I'm new in Opencv, I want to comparison two image by theirs corner features rather than others, I tried SURF, SIFT, ORB ..., but their are not suit of me, could someone give me some suggestion about this? for example, the below image image1 and image2 are similar, because their have a lot of same corners ( although it isn't accurate ), but the image3 isn't similar as the 1 and 2, thanks.
There are a lot of things to try here, and others can suggest you others solutions, but here goes mine:
Use the Minutiae algorithm (the algorithm used for fingerprint identification). In the minutiae algorithm, a set of common features are extracted, such as:
These are called Minutiae. As you can see these features are pretty similar to the corners of your images. I suggest you the following procedure:
1) Find the corners (You already did this)
2) Assign each corner to a class of minutiae (e.g. one of the classes of the image). You can do this using a local binary pattern algorithm or just follow the usual recipe from the fingerprint algorithm (see the link at the end or search on Google).
3) To compute the similarity just do some voting. For instance, let's assume an image (I will call it A) has 4 minutiae of type a) and two of type E). To compute the similarity in a new image I will have to compute these minutiae in the new image. Then, see how many items per class both images share. You can add as many features or kind of minutiae as you want to make your algorithm more robust (and also complicated).
In any case, you can look in Google at the Minutiae fingerprint recognition algorithm (is one of the most famous digital image processing algorithms). Here goes one of the multiple slides you can find explaining the algorithm
https://is.muni.cz/el/1433/jaro2008/PV204/um/finger/MinutiaeBasedFpMatching.pdf
Just take care to modify the main algorithm to suit your necessities
Hope it helps
