Construction of computer system for microobjects recognition based on neural networks

  • Authors:

  • Ulugbek Kh. Narzullaev;Akmal R. Akhatov;Olim I. Jumanov

  • Affiliations:

  • Samarkand State University Named after Alisher Navoyi, Samarkand, Uzbekistan;Samarkand State University Named after Alisher Navoyi, Samarkand, Uzbekistan;Samarkand State University Named after Alisher Navoyi, Samarkand, Uzbekistan

  • Venue:
  • CASC'07 Proceedings of the 10th international conference on Computer Algebra in Scientific Computing
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose a new and efficient approach for solving the tasks of the microobjects recognition based on using the neural network (NN) and work out a computer system of image visualization, recognition, and classification of the microobjects on the samples of the pollen grains. The technology is developed for a preliminary processing of images of the microobjects on the basis of the "Snake" model. The principle of teaching of formal neuron and mathematical model of teaching multilayer perceptron for recognition of the microobjects is proposed. An algorithm is developed for teaching the NN of the returning distribution, subject domain, and methods of classes of computer system.