Printer Fuzzy Identification based on Pixel Distribution Probability of Chinese character Image

摘要：

Printer Identification can be realized with comparison between the same printed characters by different printers.This paper proposed a new method of printer identification.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 evaluation indexes.The precision of this method is on the pixel level.The tiny difference of same printed characters by different printers can be identified by the difference of pixel of character image.Thus,the pixel distribution probability of character image is different too.It is the key to solve the problem of printer identification.With the experiment of laser and ink printer identification,the accurate identification rate exceeded 96.88％.The result of experiment showed the printer identification based on pixel distribution probability is effective and feasible.

关键词： printer identification pixel distribution probability character image the minimal distance product the maximal fuzzy correlation measure.

作者: Ning Wang

作者单位: School of Computer Science and Engineering,South China University of Technology,Guangzhou,China Guangzhou Public Security Bureau,Guangzhou,China

会议类型: 国际会议

会议名称: International Conference on Modelling,Identification and Control(模拟、鉴定、控制国际会议)

会议地点: 上海

会议语种:英文

在线出版日期: 2008-06-29（万方平台首次上网日期，不代表论文的发表时间）