A RMB optical character recognition system using FPGA

Optical Character Recognition (OCR) is an important area of pattern recognition. Automatic OCR system is one kind of intelligent system which is very important to the current automation systems such as ATMs. In this paper, a RMB OCR (ROCR) system is implemented using FPGA, which consists of Character Segmentation (CS) module and OCR module. The CME M7 was used for the implementation. 83.30% Logic Elements (LEs) of a M7 FPGA was used for the system implementation. The whole system runs with a maximum frequency of 100MHz and is capable of processing one image per 6ms with the successful recognition rate at 98.45%

[1]  Hanseok Ko,et al.  Effective character segmentation for license plate recognition under illumination changing environment , 2016, 2016 IEEE International Conference on Consumer Electronics (ICCE).

[2]  Xiaojun Zhai,et al.  Automatic Number Plate Recognition on FPGA , 2013, 2013 IEEE 20th International Conference on Electronics, Circuits, and Systems (ICECS).

[3]  Yang Jing-yu.  An Improved Drop-fall Algorithm for Handwritten Numerals Segmentation , 2007 .

[4]  Huadong Xia,et al.  The study of license plate character segmentation algorithm based on vetical projection , 2011, 2011 International Conference on Consumer Electronics, Communications and Networks (CECNet).

[5]  Xiaojun Zhai,et al.  Improved number plate character segmentation algorithm and its efficient FPGA implementation , 2012, Journal of Real-Time Image Processing.

[6]  Guoyou Wang,et al.  A novel approach for segmentation of touching characters on the license plate , 2013, International Conference on Graphic and Image Processing.

[7]  Youngwoo Yoon,et al.  Blob extraction based character segmentation method for automatic license plate recognition system , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[8]  Ligang Miao,et al.  License plate character segmentation algorithm based on variable-length template matching , 2012, 2012 IEEE 11th International Conference on Signal Processing.