Creation of a system for recognizing a person’s gender by his handwriting

Myasoutov Ramil Khamzyaevich

This paper proposes a solution to the problem of identifying a person’s gender by his handwriting. To solve this problem, the author suggests using a system complex consisting of several parts using neural networks and probabilistic - static decision-making methods. The work demonstrates a prototype of this system and also describes the overall interaction of submodules. Various methods for solving the classification problem using neural networks are considered and a comparative characteristic of the operation of each of the methods is given.

Keywords:convolutional neural networks, decision-making methods, handwriting analysis, computer vision.