Share Email Print

Proceedings Paper

A convolutional neural network with sign-to-position format conversion
Author(s): Tomohito Mizokami; Kuntopng Wararatpanya; Yoshimitsu Kuroki
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper tries improving image recognition accuracy with Convolutional Neural Networks (CNNs). CNNs are one of state-of-the-art image recognition frameworks, and have used the Rectified Linear Unit (ReLU) as the activation function. However, the ReLU rectifies negative values to zero. This paper applies the Sign-to-Position (S/P) format conversion after convolutional procedures to eliminate the rectification loss. Experimental results show that the proposed method improves the recognition accuracy of the MNIST and Fashion-MNIST data set by 0.50% and 1.30% compared with a conventional CNN respectively. The S/P format conversion also contributes to negative image recognition, and results in 12.58% and 3.66% higher accuracy.

Paper Details

Date Published: 22 March 2019
PDF: 4 pages
Proc. SPIE 11049, International Workshop on Advanced Image Technology (IWAIT) 2019, 110493Y (22 March 2019); doi: 10.1117/12.2521349
Show Author Affiliations
Tomohito Mizokami, National Institute of Technology, Kurume College (Japan)
Kuntopng Wararatpanya, King Mongkut's Institute of Technology Ladkrabang (Thailand)
Yoshimitsu Kuroki, National Institute of Technology, Kurume College (Japan)

Published in SPIE Proceedings Vol. 11049:
International Workshop on Advanced Image Technology (IWAIT) 2019
Qian Kemao; Kazuya Hayase; Phooi Yee Lau; Wen-Nung Lie; Yung-Lyul Lee; Sanun Srisuk; Lu Yu, 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?