I have a slot game screenshot. It has 20 different symbols (mainly fruits). I can cut the image in such a way that all 20 symbols to be presented as 20 separate images. There are 10 different symbols in the paytable. I need to classify each image of a symbol to its number in the paytable.
I am doing these calculations in Java. What approach will you suggest for such a classification problem?
If you have an idea for a proper Java framework it will be great to share.
The other part of the question is what algorithms are most proper? I am thinking of multilayer perception or Kohonen's self-organizing maps. What else can be used?
- Badges
- Science topic
- Similar topics
- Data Mining
- Classification
More Todor Balabanov's questions See All
Similar questions and discussions