Low-Quality Banknote Serial Number Recognition Based on Deep Neural Network

• Published in: Journal of information processing systems 2020, 16(1), 61, pp.224-237
• Main Authors: 장운수, Kun Ha Suh, 이의철
• Format: Article
• Language: English
• Subjects: 컴퓨터학
• ISSN: 1976-913X; 2092-805X
• DOI: 10.3745/JIPS.04.0160

Recognition of banknote serial number is one of the important functions for intelligent banknote counterimplementation and can be used for various purposes. However, the previous character recognition method islimited to use due to the font type of the banknote serial number, the variation problem by the solid status, andthe recognition speed issue. In this paper, we propose an aspect ratio based character region segmentation anda convolutional neural network (CNN) based banknote serial number recognition method. In order to detect thecharacter region, the character area is determined based on the aspect ratio of each character in the serial numbercandidate area after the banknote area detection and de-skewing process is performed. Then, we designed andcompared four types of CNN models and determined the best model for serial number recognition. Experimental results showed that the recognition accuracy of each character was 99.85%. In addition, it wasconfirmed that the recognition performance is improved as a result of performing data augmentation. Thebanknote used in the experiment is Indian rupee, which is badly soiled and the font of characters is unusual,therefore it can be regarded to have good performance. Recognition speed was also enough to run in real timeon a device that counts 800 banknotes per minute. KCI Citation Count: 0