| Summary: | Automatic recognition of face banknotes is an important task in practical banknote handling. Research on this task has mostly involved methods applied to automatic sorting machines with multiple imaging sensors or that use specialized sensors for capturing banknote images in various light wavelengths. However, they require specialized devices. Meanwhile, smartphones are becoming more popular and can be useful imaging devices. This project will investigate and propose the best method for classifying fake and genuine banknotes using visible-light images captured by smartphone cameras based on convolutional neural networks. This project will focus on Malaysia banknotes only. Finally, the result of precision, recall and loss for this project are 0.849, 0.971 and 0.011586.
|
|---|