Detection and compensation of undesirable discontinuities within the FarsiArabic subwords

Abstract EN

In this paper, an unexplored subject in the domains of Farsi/Arabic handwritten word preprocessing is introduced.

Sub words play a vital role in many applications such as cheque amount recognition, text recognition, lexicon reduction and sub word-based word recognition.

Correcting the faults occurred in sub words will improve the overall performance of these applications.

A sub word is a connected-component in the main body of a word.

The occurrence of a discontinuity in a sub word, divides the sub word into two isolated parts.

These parts are detected as two incorrect sub words.

In our algorithm, before correcting these faults, the baseline of each sub word is corrected using the proposed baseline correction method.

Then, to limit the exploration area in matching stage, the dots are removed.

Undesirable discontinuities in sub words are detected by using a template matching algorithm.

Disconnected parts of a sub word are joined together by using three different methods.

Experiments show that the cubic polynomial-based compensation method causes the best results and 2.87 % improvement in the sub word recognition rate.