Offline writer verification using pen pressure information from infrared image

Abstract

Writer verification methods from handwriting images have been widely used in biometrics, forensic casework and so on. However, their performance conducted by a computer is still far behind that of human beings. This study proposes an offline writer verification method which uses a new hybrid feature. The characteristics of this new feature are the combination of shape and pen pressure information. For shape information, the authors use the weighted direction code histogram, which is often used in Japanese handwriting recognition and writer verification methods. For pen pressure information, the authors use the texture features of infrared (IR) images obtained from a multi-band image scanner. Although the simple use of pen pressure information encoded in the IR image cannot improve the geometric mean (g-mean)-based error rate, the use of clipping process and second-order statistics can decrease the g-mean-based error rate from 4.8 to 3.2%.