Experimental Study of Convolutional Neural Network Architecture for Pattern Recognition in Images; Lecture Notes in Networks and Systems; Vol. 1118 : Software Engineering Methods Design and Application

Experimental Study of Convolutional Neural Network Architecture for Pattern Recognition in Images; Lecture Notes in Networks and Systems; Vol. 1118 : Software Engineering Methods Design and Application

Detalles Bibliográficos
Parent link:Lecture Notes in Networks and Systems.— .— Cham: Springer
Vol. 1118 : Software Engineering Methods Design and Application.— 2024.— P. 656-667
Autor principal: Botygin I. A. Igor Aleksandrovich
Otros Autores: Sherstnev V. S. Vladislav Stanislavovich, Sherstneva A. I. Anna Igorevna
Sumario:Title screen
The choice of optimal tools and instruments of synthesis and modelling of neural network for pattern recognition in images is carried out. A comparative analysis of the results of training a neural network using the open library of machine learning TensorFlow, libraries Keras and NumPy, data sets from the open database MNIST in the recognition of handwritten input has been carried out. The software based on the neural network of the convolutional type by topology is developed, which solves the problems of handwritten numerical symbols recognition. The main design, technological and technical-operational characteristics: accuracy 99.2%, mini-packages - 200 pieces, the ratio of training and training sets - 0.2, the number of epochs - 10. The created software can be used in areas of visual analysis of data of paper documentation of enterprises, where it is necessary to transfer data from paper to electronic form. And also, to serve as a starting point for the development of the core of more powerful software for handwriting recognition, namely, a bunch of digits, symbols (car numbers, postal codes, etc.)
Текстовый файл
AM_Agreement
Lenguaje:inglés
Publicado: 2024
Materias:
Neural Network
Convolutional Layer
Image Recognition
Overfitting
Underfitting
электронный ресурс
труды учёных ТПУ
Acceso en línea:https://doi.org/10.1007/978-3-031-70285-3_50
Formato: Electrónico Capítulo de libro
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=680012

Ejemplares similares

Ejemplares similares