Recognizing Check Magnetic Code Based on Peak-Valley Location and Amplitude

Abstract

Magnetic code is widely used in check, securities, tax invoice, etc. However, the traditional recognizing and reading method of magnetic code is mostly based on correlation coefficient and it takes significant time and cost. After analyzing the characteristics of magnetic code signals in E-13B standard, this paper has proposed a new algorithm based on the peak-valley location and amplitude (PVLA) to simplify the calculation and system design. Firstly, the magnetic code signal is separated into magnetic ink character signals by the thresholds of peak and valley. Secondly, the features of the peak-valley location (PVL) and peak-valley amplitude(PVA) of each magnetic ink character signal are extracted and normalized, then the nearest neighbor recognition algorithm based on the vectors of peak-valley location and amplitude is utilized to recognize the magnetic code. The recognition results and statistical parameters from a large number of experiments show that the new method has higher recognition rate and better robustness. In addition, the new algorithm only involves additions and subtractions, so it has a lower computation cost.