In this paper, we propose a fast and efficient algorithm to classify multi-national banknote images using size information and multi-template correlation matching. Since different banknotes have different sizes, this information was considered to be an important characteristic. Using the size information, we generated a size map to group the banknotes. Then, we determined the discriminant areas of each banknote that have high correlations among the same kind of banknote and low correlations with different kinds of banknotes. Post-processing was applied to handle degradations such as writing, aging, etc. The algorithm was tested using 55 banknotes of 30 different denominations from five countries: KRW, USD, EUR, CNY, and RUB. The experimental results showed 100% classification accuracy for unsoiled banknotes and 99.8% classification accuracy for soiled banknotes. The average processing time was about 4.83. ms per banknote.
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Computer Science Applications
- Cognitive Neuroscience