Next Article in Journal
A Potassium Ion-Exchanged Glass Optical Waveguide Sensor Locally Coated with a Crystal Violet-SiO2 Gel Film for Real-Time Detection of Organophosphorus Pesticides Simulant
Previous Article in Journal
A Multi-Protocol IoT Platform Based on Open-Source Frameworks
Open AccessArticle

Machine Learning-Based Fast Banknote Serial Number Recognition Using Knowledge Distillation and Bayesian Optimization

Department of Electronics and Electrical Engineering, Ewha Womans University, Seoul 03760, Korea
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Sensors 2019, 19(19), 4218; https://doi.org/10.3390/s19194218
Received: 8 July 2019 / Revised: 22 September 2019 / Accepted: 25 September 2019 / Published: 28 September 2019
(This article belongs to the Section Intelligent Sensors)
We investigated a machine-learning-based fast banknote serial number recognition method. Unlike existing methods, the proposed method not only recognizes multi-digit serial numbers simultaneously but also detects the region of interest for the serial number automatically from the input image. Furthermore, the proposed method uses knowledge distillation to compress a cumbersome deep-learning model into a simple model to achieve faster computation. To automatically decide hyperparameters for knowledge distillation, we applied the Bayesian optimization method. In experiments using Japanese Yen, Korean Won, and Euro banknotes, the proposed method showed significant improvement in computation time while maintaining a performance comparable to a sequential region of interest (ROI) detection and classification method. View Full-Text
Keywords: banknote serial number recognition; deep learning; knowledge distillation banknote serial number recognition; deep learning; knowledge distillation
Show Figures

Figure 1

MDPI and ACS Style

Choi, E.; Chae, S.; Kim, J. Machine Learning-Based Fast Banknote Serial Number Recognition Using Knowledge Distillation and Bayesian Optimization. Sensors 2019, 19, 4218.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop