Share Email Print

Proceedings Paper

Analysis of the convolutional neural network architectures in image classification problems
Author(s): Sergey Leonov; Alexander Vasilyev; Artyom Makovetskii; Vitaly Kober
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The work aims to construct effective methods for image classification. For this purpose, we analyze neural network convolutional architectures, which understand as the number of network layers, elements in the input and output layers, the type of activation functions, and the connections between neurons. We studied the application of various configurations of convolutional networks for solving image classification problems. Numerical experiments on BOSPHORUS database were conducted; we described the results in this work. A neural network architecture has been developed based on the analysis of convolutional neural networks, which for the data set under consideration, provides the most accurate classification. A new method combines the advantages of using RGB images and depth maps as input data is proposed for processing the output of a convolutional network.

Paper Details

Date Published: 6 September 2019
PDF: 8 pages
Proc. SPIE 11137, Applications of Digital Image Processing XLII, 111372E (6 September 2019); doi: 10.1117/12.2529232
Show Author Affiliations
Sergey Leonov, Chelyabinsk State Univ. (Russian Federation)
Alexander Vasilyev, Saint-Petersburg State Polytechnical Univ. (Russian Federation)
Artyom Makovetskii, Chelyabinsk State Univ. (Russian Federation)
Vitaly Kober, Chelyabinsk State Univ. (Russian Federation)
CICESE (Mexico)

Published in SPIE Proceedings Vol. 11137:
Applications of Digital Image Processing XLII
Andrew G. Tescher; Touradj Ebrahimi, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?