|
The Analysis System of Counterfeit Banknote by Photo on Smartphone using Deep Learning Technique |
|---|---|
| รหัสดีโอไอ | |
| Creator | Nattavadee Hongboonmee |
| Title | The Analysis System of Counterfeit Banknote by Photo on Smartphone using Deep Learning Technique |
| Contributor | Kanin Pratoomthong |
| Publisher | Faculty of Engineering and Technology, Mahanakorn University of Technology |
| Publication Year | 2563 |
| Journal Title | Journal of Information Science and Technology |
| Journal Vol. | 10 |
| Journal No. | 2 |
| Page no. | 90-100 |
| Keyword | Counterfeit Banknote, Image Classification, Convolutional Neural Network, Deep Learning, TensorFlow |
| URL Website | https://tci-thaijo.org/index.php/JIST |
| Website title | Journal of Information Science and Technology |
| ISSN | 2651-1053 |
| Abstract | The aims of this research is to develop system used for classifying of counterfeit banknote using image processing with deep learning technology to help the analysis of counterfeit banknotes for use on smartphones. The operation consisted of 5 steps: 1) Collecting 10 samples of datagroup, 100 images per group, a total of 1,000 images.2) Develop classification modeling using deep convolutional neural network technique with MobileNet algorithms through the TensorFlow library, train our model for 500 rounds. 3) Model evaluation. 4) Development of a user interface as a smartphone application. 5) System testing. The results of the experiment showed that a convolutional neural network model capable of accurately recognizing counterfeit banknotes with accuracy of 98.00%. The results of the application performance test. It was found that the application was able to analyze counterfeit banknotes using smartphone camera images and was able to recognize the images of all 10 types of banknotes with an average accuracy of 80.00%. In conclusion, this application can useful in detect of counterfeit banknotes. |
