ABSTRACT

This paper deals with the theoretical analysis of Devanagari script according to machine recognition perspective. An individual having good knowledge of the script of a language can easily read some words written on a paper pertaining to that script, though these are expressed in very bad manner, on the basis of his/her mental dictionary. Such words may not be easy to read through a machine as there may be various irregularities caused in expressing these words which are not easy to handle by a machine. A word in Devanagari script can be divided into three vertical regions i.e. the upper, the lower and the middle. The irregularities caused can belong to the upper, the lower and the middle region in a hand-printed word. Some common irregularities in writing Devanagari script are reported here. The various problems likely to be faced in machine recognition process pertaining to the words of Devanagari script are also detailed. Each individual writes uniquely. The writing of a writer may be very good or very bad. Some awkward styles of writing, due to which a lot of difficulties are faced in machine recognition process, are also discussed in detail.