A convolutional neural network with sign-to-position format conversion

Tomohito Mizokami; Kuntopng Wararatpanya; Yoshimitsu Kuroki

doi:10.1117/12.2521349

22 March 2019 A convolutional neural network with sign-to-position format conversion

Tomohito Mizokami, Kuntopng Wararatpanya, Yoshimitsu Kuroki

Proceedings Volume 11049, International Workshop on Advanced Image Technology (IWAIT) 2019; 110493Y (2019) https://doi.org/10.1117/12.2521349
Event: 2019 Joint International Workshop on Advanced Image Technology (IWAIT) and International Forum on Medical Imaging in Asia (IFMIA), 2019, Singapore, Singapore

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.

Citation Download Citation

Tomohito Mizokami, Kuntopng Wararatpanya, and Yoshimitsu Kuroki "A convolutional neural network with sign-to-position format conversion", Proc. SPIE 11049, International Workshop on Advanced Image Technology (IWAIT) 2019, 110493Y (22 March 2019); https://doi.org/10.1117/12.2521349

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