Good day!

I am writing a thesis, the theme is text recognition. At the entrance to the picture with the symbol - at the output of the recognized symbol. The program is implemented using a neural network. Currently able to recognize letters, numbers, math. characters.

The program for the diploma must be innovative.

I, for one, see the innovativeness of my program in that, compared to other recognition programs based on neural networks (little-known programs), it gives a less or less good result ...

I want to address you: What do you think can be positioned as innovativeness for my program? .. I am very interested to hear your opinion ...

Thanks a lot in advance!

Closed due to the fact that it is necessary to reformulate the question so that you can give an objectively correct answer to the participants of Kromster , Regent , Cyrus , aleksandr barakin , xaja Sep 8 '15 at 7:26 .

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 .

  • one
    > it is compared to other recognition programs based on neural networks. This is a reason to think about whether you use the tool. If I were in your commission I would definitely ask the question: “What determines the choice of the method of constructing a model for recognition?”. If you do not know the answer, such an innovation looks like a flaw . - Vladislav Pyatkov
  • For example, innovation may be that the alphabet is not known in advance, but it is known that it is limited and the text for recognition consists only of their alphabet. The program that will be able to compose the alphabet and recognize it will be innovative :-) What your NA will recognize better still needs to be proved :-) - ReinRaus

0