I want to realize the recognition of images on the screen.

The collection of pictures is static, i.e. invariably the number and type of pictures (no distortion, etc.). The block that will recognize the images is known for all possible options.
I assume that recognition will be made on the basis of a comparison of the current image (s) with all possible. How to start working on a task?

Not very deep googling gave the OpenCV library.

Closed due to the fact that it is necessary to reformulate the question so that the participants can give an objectively correct answer Vladimir Martyanov , aleksandr barakin , Grundy , Vartlok , PashaPash ♦ 15 Apr '16 at 20:42

The question gives rise to endless debates and discussions based not on knowledge, but on opinions. To get an answer, rephrase your question so that it can be given an unambiguously correct answer, or delete the question altogether. If the question can be reformulated according to the rules set out in the certificate , edit it .

  • Well, start with OpenCV. - Vladimir Martyanov

1 answer 1

Maybe you need a neural network.

I tried the AForge library, and still watch the video on youtube . There, in general, this library is used. Plus, a very good theoretical base. Look for videos with titles AIML-4 -...

  • Why do we need a neural network if all the options are known and there are no distortions? - Qwertiy ♦
  • Thanks for the link to the channel. @Qwertiy how would you solve this problem? - cruim 4:05 pm
  • @cruim, in fact, as you described in the question - by comparison with samples. - Qwertiy ♦