- مبلغ: ۸۶,۰۰۰ تومان
- مبلغ: ۹۱,۰۰۰ تومان
Machine simulation of human reading has been the subject of intensive research for almost three decades. A large number of research papers and reports have already been published on Latin, Chinese and Japanese characters. However, little work has been conducted on the automatic recognition of Arabic characters because of the complexity of printed and handwritten text, and this problem is still an open research field. The main objective of this paper is to present the state of Arabic character recognition research throughout the last two decades.
Character recognition systems can contribute tremendously to the advancement of the automation process and can improve the interaction between man and machine in many applications, including office automation, check verification and a large variety of banking, business and data entry applications.
The different approaches covered under the general term character recognition fall into either the on-line or off-line category, each having its own hardware and recognition algorithms.
In on-line character recognition systems, the computer recognizes the symbols as they are drawn.(1~4) The most common writing surface is the digitizing tablet, which operates through a special pen in contact with the surface of the tablet and emits the coordinates of the plotted points at a constant frequency. Breaking contact prompts the transmission of a special character. Thus, recording on the tablet produces strings of coordinates separated by signs indicating when the pen has ceased to touch the tablet surface.
This paper presented the problems related to printed and handwritten Arabic characters, and much of the important research work was briefly described in an attempt to present the current status of Arabic character recognition research. This is still an open research area and there is no commercial Arabic OCR system available yet. This is because of the segmentation problem, which is in fact similar to the segmentation of cursive script in many languages, and because of the complexity of Arabic characters. Moreover, all the algorithms presented in this paper deal with unvocalized text and the recognition of vowel diacritics is an extremely important research area in the Arabic language.
However, it is very difficult to give comparative results for the methods proposed so far. Most of the methods used for Arabic handwriting were tested on small and different Databases created by only a few people as there is not any common Arabic Database available. This is also true for all the methods used for printed Arabic characters. This is the reason why the results in the previous sections, which are dedicated to the description of the techniques, were not included.
As stated previously, no vital computational techniques in this area have yet been fully explored. As such, this field is of importance for future research.