Recognition of Modification-based Scripts Using Direction Tensors

The research on the OCR technology for the Latinbased scripts has been successful in achieving the status of image scanners with built-in OCR facility. But, a majority of modification-based scripts such as Brahmi descended South Asian or Ethiopic scripts are still progressing to achieve this status. This indicates the difficulties in adopting the recognition methods that have been proposed so far for the Latin-based scripts to modification-based scripts. In this paper we propose a novel method that can be adopted to recognise modification-based printed scripts consisting of a large character set, without the need for prior segmentation. The major strength of this method is that, the direction features that are used as the main principle for recognition, are further used in the separation of confusing characters, detection of skew angle, segmentation of script and graphic objects which substantially improves the computation efficiency. Algorithms developed initially for the Brahmi descended Sinhala script used in Sri Lanka, have been extended successfully for the Ethiopic script which has been evolved in a different geographical region, yielding consistently accurate results. Together, these two scripts are used by a population of ninety million.