Recognizing Check Magnetic Code Based on Peak-Valley Code and Distance

Abstract

The check is a popular form for the non-cash payment and accounts for more than 50% of the non-cash transactions. Magnetic ink character recognition system can recognize the check magnetic code automatically and get the information of the bank and account. In magnetic ink character recognition system, the recognizing algorithm is mostly based on correlation coefficient. The computational cost of this algorithm is very high. This paper has proposed a new algorithm based on the peak-valley code and peak-valley distance after analyzing the characteristics of magnetic code signals in E-13B standards to simplify the calculations and system design. Firstly, the magnetic code signal is normalized and separated into magnetic character signals by the thresholds of peak and valley. Secondly, the features of the peak-valley code and peak-valley distance of each magnetic character signal are extracted, then the recognition based on peak-valley code and the nearest neighbor recognition algorithm based on peak-valley distance are utilized to recognize the magnetic code. The recognition results and statistical parameters from a large number of experiments show that the new method has high recognition rate, good robustness and low computational cost.