Printing Press Fuzzy Identification Based on Pixel Distribution Probability of Character Image

Printing press identification can be realized with comparison between the same printed characters by different printing presses. This paper proposed a new method of printing press identification. It takes advantage of the method of Casey and Nagy and overcomes the disadvantage of the traditional the method of character recognition. In this method, the pixel distribution probability of character image is the basal index. The minimal distance product and the maximal fuzzy correlation measure are the double-optimized evaluation indexes. The precision of this method is on the pixel level. The tiny difference of same printed characters by different printing presses can be identified by the difference of pixel of character image. So the pixel distribution probability of character image is different too. With the experiment of printing press identification, the accurate identification rate is about 96.18%. The result of experiment showed printing press identification based on pixel distribution probability is effective and feasible.