Removing Noise from Handwritten Character Images using U-Net through Online Learning

被引：0

作者：

Komatsu, Rina ^{[1
]}

Gonsalves, Tad ^{[1
]}

机构：

[1] Sophia Univ, Fac Sci & Technol, Chiyoda Ku, 7-1 Kioicho, Tokyo 1028554, Japan

来源：

2018 INTERNATIONAL CONFERENCE ON IMAGE AND VIDEO PROCESSING, AND ARTIFICIAL INTELLIGENCE | 2018年 / 10836卷

关键词：

Deep Learning; image processing; remove noise; U-Net;

D O I：

10.1117/12.2514045

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页数：5

共 50 条

[1] Mosaic Images Segmentation using U-net
Fenu, Gianfranco
Medvet, Eric
Panfilo, Daniele
Pellegrino, Felice Andrea
ICPRAM: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION APPLICATIONS AND METHODS, 2020, : 485 - 492
[2] Building Extraction from RGB Satellite Images using Deep Learning: A U-Net Approach
Temenos, Anastasios
Protopapadakis, Eftychios
Doulamis, Anastasios
Temenos, Nikos
THE 14TH ACM INTERNATIONAL CONFERENCE ON PERVASIVE TECHNOLOGIES RELATED TO ASSISTIVE ENVIRONMENTS, PETRA 2021, 2021, : 391 - 395
[3] Polyp Segmentation in Colonoscopy Images using U-Net and Cyclic Learning Rate
Bulut, Betul
Butun, Ertan
Kaya, Mehmet
2022 INTERNATIONAL CONFERENCE ON DECISION AID SCIENCES AND APPLICATIONS (DASA), 2022, : 1149 - 1152
[4] Flooded Areas Detection through SAR Images and U-NET Deep Learning Model
Pech-May, Fernando
Sanchez-Hernandez, Julio Victor
Lopez-Gomez, Luis Antonio
Magana-Govea, Jorge
Mil-Chontal, Edna Mariel
COMPUTACION Y SISTEMAS, 2023, 27 (02): : 449 - 458
[5] Detecting Buildings and Nonbuildings from Satellite Images Using U-Net
Alsabhan, Waleed
Alotaiby, Turky
Dudin, Basil
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
[6] U-Net Architecture for Ancient Handwritten Chinese Character Detection in Han Dynasty Wooden Slips
Shimoyama, Hojun
Yoshida, Soh
Fujita, Takao
Muneyasu, Mitsuji
IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2023, E106A (11) : 1406 - 1415
[7] Segmentation of Palm Vein Images Using U-Net
Marattukalam, Felix
Abdulla, Waleed H.
2020 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2020, : 64 - 70
[8] Segmentation of Nano-Particles from SEM Images Using Transfer Learning and Modified U-Net
Sanan, V. Sowmya
Isaac, R. S. Rimal
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2025, 16 (01) : 662 - 677
[9] Segmentation of Mammogram Images Using U-Net with Fusion of Channel and Spatial Attention Modules (U-Net CASAM)
Robert Singh, A.
Vidya, S.
Hariharasitaraman, S.
Athisayamani, Suganya
Hsu, Fang Rong
Lecture Notes in Networks and Systems, 2024, 966 LNNS : 435 - 448
[10] Accurate Road Detection from Satellite Images Using Modified U-net
Constantin, Alexandre
Ding, Jian-Jiun
Lee, Yih-Cherng
2018 IEEE ASIA PACIFIC CONFERENCE ON CIRCUITS AND SYSTEMS (APCCAS 2018), 2018, : 423 - 426

← 1 2 3 4 5 →