Aida Sheikh - Department of Computer, Qazvin Branch , Islamic Azad university, Qazvin, Iran
Hassan Khotanlou - Department of Computer, Bu-Ali Sina University, Hamedan, Iran.

There are many ways to recognize the identity ofindividuals and authenticate them. Recognition andauthentication of individuals with the help of theirhandwriting is regarded as a research topic in recent years. Itis widely used in the field of security, legal, access controland financial activities. This article tries to examines theidentification and authentication of individuals in Persian(Farsi) handwritten texts so that the identity of the author canbe determined with a handwritten text. The proposed systemfor recognizing the identity of the author in this study can bedivided into two main parts: one part is intended for trainingand the other for testing. To assess the performance ofintroduced characteristics, the Hidden Markov Model is usedas the classifier; thus, a model is defined foreach angularcharacteristic. The defined angular models are connected by aspecific chain network to form a comprehensive database forclassification. This database is then used to determine andauthenticate the author.

Persian handwriting recognition, authentication,Off-line, Hidden Markov Model