would think about instead doing this -

  • Do SIFT keyponits detection for a sample reference image.
  • Manually filter out keypoints that does not belong to the things in the image that are invariant. That is, just take keypoints at the locations in the image that is guaranteed (or very likely) to be always present.
  • When you get a new image, compute the keypoints and do matching with the reference image.
  • Set some threshold of the ratio of good matches to the total number of matches.

Depending on your application, this might give you good enough results.

If not, and if you really want your solution to be NN based, I would say you need to manually label the dataset as opposed to using SIFT.

Ananda
  • 2,925
  • 5
  • 22
  • 45
  • Ok I think there is a small misunderstanding here. I would be doing the labeling based on a supervised approach. I already have a corpus of images for which I know which ones are meant to pass and which ones are meant to fail. Where I am stuck is how to quantify the difference between pairs of images in my corpus in a feature-vector using SIFT, that I can then label. The idea then is to use learning to generate a function that can predict that given a certain pair of images, we can generate the feature vector and get the appropriate labeling. Does that make sense? – bumblyboi Dec 15 '20 at 05:48
  • But I could use the SIFT labels like you suggest, but how do I know where the threshold lies between pass and fail? Is there a way to tune that parameter somehow? – bumblyboi Dec 15 '20 at 05:57