Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal IAES International Journal of Robotics and Automation (IJRA)
Chiang, Pei-Shan
Unknown Affiliation
Automotive Engineering Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Use of artificial intelligence in banknote reconstruction Wu, Yi-Chang; Chiang, Pei-Shan; Liu, Yao-Cheng; Huang, Ru-Yi
IAES International Journal of Robotics and Automation (IJRA) Vol 13, No 4: December 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijra.v13i4.pp410-422

Abstract

Banknotes may be damaged during various events, such as floods, fires, insect infestations, and mechanical or manual shredding. Disaster victims might need to perform banknote reconstruction when applying for currency exchange, or investigative agencies might need to conduct such reconstruction during evidence collection. When the number of banknote fragments is small, they can be manually assembled; however, when this number is large, manual assembly becomes increasingly difficult and time-consuming. Therefore, an automated and effective method is required for banknote reconstruction. The process of banknote reconstruction can be considered similar to solving a large-scale jigsaw puzzle. This study employed an artificial intelligence (AI) system to reconstruct damaged banknotes. A robotic arm was used to replace manual separation and automated digital image processing techniques, and AI image registration technology, deep learning, and logical operations were utilized. A deep convolutional neural network was used to estimate the relative homography between images, and fragmented banknotes were mapped to a reference banknote for image transformation, thereby reconstructing the damaged banknotes. Additionally, a repetitive matching method was established to optimize the matching results to achieve the best possible mapping and enhance validation efficiency.
Co-Authors Huang, Ru-Yi Liu, Yao-Cheng Wu, Yi-Chang