Exploring the importance of pooling schemes for convolutional neural networks in hiragana character classification

Hector Osuna; Marcos Moroyoqui; David Espina; Ulises Orozco-Rosas; Kenia Picos

doi:10.1117/12.2633122

3 October 2022 Exploring the importance of pooling schemes for convolutional neural networks in hiragana character classification

Hector Osuna, Marcos Moroyoqui, David Espina, Ulises Orozco-Rosas, Kenia Picos

Author Affiliations +

Proceedings Volume 12225, Optics and Photonics for Information Processing XVI; 122250C (2022) https://doi.org/10.1117/12.2633122
Event: SPIE Optical Engineering + Applications, 2022, San Diego, California, United States

Abstract

This paper presents a comparison between the implementation of different convolutional neural network models varying the usage of pooling layers to address the problem of hiragana character classification. This study is focused on understanding how the selection and usage of different pooling layers affect the accuracy convergence in a model. To assess this situation eight models were tested with different configurations and using minimum pooling, average pooling, and max pooling schemes. Experimental results to validate the analysis and implementation are provided.

Conference Presentation

Citation Download Citation

Hector Osuna, Marcos Moroyoqui, David Espina, Ulises Orozco-Rosas, and Kenia Picos "Exploring the importance of pooling schemes for convolutional neural networks in hiragana character classification", Proc. SPIE 12225, Optics and Photonics for Information Processing XVI, 122250C (3 October 2022); https://doi.org/10.1117/12.2633122

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available