Abstract—Nowadays, OCR systems have got several applications and are increasingly employed in daily life. Much research has been done regarding the identification of Latin, Japanese, and Chinese characters. However, very little investigation has been performed regarding Farsi/Arabic characters recognition. Probably the reason is difficulty and complexity of those characters identification compared to the others and limitation of IT activities in Farsi and Arabic speaking countries. In this paper, a technique has been employed to identify isolated Farsi/Arabic characters. A chain code based algorithm along with other significant peculiarities such as number and location of dots and auxiliary parts, and the number of holes existing in the isolated character has been used in this study to identify Farsi/Arabic characters. Experimental results show the relatively high accuracy of the method developed when it is tested on several standard Farsi fonts. Keywords—Farsi characters, OCR, feature extraction, chain code. I. INTRODUCTION HE Farsi language has got 32 characters which 28 of them are common with Arabic. These Characters are written in cursive form and location and number of dots play an important role in the identification of characters. The sentences are written from right to left in contrast to the Latin languages. Properties of Farsi/Arabic characters have been given in [1-4] in details. Due to the continuity of Farsi and Arabic texts, it is more difficult to identify these characters than Latin characters, especially when we have dealing with various fonts. Most available OCR systems have been designed for recognition of Latin, Chinese, and Japanese characters [5-9]. Systems developed for identifying Farsi/Arabic characters are not still so efficient and leave much place for further investigations in this field. Fig. 1 shows Farsi characters, while Fig. 2 illustrates a few Farsi sentences where the separation of words but continuity of Hesam Izakian, is an MSC student at the department of computer engineering, faculty of engineering, university of Isfahan, Iran (e-mail: izakian@comp.ui.ac.ir). S. Amirhassan Monadjemi, is an assistant professor at the department of computer engineering, faculty of engineering, university of Isfahan, Iran (e- mail: monadjemi@eng.ui.ac.ir). Behrouz Tork Ladani, is an assistant professor at the department of computer engineering, faculty of engineering, university of Isfahan, Iran (e- mail: ladani@eng.ui.ac.ir). Kamran Zamanifar, is an assistant professor at the department of computer engineering, faculty of engineering, university of Isfahan, Iran (e-mail: zamanifar@eng.ui.ac.ir). letters within a word is obvious. Fig. 3 shows some of the Farsi characters in different standard MS-Windows fonts. Fig. 1 The Farsi alphabets and their pronunciations, from top right to the bottom left Fig. 2 Farsi Poems Multi-Font Farsi/Arabic Isolated Character Recognition Using Chain Codes H. Izakian, S. A. Monadjemi, B. Tork Ladani, and K. Zamanifar T World Academy of Science, Engineering and Technology Vol:2 2008-07-27 58 International Science Index Vol:2, No:7, 2008 waset.org/Publication/301