Machine learning-based fast banknote serial number recognition using knowledge distillation and bayesian optimization

Eunjeong Choi, Somi Chae, Jeongtae Kim

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

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, KoreanWon, 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.

Original languageEnglish
Article number4218
JournalSensors (Switzerland)
Volume19
Issue number19
DOIs
StatePublished - 1 Oct 2019

Keywords

  • Banknote serial number recognition
  • Deep learning
  • Knowledge distillation

Fingerprint

Dive into the research topics of 'Machine learning-based fast banknote serial number recognition using knowledge distillation and bayesian optimization'. Together they form a unique fingerprint.

Cite this