Script Identification from Handwritten Document

Abstract

Every country has their own language and script. This may or may not common to other countries. To communicate with each other we need to have a common language. English is the language that is performing that role. So most of the countries (other than Roman) use bi-script documents. But for countries like India where we have a total of 12 official scripts (and 22 languages) things are more complex. So to have an OCR we need to identify the script by which the script the document is written (even the document is not itself multi-script). Postal document, pre-printed forms are good example of such documents. So identification of the script from a document may be written with any of these 13 scripts is a very challenging work. In this paper we have tried to identify scripts written by any of the 6 official languages of India. Here we have used very simple and efficient feature at component level for the same. Using Fractal-based features, component based feature and Topological features, series of classifiers were used. Overall accuracy of the proposed system is at present 89.48% on the test set without rejection.