State of the art in off-line writer identification of handwritten text and survey of writer identification of Arabic text

In this paper we present the state of the art in writer identification and verification of handwritten text. In addition, a special and extensive survey of writer identification and verification of Arabic handwritten text is also included. Different feature extraction techniques are addressed showing the different research groups’ efforts as well as individual efforts. The different classification approaches, e.g. minimum distance classifiers and statistical classifiers, used for identification by writer and verification by different groups and individuals are presented. Identification results of surveyed publications are investigated and tabulated for ease of reference. Examples of writer identification and verification of others languages are addressed. An extensive survey of databases used in writer identification and verification for Latin and Arabic text is presented. Conclusions relevant to writer identification of Arabic text are discussed and future directions stated.