During the past decade, a remarkable progress has been achieved in the field of machine-printed and handwritten word recognition, and many applications, such as automatic reading of postal addresses, bank checks and forms have been emerged. However, most of the published works deal with the recognition of Latin and Chinese scripts. Persian script recognition has progressed slowly mainly due to the special characteristics of this language. This book, therefore, provides a new method for recognition of the Persian handwriting words in off-line mode. Based on the characteristic of Persian writing, four different feature extraction methods are introduced. To classify the handwritten words a weighted rule-based classifier is proposed.Experiments carried out on 3000 machine-printed Persian words shown promising performance results of 91.81% when testing and training sets are different, and 100% when training and testing sets have 8% overlap. The recognition rate of 71.34% is achieved for the handwritten word recognition system with 9,326 lexicon size.