Methods of the development of the architecture of the neural networks for identification and authentication of individuals
Journal: Physical Sciences and Technology (Vol.7, No. 34)Publication Date: 2020-12-29
Authors : O. Y. Golikov; M. A. Ramos;
Page : 44-49
Keywords : biometric identification of individuals; three-dimensional object recognition; convolutional neural network; deep machine learning; subsampling.;
Abstract
This paper deals with the neural network methods of the implementation of systems of identification of individuals based on videos and photographs. Over the last few decades, it has been considered to be one of the most powerful tools and has become very popular in the literature as it is able to handle a huge amount of data. The neural network architectures used in modern biometric identification systems have been reviewed. Based on the research conducted in this field, an approach was developed that can improve the accuracy of object recognition in photo and video images by increasing the quality of the attributes of the weights and reducing the number of the weights, as well as the number of the connections. The basis of the developed neural network model is a multilayer perceptron; the main system is a convolutional neural network. The neural network model has been implemented using the Python programming language with the most popular machine learning libraries Keras and TensorFlow. In addition, we will also enumerate the parameters that affect CNN efficiency
Other Latest Articles
- IDENTIFICATION AND CHARACTERIZATION OF PHLEBOTOM POPULATION LEISHMANIA VECTORS IN THE REGION OF MEKNES
- BRAIN TUMOUR SEGMENTATION USING GENETIC AND ANT COLONY
- Current and capacitance hysteresis in porous semiconductor nanofilms
- THE IMPACT OF E-BANKING SERVICES ON CUSTOMER SATISFACTION: THE CASE OF COMMERCIAL BANK OF ETHIOPIA IN NEKEMTE
- Study of structural changes in ZrO2 ceramics irradiated with heavy ions of Kr15+ with an energy of 147 MeV
Last modified: 2021-02-23 21:23:40