Removing noise from handwritten character images using U-Net through online learning

Rina Komatsu; Tad Gonsalves

doi:10.1117/12.2514045

29 October 2018 Removing noise from handwritten character images using U-Net through online learning

Rina Komatsu, Tad Gonsalves

Proceedings Volume 10836, 2018 International Conference on Image and Video Processing, and Artificial Intelligence; 108360K (2018) https://doi.org/10.1117/12.2514045
Event: 2018 International Conference on Image, Video Processing and Artificial Intelligence, 2018, Shanghai, China

Abstract

Today, recognizing offline handwritten character images is still hard challenge. This is because there are the obstacles, ‘noise’ produced in scanning process. Noise makes handwritten character distorted, murky, and blurred. As a result, it become hard to read and recognize these images for human. In this study, we tried to get rid of various noises using CNN architecture named “U-Net” to analyze 607,200 sample images consisting of 3,036 Japanese characters. Finally, our results indicate that the “U-Net” has efficient ability to remove noise and enhance the parts of strokes even through there are a huge variety of handwritten styles which includes various noises.

Citation Download Citation

Rina Komatsu and Tad Gonsalves "Removing noise from handwritten character images using U-Net through online learning", Proc. SPIE 10836, 2018 International Conference on Image and Video Processing, and Artificial Intelligence, 108360K (29 October 2018); https://doi.org/10.1117/12.2514045

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